WO2023152056A1

WO2023152056A1 - Computer-implemented method for controlling and/or monitoring at least one particle foam molding process

Info

Publication number: WO2023152056A1
Application number: PCT/EP2023/052728
Authority: WO
Inventors: Andreas Dr. Wollny; Hans Rudolph
Original assignee: Basf Se
Priority date: 2022-02-11
Filing date: 2023-02-03
Publication date: 2023-08-17
Also published as: CN118679044A; TW202346065A

Abstract

A computer-implemented method for controlling and/or monitoring at least one particle foam molding process in at least one particle foam molding machine is proposed. The particle foam molding process is based on a plurality of process parameters. The method comprises the following steps: a) providing a set of input parameters by at least one external processing unit, wherein the set of input parameters comprises at least one simulation model, material specific parameters and particle foam molding machine parameters; b) the external processing unit, simulating a particle foam molding process based on the set of input parameters and determining at least one predicted process parameter of the simulated particle foam molding process by applying an optimizing algorithm in terms of at least one optimization target on the simulation model, wherein the predicted process parameter is provided to the particle foam molding machine via at least one interface; c) performing at least one particle foam molding process using the particle foam molding machine based on the predicted process parameter for generating at least one workpiece, determining at least one property of the generated workpiece and comparing the property with the optimization target, wherein, in case the property of the generated workpiece deviates from the optimization target, at least one process parameter of the particle foam molding machine is adapted depending on the comparison, and the particle foam molding process, determining of the property of the generated workpiece, and comparing the property with the optimization target is repeated with adapted process parameter until the property of the generated workpiece is in accordance with the optimization target at least within pre-defined tolerances; d) determining at least one actual process parameter of the particle foam molding process and comparing the actual process parameter and the predicted process parameter and adapting the simulation model based on the comparison.

Description

Computer-implemented method for controlling and/or monitoring at least one particle foam molding process

Description

Technical Field

The invention relates to a computer-implemented method for controlling and/or monitoring at least one particle foam molding process, a computer program, a computer-readable storage medium and an automated control system. Such methods, systems and devices can, in general, be employed for technical design or configuration purposes e.g. in a development or production phase of an particle foam molding process. However, further applications are possible.

Background art

Foams, especially particle foams, have long been known and have been widely described in the literature, e.g. in Ullmann's "Encyclopedia of Technical Chemistry", 4th edition, volume 20, p. 416 ff.

Highly elastic, largely closed-cell foams, such as particle foams made of thermoplastic elastomers, which e.g. are produced in an autoclave or by an extruder process show special dynamic properties, and in some cases also good rebound resilience. Hybrid foams made from particles of thermoplastic elastomers and system foam or binders are also known. Depending on the foam density, the manufacturing method and the matrix material, a relatively broad level of rigidity can be adjusted. The properties of the foam can also be influenced by post-treatment of the foam, such as tempering, or molding the particle foam in a mold, such as steam chest molding.

Foamed pellets, which are also referred to as particle foams (or bead foams, particle foam), and molded articles made therefrom, based on thermoplastic polyurethane or other elastomers, are known (for example WO 94/20568A1 , WO 2007/082838 A1 , WO2017/030835 A1 , WO 2013/153190 A1 , WO2010/010010 A1) and can be used in many different ways.

A foamed pellet or also a particle foam or bead foam in the sense of the present invention refers to a foam in the form of a particle, the average length of the particles preferably being in the range of from 1 to 14 mm, preferred 2-13 mm, most preferred 3-12 mm and in particular preferred 9.5 mm. In the case of non-spherical, e.g. elongated or cylindrical, particles, length means the longest dimension. Typically, the foam beads I particle foams are further processed to obtain a molded article based on particle foams. Such molded article, are also named particle foam moldings or workpieces, which are obtained or obtainable by a process according to the present invention.

The quality parameters and properties of particle foams (e.g. expanded thermoplastic polyurethane beads (E-TPLI)) can vary from batch to batch. These different properties can have an influence on the further processing of the particle foams, in particular the process of molding I fusing the particle foam beads together. Thus, the batch to batch variations have an influence on the produced molded parts I workpieces.

Particle foam molding processes are common manufacturing processes in small and large scale manufacturing industry. In typical particle foam molding processes foamed beads, e.g. based on a thermoplastic, thermosetting or elastomer material, is fused together in a mold by methods comprising mechanical processes, mechanical devices, gluing, adhesive additives, pressing, hot-pressing, X-ray, microwaves, elevated temperature above room temperature, steam, hot steam, or combinations thereof, which can be applied for adhering together particle foam material in a mold. The obtained material then adheres together, in order to remain in the form given by the die, thereby becoming the manufactured product. It allows reproduction of the products formed by the die in large quantities. Due to high costs for designing and configuring the die, the die cannot be easily modified if any problems occur during particle foam molding process. Thus, in order to minimize production costs and waste, simulation the molding process of fusing beads in the die or mold cavity would be desirable.

For comparable forming processes like injection molding, simulation, for example from Moldflow, can be used to optimize a tool and the filling process for a given part. Moldflow has two core products: Moldflow Adviser which provides manufacturability guidance and directional feedback for standard part and mold design, and Moldflow Insight which provides definitive results for flow, cooling, and warpage along with support for specialized molding processes, see en.wikipedia.org/wiki/Moldflow.

It is known that optimization procedures can be implemented within the injection molding machine itself, e.g. from DE 10 2013 111 257 B3, DE 10 2018 107 233 A1 or EP3294519B1.

On other technical fields such as for chemical processes further optimization methods are known such as described in WO 2019/138118, WO 2019/138120, WO 2019/138122.

US 2020/0293011 describes a system for producing a product, the system comprising a production facility and an information processing device comprising a computer processor. The com- puter processor generates one or more production condition candidates; determines, using a prediction model, a prediction of a production result of a case in which the product is produced under the one or more production candidates; and generates an evaluation of each of the one or more production condition candidates. The computer processor repeats the process ii) while changing between the one or more production candidates, and determines the production condition candidate, the evaluation of which in the process iii) satisfies a predetermined standard, to be the production condition under which the product is to be produced. The computer processor outputs the determined production condition, and the production facility produces the product under the outputted production condition.

US 5 900 259 A describes a molding condition optimizing system for an injection molding machine comprising plastic flow condition optimizing section and an operating condition determining section. The plastic flow condition optimizing section carries out a plastic flow analysis on a molded part model and determines an optimum flow condition in a filling stage and a packing stage of an injection molding process of the injection molding machine by repeatedly executing an automated calculation using the result of the plastic flow analysis and the plastic flow analysis itself. The operating condition determining section comprises an injection-side condition determining section for determining an optimum injection-side condition of the injection molding machine according to the optimum flow condition obtained by the plastic flow condition optimizing means and a knowledge database with respect to an injection condition, and a clampingside condition determining section for determining an optimum clamping-side condition according to the molded part form data generated by the plastic flow condition optimizing means, the result of the plastic flow analysis, mold design data, and a knowledge database with respect to a mold clamping condition.

US 2018/181694 A1 describes a method of optimizing a process optimization system for a molding machine which includes setting a setting data by a user on the actual molding machine, obtaining first values for at least one descriptive variable of the molding process based on the setting data set and/or on the basis of the cyclically carried out molding process, and obtaining second values for the at least one descriptive variable based on data from the process optimization system. According to a predetermined differentiating criterion, it is checked whether the first values and the second values differ from each other. If the checking shows that the first values and the second values differ from each other, the process optimization system is modified such that, when applied to the molding machine and/or the molding process, the first values for the descriptive variable substantially result instead of the second values for the descriptive variable.

WO 2019/106499 A1 describes a method for processing molding parameters for an injection molding machine obtained by CAE. The CAE simulation generates simulation results, first ma- chine parameters are generated by electronically processing the simulation results, second machine parameters are obtained, different from the first ones, from the execution of another molding process for the same object; and in an electronic database accessible by a user the first and second machine parameters are saved associating them in a common collection. In a further variation, the last method step is replaced by processing the first and second machine parameters with a software and modifying the machine parameters calculated with a subsequent CAE simulation as a function of the processing produced by said software.

US 2006/224540 A1 describes test molding and mass-production molding which are performed by an injection molding machine that includes a control apparatus in which neural networks are used. A quality prediction function determined based on the test molding is revised as necessary during mass-production molding.

EP 0 368 300 A2 describes an optimum molding condition setting system for an injection molding machine. The system comprises a molten material flow analysis means for analyzing a resin flow, a resin cooling and a structure/strength of molded products by using a designed model mold and also comprises an analysis result evaluation means for determining an initial molding condition and its permissible range in accordance with the analysis results. The initial molding condition is set into the injection molding machine and a test shot is carried out in order to check for a deficiency of a molded product. If the deficiency of the molded product has found out, a data of the deficiency is entered into a molding defect elimination means.

Despite the advantages involved in recent molding process optimization and simulation methods, several technical challenges remain, in particular for the application of simulation methods for particle foam molding. Thus, still, simulating and optimizing the molding process may be very time-consuming and complex, and required computation capacities may still be excessively high which may be impossible to be realized within the particle foam molding machine itself due to the fact that the particle foam molding machine has to produce workpieces and no simulation results. Further, it would be desirable to even improve known simulation and optimization methods for particle foam molding with respect to efficiency and precision of the simulation and the optimization process.

Problem to be solved

It is therefore desirable to provide means and methods which address the above-mentioned technical challenges. Specifically, methods, systems, programs and databases shall be proposed for further improve performance of simulating and optimizing a particle foam molding process, compared to devices, methods and systems known in the art, in particular in terms of efficiency and precision. This problem is addressed by the methods, systems, programs and databases with the features of the independent claims. Advantageous embodiments which might be realized in an isolated fashion or in any arbitrary combinations are listed in the dependent claims.

As used in the following, the terms “have”, “comprise” or “include” or any arbitrary grammatical variations thereof are used in a non-exclusive way. Thus, these terms may both refer to a situation in which, besides the feature introduced by these terms, no further features are present in the entity described in this context and to a situation in which one or more further features are present. As an example, the expressions “A has B”, “A comprises B” and “A includes B” may both refer to a situation in which, besides B, no other element is present in A (i.e. a situation in which A solely and exclusively consists of B) and to a situation in which, besides B, one or more further elements are present in entity A, such as element C, elements C and D or even further elements.

Further, it shall be noted that the terms “at least one”, “one or more” or similar expressions indicating that a feature or element may be present once or more than once typically will be used only once when introducing the respective feature or element. In the following, in most cases, when referring to the respective feature or element, the expressions “at least one” or “one or more” will not be repeated, non-withstanding the fact that the respective feature or element may be present once or more than once.

Further, as used in the following, the terms "preferably", "more preferably", "particularly", "more particularly", "specifically", "more specifically" or similar terms are used in conjunction with optional features, without restricting alternative possibilities. Thus, features introduced by these terms are optional features and are not intended to restrict the scope of the claims in any way. The invention may, as the skilled person will recognize, be performed by using alternative features. Similarly, features introduced by "in an embodiment of the invention" or similar expressions are intended to be optional features, without any restriction regarding alternative embodiments of the invention, without any restrictions regarding the scope of the invention and without any restriction regarding the possibility of combining the features introduced in such way with other optional or non-optional features of the invention.

In a first aspect of the invention a computer-implemented method for controlling and/or monitoring at least one particle foam molding process in at least one particle foam molding machine is disclosed. The term “computer-implemented” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a process which is fully or partially implemented by using a data processing means, such as data processing means comprising at least one processor. The term “computer”, thus, may generally refer to a device or to a combination or network of devices having at least one data processing means such as at least one processor. The computer, additionally, may comprise one or more further components, such as at least one of a data storage device, an electronic interface or a human-machine interface. The term “processor” or “processing unit” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to an arbitrary logic circuitry configured for performing basic operations of a computer or system, and/or, generally, to a device which is configured for performing calculations or logic operations. In particular, the processor may be configured for processing basic instructions that drive the computer or system. As an example, the processor may comprise at least one arithmetic logic unit (ALU), at least one floating-point unit (FPU), such as a math coprocessor or a numeric coprocessor, a plurality of registers, specifically registers configured for supplying operands to the ALU and storing results of operations, and a memory, such as an L1 and L2 cache memory. In particular, the processor may be a multicore processor. Specifically, the processor may be or may comprise a central processing unit (CPU). Additionally or alternatively, the processor may be or may comprise a microprocessor, thus specifically the processor’s elements may be contained in one single integrated circuitry (IC) chip. Additionally or alternatively, the processor may be or may comprise one or more application-specific integrated circuits (ASICs) and/or one or more field-programmable gate arrays (FPGAs) or the like.

The term “molding process” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a process or procedure of shaping at least one material into an arbitrary form or shape. The term “particle foam molding process” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a type of molding process performed by fusing particle foam material in a mold.

Further understood as molding process in the context of the present invention are methods comprising mechanical processes, mechanical devices, gluing, adhesive additives, pressing, hot-pressing, X-ray, microwaves, elevated temperature above room temperature, steam, hot steam, or combinations thereof, which can be applied for adhering together particle foam material in a mold.

The preparation of the corresponding moldings can be carried out according to the skilled person known methods.

A preferred method for the preparation of a foam molding part includes the following steps:

(A) Inserting foamed granules I particle foam according to the invention in a corresponding form,

(B) Fusing of the foamed granules I particle foam according to the invention from step (A).

The fusion in step (B) is preferably carried out in a closed form, wherein the fusion can be carried out by water vapor, hot air (as e.g. described in EP1979401) or energetic radiation (microwaves or radio waves).

The temperature at the fusion of the foamed granules is preferably below or close to the melting temperature of the polymer from which the particle foam was produced. For the common polymers, therefore, the temperature for fusion of the foamed granules is between 100°C and 180°C, preferably between 120°C and 150°C.

Temperature profiles I residence times can be determined individually, e.g. in analogy to the methods described in the LIS20150337102 or EP2872309.

Fusing by energetic radiation is generally carried out in the frequency range of microwaves or radio waves, if necessary in the presence of water or other polar liquids, such as polar groups having microwave-absorbing hydrocarbons (such as esters of carboxylic acids and diols or triols or glycols and liquid polyethylene glycol) and can be carried out in analogy to the methods described in EP3053732 or WO16146537.

According to the present invention, fusing the particle foam (foamed pellets) is preferably carried out in a mold to shape the molded body obtained. In principle, all suitable methods for fusing foamed pellets can be used according to the present invention, for example fusing at elevated temperatures, such as for example steam chest molding, molding at high frequencies, for example using electromagnetic radiation, processes using a double belt press, or variotherm processes.

The thermoplastic polymer foam from which the molded body is manufactured can be any opencell or closed-cell polymer foam that can be produced from a thermoplastic. The thermoplastic polymer foam is particularly preferably a molded foam. The production of the molding made of the polymer foam can be achieved in any desired manner known to the person skilled in the art: by way of example, webs made of a foamed polymer can be produced, and the moldings can be cut out from the webs. If the polymer foam from which the molding has been produced is a molded foam, the molding can be produced by any process known to the person skilled in the art for the production of moldings made of a molded foam: it is possible by way of example to charge pellets made of an expandable thermoplastic polymer to a mold, to expand the pellets to give foam beads by heating, and then to use pressure to bond the hot foam beads to one another. The pressure is generated here via the foaming of the beads, the volume of which increases while the internal volume of the mold remains the same. Uniform heating can be achieved by way of example by passing steam through the mold. However, it is alternatively also possible to charge pre-expanded beads to the mold. In this case, the procedure begins with complete filling of the mold. In a further step, the volume of the mold is reduced by insertion of a ram at the feed aperture, which has likewise been completely filled with expanded beads, and the pressure in the mold is thus increased. The expanded beads are thus pressed against one another and can therefore become fused to give the molding. Here again, the fusion of the beads is in particular achieved via passage of steam through the system.

The injection process used to apply the thermoplastic polymer can by way of example be an injection molding process, a transfer-molding process, or an injection compression-molding process. It is possible on the one hand to insert the molding made of thermoplastic polymer into a mold for the injection molding process, transfer-molding process, or injection compressionmolding process, and then to apply the thermoplastic polymer. Alternatively, it is also possible to utilize, for the over molding process, the mold in which the molding made of the polymer foam is also produced. It is usual to use, for this purpose, molds with displaceable core. If the intention is that the thermoplastic polymer be applied only to one side of the molding made of polymer foam, it is alternatively also possible, after the production of the molding made of polymer foam, to remove one mold half, and to seal the second mold half in which the molding is still present by using another mold half into which the thermoplastic polymer for the functional layer is then injected or forced.

For fusing with radiofrequency electromagnetic radiation, the particle foams can preferably be wetted with a polar liquid, which is suitable to absorb the radiation, for example in proportions of 0.1 to 10 wt .-%, preferably in proportions of 1 to 6 wt .-%, based on the used particle foams. Fusing with radiofrequency electromagnetic radiation of the particle foams can be achieved in the context of the present invention even without the use of a polar liquid. The thermal connection of the foam particles takes place, for example, in a form by means of radiofrequency electromagnetic radiation, in particular by means of microwaves. Electromagnetic radiation with fre- quencies of at least 20 MHz, for example of at least 100 MHz, is understood to be high frequency. As a rule, electromagnetic radiation is used in the frequency range between 20 MHz and 300 GHz, for example between 100 MHz and 300 GHz. Microwaves are preferred in the frequency range between 0.5 and 100 GHz, especially preferably 0.8 to 10 GHz and irradiation times between 0.1 and 15 minutes are used. Preferably, the frequency range of the microwave is adjusted to the absorption behavior of the polar liquid or vice versa the polar liquid is selected based on the absorption behavior according to the frequency range of the used microwave device. Suitable methods are described, for example, in WO2016/146537.

Due to the good mechanical properties and the good temperature behavior, the polymer foams according to the invention are particularly suitable for the preparation of moldings. Molded bodies can be prepared from the foamed granules I particle foam according to the invention, for example by fusing or gluing.

The term “mold” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a die or form, e.g. a form giving matrix or frame. In particular, as used herein, the mold may refer to an arbitrary die and/or form comprising at least one cavity, such as at least one form giving structure and/or cut-out. The mold may specifically be used in the particle foam molding process, wherein at least one type of particle foam material may be provided in at least one cavity of the mold. For sake of simplicity, herein, the terms “mold” and “mold cavity” may be used interchangeably. As an example, the mold having the at least one cavity may be used in the molding process for forming the material. In particular, the particle foam material added into the cavity of the mold may be given a negative form and/or geometry of the cavity. Specifically, the mold may be used for manufacturing at least one workpiece, also denoted as component, wherein the manufactured workpiece may have a negative form and/or shape of the mold cavity.

The molding process may be configured for manufacturing at least one workpiece. The term “workpiece” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to an arbitrary part or element. In particular, the workpiece may be or may comprise a constituent member of an arbitrary machine or apparatus. The workpiece may, for example, at least partially have a negative shape of the mold or of a cavity of the mold used in the molding process for manufacturing the component. Thus, the particle foam molding process may be or may refer to a form-giving procedure for creating the workpiece. Applications of the workpieces (molded articles) based on particle foams can be the following: Use of particle foam based molding / workpiece as shoe intermediate soles, shoe insoles, shoe combination soles, bicycle saddles, bicycle tires, vehicle tires, cushioning elements, upholstery, mattresses, bases, handles, protective foils, in components in the interior and exterior of the automobile, in balls and sports equipment or as floor coverings, in particular for sports areas, athletics tracks, sports halls, children's playgrounds and sidewalks.

Preferred is the use of a particle foam according to the invention for the preparation of a molded body for shoe midsoles, shoe insoles, shoe combination soles or upholstery element for shoes. Here, the shoe is preferably a street shoe, sports shoe, sandal, boot or safety shoe, especially preferred are sport shoes.

Further subject-matter of the present invention is therefore also a molding body, wherein the shape is a shoe combination sole for shoes, preferably for street shoes, sports shoes, sandals, boots or safety shoes, especially preferably sports shoes.

Further object of the present invention is therefore also a molded body, wherein the molding is a midsole for shoes, preferably for street shoes, sports shoes, sandals, boots or safety shoes, particularly preferably sports shoes. Further object of the present invention is therefore also a molded body, wherein the molding is an insert for shoes, preferably for street shoes, sports shoes, sandals, boots or safety shoes, particularly preferably sports shoes.

Further object of the present invention is therefore also a molded body, wherein the molding is an upholstery element for shoes, preferably for street shoes, sports shoes, sandals, boots or safety shoes, particularly preferably sports shoes. Here, the upholstery element can be used e.g. in the heel area or front foot area. Further object of the present invention is therefore also a shoe in which the molded body according to the invention is used as a midsole, midsole or upholstery in the e.g. heel area, front foot area, wherein the shoe is preferably a street shoe, sports shoe, sandal, boot or safety shoe, particularly preferably a sports shoe.

The term “particle foam molding machine” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to an arbitrary device or machine configured for performing the particle foam molding process. The particle foam molding machine may comprise at least one particle foam forming unit.

The particle foam molding process is based on a plurality of process parameters. The term “process parameter” as used herein is a broad term and is to be given its ordinary and custom- ary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to at least one settable and/or selectable and/or adjustable and/or configurable parameter influencing the particle foam molding process. The process parameters may relate to operating conditions of the particle foam molding machine. In particular, the process parameter may be a particle foam molding machine parameter. For example, the process parameters may comprise one or more of a polymer melt temperature, barrel temperature, filling time, silo pressure, air pressure, autoclave time, cross steam time, particle foam forming unit temperature, steam pressure, holding pressure, holding time, cooling or curing time, crack, cooling or curing parameters such as cooling or curing medium throughput, cooling or curing medium temperature. The particle foam molding machine parameter may further comprise dimensions of the machine such as particle foam forming unit, equipment of the machine such as cylinder diameter or maximum cylinder temperature and the like.

The term “control” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to determining and/or adjusting at least one process parameter. The term “monitoring” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to quantitative and/or qualitative determining at least one process parameter.

The computer-implemented method comprises the following steps, which may be performed in the given order. However, a different order may also be possible. Further, one or more than one or even all of the steps may be performed once or repeatedly. Further, the method steps may be performed in a timely overlapping fashion or even in parallel. The method may further comprise additional method steps which are not listed.

The method comprises the following steps: a) providing a set of input parameters by at least one external processing unit, wherein the set of input parameters comprises at least one simulation model, material specific parameters and particle foam molding machine parameters; b) the external processing unit, simulating a particle foam molding process based on the set of input parameters and determining at least one predicted process parameter of the simulated particle foam molding process by applying an optimizing algorithm in terms of at least one optimization target on the simulation model, wherein the predicted process parameter is provided to the particle foam molding machine via at least one interface; c) performing at least one particle foam molding process using the particle foam molding machine based on the predicted process parameter for generating at least one workpiece, de- termining at least one property of the generated workpiece and comparing the property with the optimization target, wherein, in case the property of the generated workpiece deviates from the optimization target, at least one process parameter of the particle foam molding machine is adapted depending on the comparison, and the particle foam molding process, determining of the property of the generated workpiece, and comparing the property with the optimization target is repeated with adapted process parameter until the property of the generated workpiece is in accordance with the optimization target at least within predefined tolerances; d) determining at least one actual process parameter of the particle foam molding process and comparing the actual process parameter and the predicted process parameter and adapting the simulation model based on the comparison.

The term “external processing unit” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to at least one processing unit designed separately from the particle foam molding machine. The particle foam molding machine may comprise an internal processing unit, which, in particular, is configured for controlling and monitoring machine parameters. The external processing unit may be configured for transferring and/or receiving data to the internal processing unit via at least one communication interface. The internal processing unit may be configured to transfer and/or to receive data to the external processing unit via at least one communication interface. The external processing unit may comprise a plurality of processors. The external processing unit may be and/or comprises a cloud computing system.

The external processing unit may comprise at least one database. The term “database” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to an arbitrary collection of information. The database may be stored in at least one data storage device. In particular, the database may contain an arbitrary collection of information. The data storage device may be or may comprise at least one element selected from the group consisting of: at least one server, at least one server system comprising a plurality of servers, at least one cloud server or cloud computing infrastructure.

The term “communication interface” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to an item or element forming a boundary configured for transferring information. In particular, the communication interface may be configured for transferring information from a computational device, e.g. a computer, such as to send or output information, e.g. onto another device. Additionally or alternatively, the communication interface may be configured for transferring information onto a computational device, e.g. onto a computer, such as to receive information. The communication interface may specifically provide means for transferring or exchanging information. In particular, the communication interface may provide a data transfer connection, e.g. Bluetooth, NFC, inductive coupling or the like. As an example, the communication interface may be or may comprise at least one port comprising one or more of a network or internet port, a USB-port and a disk drive. The communication interface may be at least one web interface.

The term “providing” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to retrieving and/or selecting the set of input parameters. The term “retrieving” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to the process of a system, specifically a computer system, generating data and/or obtaining data from an arbitrary data source, such as from a data storage, from a network or from a further computer or computer system. The retrieving specifically may take place via at least one computer interface, such as via a port such as a serial or parallel port. The retrieving may comprise several sub-steps, such as the sub-step of obtaining one or more items of primary information and generating secondary information by making use of the primary information, such as by applying one or more algorithms to the primary information, e.g. by using a processor.

The term “set of input parameters” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to information about the simulation model, material specific parameters and particle foam molding machine parameters.

The term “particle foam molding machine parameters” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to parameters influencing the operating conditions of the particle foam molding machine. The particle foam molding machine parameters may comprise setting of machine components of the particle foam molding machine. The particle foam molding machine parameters may comprise specific values and/or parameter profiles. The particle foam molding machine parameters may comprise at least one parameter selected from the group consisting of: filling time, polymer melt temperature, barrel temperature, particle foam forming unit temperature, silo pressure, air pressure, steam pressure, holding pressure, autoclave time, holding time, cooling or curing time, cross steam time, crack, cooling or curing parameters such as cooling or curing medium throughput, cooling or curing medium temperature.

The term “material specific parameters” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to information about the material or materials used for the particle foam molding process. The material specific parameters may be provided by material suppliers and/or may be downloaded from a website or other database. Material suppliers may have a lot of product specific data, like rheological data, viscosity, tensile strength of the particle foam material and lot specific data for every material produced. The material specific parameters comprise at least one parameter selected from the group consisting of: compressibility, flow characteristics, temperature characteristics.

The material, specifically the material used in the molding process, e.g. for manufacturing the workpiece, may for example be or may comprise a plastic material. The term “plastic material” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to an arbitrary thermoplastic, thermosetting or elastomer material. In particular, the plastic material may be a mixture of substances comprising monomers and/or polymers. Specifically, the plastic material may be or may comprise a thermoplastic material. Additionally or alternatively, the plastic material may be or may comprise a thermosetting material. Additionally or alternatively, the plastic material may comprise an elastomer material.

In a preferred embodiment the particle foam material is selected from the group consisting of polyurethane, polyamide, polyolefin, polypropylene, polyethylene, polystyrene and mixtures thereof.

In a preferred embodiment the particle foam material is a thermoplastic elastomer and is selected from the group consisting of thermoplastic polyurethanes (TPU), thermoplastic polyamides (TPA) and thermoplastic polyetheresters (TPC), thermoplastic polyesteresters (TPC), thermoplastic vulcanizates (TPV), thermoplastic polyolefins (TPO), thermoplastic styrenic elastomers (TPS) and mixtures thereof.

The term “simulation” or “simulating” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a process for, specifically approximately, imitating of the real particle foam molding process. The term “simulation model” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to at least one model based on which the simulation is performed. The simulation model may be generated by the software on the external processing unit or the simulation model may be a data set in the software.

The simulation model may comprise at least one trained and trainable model. The term “trained model” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a mathematical model trained on at least one training data set. The term “trainable model” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to the fact that the simulation model can be further trained and/or updated based on additional training data. Specifically, the simulation model is trained on a training dataset. The simulation model may be trained by using machine learning. The simulation model may be at least partially data-driven by being trained on data from historical production runs. The term “data driven” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to the fact that the model is an empirical, predictive model. Specifically, the data driven model is derived from analysis of experimental data of previous particle foam molding processes. The term “historical production run” refers to particle foam molding processes in the past or at an earlier time point. Specifically, for further training of the simulation model, the training data set may be generated from comparison data of actual and predicted process parameter as determined in step d). As used herein, the term “at least partially data-driven model” is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to the fact that the trained model comprises data-driven model parts, wherein it is possible that the model comprises further or other model parts. The term “machine-learning” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a method of using artificial intelligence (Al) for automatically model building of machine-learning models, in particular of prediction models. The external processing unit may be configured for performing and/or executing at least one machine-learning algorithm. The simulation model may be based on the results of at least one machine-learning algorithm. The machine-learning algorithm may comprise decision trees, naive bayes classifications, nearest neighbors, neural networks, convolutional neural networks, generative adversarial networks, support vector ma- chines, linear regression, logistic regression, random forest and/or gradient boosting algorithms. Preferably, the machine-learning algorithm is organized to process an input having a high dimensionality into an output of a much lower dimensionality. Such a machine-learning algorithm is termed “intelligent” because it is capable of being “trained”. The algorithm may be trained using records of training data. A record of training data may comprise training input data and corresponding training output data. The training output data of a record of training data may be the result that is expected to be produced by the machine-learning algorithm when being given the training input data of the same record of training data as input. The deviation between this expected result and the actual result produced by the algorithm may be observed and rated by means of a “loss function”. This loss function may be used as a feedback for adjusting the parameters of the internal processing chain of the machine-learning algorithm. For example, the parameters may be adjusted with the optimization goal of minimizing the values of the loss function that result when all training input data is fed into the machine-learning algorithm and the outcome is compared with the corresponding training output data. The result of this training may be that given a relatively small number of records of training data as “ground truth”, the machine-learning algorithm is enabled to perform its job well for a number of records of input data higher by many orders of magnitude. Thus, the simulation model may comprise at least one algorithm and model parameters. Parameters of the simulation model may be generated by using at least one artificial neural network. The simulation model, in particular model parameters, may be adapted, and thus, may be further trained, in step d).

The simulation model may comprise a digital twin of the particle foam molding process. The simulation model is configured for simulating a particle foam modeling process. The simulation model may comprise a filling simulation. Specifically, the simulation model may be configured for simulating of a filling of the mold cavity with particle foams of at least one material. The simulation model may be configured for simulating of a manufacturing of the workpiece. The simulation model may be configured for simulating geometry and/or shape of the workpiece. The simulation model may comprise a strength analysis.

The simulation model may use geometrical data of a workpiece to be manufactured. The term “geometrical data” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to information on a three- dimensional form or shape of an arbitrary object or element. Specifically, the geometrical data, such as the information on a three-dimensional shape, may be present in a computer-readable form, such as in a computer compatible data set, specifically a digital data set. As an example, the geometrical data may be or may comprise computer-aided-design-data (CAD data). Specifi- cally, three-dimensional geometrical data may be or may comprise CAD data describing the form or shape of the object or element.

The simulation model may be configured for considering material specific properties. The simulation model may comprise a digital twin of the material. The simulation model may be configured for considering batch properties of raw material batches such as tensile strength of the particle foam material batch. The simulation process is not performed on the particle foam molding machine itself but is performed by the external processing unit such as by at least one cloud computing system. This may allow taking into account, in addition to machine parameters and/or sensor parameters provided by the particle foam molding machine and/or at least one sensor thereof and/or available in the particle foam molding machine, additional parameters influencing the particle foam molding process. These additional parameters may relate to external knowledge e.g. knowledge of a material supplier, such as product specific data, like rheological data, viscosity, tensile strength of the particle foam material and/or algorithms, and/or specific data for produced material.

Using simulation data, process data and product related data in a cloud based process optimizing of the particle foam molding process may be possible. As outlined above, material suppliers may have a lot of product specific data, like rheological data, viscosity, tensile strength of the particle foam material and lot specific data for every material produced. The present invention proposes a closed loop between the simulation and the particle foam molding process such that parameters from the simulation can directly be used in the particle foam molding process. Moreover, the other way round, process data can be used to optimize the modelling process using machine learning models. The lot specific information of the material may be further linked to the simulation the manufacturing process by using a cloud based digital twin of the material and the particle foam molding process such that the efficiency of the particle foam molding process can be even further improved.

As used herein, the term “predicted process parameter of the simulated particle foam molding process” is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to expected values of the process parameters, in particular for reaching an optimal manufacturing result and/or optimal usage of resources. The predicted process parameter may be a parameter influencing the particle foam molding process. The predicted process parameter may be determined for optimizing the particle foam molding process. In known systems and devices, such as described in US 5 900 259 A, the optimization is performed in view of workpiece optimization. In contrast, the present invention refers to pro- cess optimization. The process optimization may, in addition to optimal manufacturing result, take into account optimal usage of resources.

Step b) may comprise at least one optimization step. The optimization may be performed by an optimization algorithm. The term “optimization”, as used herein, is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to the process of selecting of a best parameter set with regard to the optimization target from a parameter space of possible parameters. The optimization algorithm may be configured to select the best parameter set with regard to the optimization target from a parameter space of possible parameters. The optimization algorithm may be configured to minimize the deviation between the actual and the target values of the optimization target. The term “optimization target”, as used herein, is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to at least one criterion under which the optimization is performed. The optimization target may comprise at least one optimization goal and accuracy and/or precision. The optimization target may be at least one property of the workpiece. The property of the workpiece may be at least one element selected from the group consisting of: weight of the workpiece, dimensions of the workpiece, surface structure, density, shrinkage, rebound, yield point, tensile strength, elongation at break, abrasion, compression set, stiffness, compression stress at given deformation, cushioning, warping. The optimization target may be pre-specified such as by at least one customer and/or at least one user of the particle foam molding machine. The optimization target may be at least one user’s specification. The user may select the optimization goal and a desired accuracy and/or precision. The predicted process parameter is provided to the particle foam molding machine via at least one interface, in particular via a communication interface. In known systems and devices, such as described in US 5 900 259 A, the parameters defining an injection molding process are stored in an injection molding machine. Thus, usually, the parameters are static. In contrast, the present invention proposes a self-learning method, and in particular, continuous improvement of the performance of particle foam molding process, by adapting the simulation model in step d) taking into account newly determined predicted process parameter in step c) and using the improved simulation model for predicting improved process parameters for performing the at least one particle foam molding process in step c). Therefore, a cycle or loop is proposed by performing steps a) to d).

The method comprises performing at least one particle foam molding process using the particle foam molding machine based on the predicted process parameter for generating at least one workpiece. Using the predicted process parameter for performing the particle foam molding pro- cess may refer to not only relying on machine parameters and/or sensor parameters provided by the particle foam molding machine and/or at least one sensor thereof and/or available in the particle foam molding machine but to take into account in addition external knowledge e.g. knowledge of a material supplier such as product specific data, like rheological data, viscosity, tensile strength of the particle foam, and/or algorithms, and/or particle foam material data, and/or specific data for produced material. Using the predicted process parameter may allow continuously improving the particle foam molding process. The manufactured workpiece may be measured, e.g. by using optical or tactile measurement techniques such as scanning. The term “scanning” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to an arbitrary process or procedure of examining an arbitrary object or data. The scanning may comprise determining shape, performance behavior (e.g. rebound, elasticity) and dimensions of the workpiece. The scanning may specifically be performed automatically. The scanning may be performed autonomously by a computer or computer network.

The determined property of the workpiece may be compared to the optimization target. The comparison may comprise determining deviation from a target-shape and/or target-dimensions, also denoted target-size. The generated workpiece is considered to deviate from the targetshape and/or target-dimensions if a difference of the determined property and the optimization target is above a tolerance limit. The tolerance limit may depend on accuracy such as of the determining of the property and/or customer requirements and the like.

In case the property of the generated workpiece deviates from the optimization target, at least one process parameter of the particle foam molding machine is adapted depending on the comparison. The adaptation of the at least one process parameter may be performed by an optimization algorithm.

For example, the comparison of the determined property of the workpiece with the optimization target may reveal that the workpiece deviates from the desired shape and that, it in particular exhibits twisting, warping, wavy surfaces and angle deviations. The cause for this may be a different shrinkage tendency (shrinkage potential) of the various areas of the workpiece. The shrinkage differences may be caused by different degrees of packing in different areas of the workpiece as well as by different orientations of fibers and polymer chains. Further causes may be that the selected mold temperatures and/or pressures are unfavorable, that the molded workpiece has different thicknesses, that the pressure gradient of the workpiece is too high along the flow path, that the selected cooling time is too short so that the workpiece is removed from the mold at a too high temperature and the workpiece becomes deformed after being re- moved from the mold, that an unfavorable material is being used. At least one of the following process parameters of the particle foam molding machine may be adapted as follows depending on the comparison: changing temperatures for the mold, increasing the cooling time, adapting the process such that the molding is not catching or being held with negative draft, changing the pressure, and changing the holding time. Moreover, in view of the comparison the materials used may be changed. Specifically using low-warpage materials, e. g. blends with an amorphous phase, may be used. Moreover, the workpiece design may be changed. The process parameters of the particle foam molding machine may be adapted with respect to a predetermined hierarchy. For example, first the mold temperature may be adapted, then the cooling time may be adapted. Subsequently the further process parameters may be adapted.

For example, the comparison of the determined property of the workpiece with the optimization target may reveal that the workpiece comprises at least one sink mark. The term “sink mark” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. At least one of the following process parameters of the particle foam molding machine may be adapted as follows depending on the comparison: temperature, pressure. Moreover, the workpiece design may be changed. The process parameters of the particle foam molding machine may be adapted with respect to a pre-determined hierarchy.

The particle foam molding process, determining of the property of the generated workpiece, and comparing the property with the optimization target is repeated with adapted process parameter until the property of the generated workpiece is in accordance with the optimization target at least within pre-defined tolerances. “Is repeated” means that all acts, i.e. the particle foam molding process, determining of the property of the generated workpiece, and comparing the property with the optimization targe are repeated.

Step d) comprises determining at least one actual process parameter of the particle foam molding process. The particle foam molding machine may be configured for measuring and/or monitoring process at least one process parameter during the particle foam molding process. The at least one actual process parameter may be at least one process parameter which is measurable and/or monitorable during the particle foam molding process, e.g. by using at least one sensor. The term “during the particle foam molding process” may refer to the time span between start and end of the particle foam molding process and/or a time span in which process conditions are expected to be essentially comparable to process conditions during the particle foam molding process. The particle foam molding machine may be configured for measuring the process parameters in real time and to adapt the process parameters on the run. The particle foam molding machine may be configured for measuring the at least one actual process parameter in real time. The particle foam molding machine may be configured for adapting the at least one actual process parameter on the run. In case step c) comprises determining a plurality of predicted process parameters, step d) may comprise determining a plurality of process parameters such as a set of process parameters defining the particle foam molding process. The particle foam molding machine may comprise at least one sensor. Measured parameters of the particle foam molding machine may be registered and transferred to the external processing unit. The particle foam molding machine may comprise at least one element selected from the group consisting of: a temperature sensor; a pressure sensor; a clock. For example, the at least one actual process parameter may be at least one parameter selected from the group consisting of polymer melt temperature, barrel temperature, particle foam forming unit temperature, steam pressure, holding pressure, holding time, filling time, cooling or curing time, cooling or curing parameters such as cooling or curing medium throughput, cooling or curing medium temperature, silo pressure, air pressure, autoclave steam pressure, cross steam pressure, crack. Step d) may comprise determining a set of actual process parameters which are to be optimized, in particular actual process parameters corresponding to the process parameters predicted in step c). Thus, not only a single process parameter may be used during the optimization cycle but a plurality of process parameters, in particular a set of process parameters defining the particle foam molding process, may be used.

Step d) further comprises comparing the actual process parameter and the predicted process parameter and adapting the simulation model based on the comparison. In case a plurality of predicted process parameters is determined in step c), step d) further may comprise comparing the respective actual process parameter and the respective predicted process parameter and adapting the simulation model based on the comparison. The comparison may comprise determining deviation of the predicted process parameter from the actual process parameter or view versa. The actual process parameter is considered to deviate from the predicted process parameter if a difference is above a tolerance limit. The tolerance limit may depend on measurement accuracy. The comparison may be performed by the internal processing unit of the particle foam molding machine. The information about the deviation and/or the actual process parameters may be transferred to the external processing unit. The external processing unit may be configured for adapting the simulation model, in particular the model parameters, based on the information about the deviation and/or the actual process parameters. Adapting the simulation model is a standard procedure for a skilled person.

The method further may comprise outputting the predicted process parameter and/or a result of the comparison of the actual process parameter and the predicted process parameter via at least one output interface or port. The output may comprise the set of predicted process parameters and/or results of the comparisons of the actual process parameters and the predicted pro- cess parameters. The term “outputting” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to the process of making information available to another system, data storage, person or entity. As an example, the output may take place via one or more interfaces, such as a computer interface or a human-machine interface. The output, as an example, may take place in one or more of a computer-readable format, a visible format or an audible format. For example, the outputting may be performed via at least one display, at least one microphone and the like.

Method steps a) to d) may be repeated, wherein the adapted simulation model may be used in step a).

In a further aspect of the invention, a computer program comprising instructions which, when the program is executed by a computer or computer system, cause the computer or computer system to carry out the method, in particular steps a) to d), according to the invention. For possible definitions of most of the terms used herein, reference may be made to the description of the computer-implemented method above or as described in further detail below.

Specifically, the computer program may be stored on a computer-readable data carrier and/or on a computer-readable storage medium. As used herein, the terms “computer-readable data carrier” and “computer-readable storage medium” specifically may refer to non-transitory data storage means, such as a hardware storage medium having stored thereon computerexecutable instructions. The computer-readable data carrier or storage medium specifically may be or may comprise a storage medium such as a random-access memory (RAM) and/or a readonly memory (ROM).

Further disclosed and proposed herein is a computer program product comprising instructions which, when the program is executed by a computer or computer system, cause the computer or computer system to carry out the computer implemented method, as described above or as described in further detail below. Thus, for possible definitions of most of the terms used herein, again reference may be made to the description of the method as disclosed in the first aspect of the present invention.

In particular, the computer program product may comprise program code means stored on a computer-readable data carrier, in order to perform the method according to one or more of the embodiments disclosed herein, when the program is executed on a computer or computer network. As used herein, a computer program product refers to the program as a tradable product. The product may generally exist in an arbitrary format, such as in a paper format, or on a com- puter-readable data carrier. Specifically, the computer program product may be distributed over a data network.

Further disclosed and proposed herein is a computer-readable storage medium comprising instructions which, when executed by a computer or computer system, cause the computer or computer system to carry out the computer-implemented method as described above or as described in further detail below. Thus, for possible definitions of most of the terms used herein, again reference may be made to the description of the method as disclosed in the first aspect of the present invention.

In a further aspect, an automated control system for a particle foam molding process in at least one particle foam molding machine is disclosed. The particle foam molding process is based on a plurality of process parameters.

The control system comprises at least one external processing unit is configured for simulating a particle foam molding process based on a set of input parameters comprising at least one simulation model, material specific parameters and particle foam molding machine parameters by applying an optimizing algorithm in terms of at least one optimization target on the simulation model.

The control system comprises at least one interface configured for providing the predicted process parameter to the particle foam molding machine. The control system is configured for performing at least one particle foam molding process using the particle foam molding machine based on the predicted process parameter for generating at least one workpiece. The control system is configured for determining at least one property of the generated workpiece, for comparing the property with the optimization target and for adapting at least one process parameter of the particle foam molding machine depending on the comparison. The control system is configured for repeating the particle foam molding process, the determining of the property, the comparing of the property and the optimization target and the adapting of the process parameters until the property of the generated workpiece is in accordance with the optimization target at least within pre-defined tolerances.

The control system is configured for determining at least one actual process parameter of the particle foam molding process. The control system is configured for comparing the actual process parameter and the predicted process parameter and for adapting the simulation model based on the comparison. The automated control system may be configured for performing the method according to the present invention. Thus, for possible definitions of most of the terms used herein, again reference may be made to the description of the method as disclosed in the first aspect of the present invention.

The methods, systems and programs of the present invention have numerous advantages over methods, systems and programs known in the art. In particular, the methods, systems and programs as disclosed herein may improve the performance of particle foam molding processes, compared to devices, methods and systems known in the art. The simulation can run on cloud solutions. The present invention proposes that in the cloud the simulation model is run to identify optimum parameters (to be process), and that this information can be linked to the actual parameters (as is process) such that a quick and efficient estimation loop is run. By means of a digital identity, the simulation model can also take into account material specific properties to improve even more the simulation.

A combination of an optimization algorithm of the method, the quality parameters of the batch and the machine parameters allow higher quality of the produced parts. The invention relates to a computer-implemented method for controlling and/or monitoring at least one particle foam molding process, a computer program, a computer-readable storage medium and an automated control system. Such methods, systems and devices can, in general, be employed for technical design or configuration purposes e.g. in a development or production phase of a particle molding process. However, further applications are possible.

Summarizing and without excluding further possible embodiments, the following embodiments may be envisaged:

Embodiment 1 A computer-implemented method for controlling and/or monitoring at least one particle foam molding process in at least one particle foam molding machine, wherein the particle foam molding process is based on a plurality of process parameters, wherein the method comprises the following steps: a) providing a set of input parameters by at least one external processing unit, wherein the set of input parameters comprises at least one simulation model, material specific parameters and particle foam molding machine parameters; b) the external processing unit, simulating a particle foam molding process based on the set of input parameters and determining at least one predicted process parameter of the simulated particle foam molding process by applying an optimizing algorithm in terms of at least one optimization target on the simulation model, wherein the predicted process parameter is provided to the particle foam molding machine via at least one interface; c) performing at least one particle foam molding process using the particle foam molding machine based on the predicted process parameter for generating at least one workpiece, determining at least one property of the generated workpiece and comparing the property with the optimization target, wherein, in case the property of the generated workpiece deviates from the optimization target, at least one process parameter of the particle foam molding machine is adapted depending on the comparison, and the particle foam molding process, determining of the property of the generated workpiece, and comparing the property with the optimization target is repeated with adapted process parameter until the property of the generated workpiece is in accordance with the optimization target at least within predefined tolerances; d) determining at least one actual process parameter of the particle foam molding process and comparing the actual process parameter and the predicted process parameter and adapting the simulation model based on the comparison.

Embodiment 2 The method according to the preceding embodiment, wherein method steps a) to d) are repeated, wherein the adapted simulation model is used in step a).

Embodiment 3 The method according to any one of the preceding embodiments, wherein the particle foam molding machine parameters comprise at least one parameter selected from the group consisting of: polymer melt temperature, barrel temperature, particle foam forming unit temperature, steam pressure, holding pressure, holding time, cooling or curing time, cooling or curing parameters.

Embodiment 4 The method according to any one of the preceding embodiments, wherein measured parameters of the particle foam molding machine are registered and transferred to the external processing unit, wherein the particle foam molding machine comprises at least one element selected from the group consisting of: a temperature sensor; a pressure sensor; a clock.

Embodiment 5 The method according to any one of the preceding embodiments, wherein the simulation model comprises a filling simulation.

Embodiment 6 The method according to any one of the preceding embodiments, wherein the simulation model is configured for simulating a filling of a mold cavity with a particle foam of at least one material. Embodiment 7 The method according to any one of the preceding embodiments, wherein the simulation model is configured for simulating geometry and/or shape of the workpiece.

Embodiment 8 The method according to any one of the preceding embodiments, wherein the simulation model comprises a strength analysis.

Embodiment 9 The method according to any one of the preceding embodiments, wherein the material specific parameters comprise at least one parameter selected from the group consisting of: compressibility, flow characteristics, temperature characteristics.

Embodiment 10 The method according to any one of the preceding embodiments, wherein the simulation model is configured for considering material specific properties.

Embodiment 11 The method according to the preceding embodiment, wherein the simulation model is configured for considering batch properties of raw material batches.

Embodiment 12 The method according to any one of the preceding embodiments, wherein the property of the workpiece is at least one element selected from the group consisting of: weight of the workpiece, dimensions of the workpiece, warping.

Embodiment 13 The method according to any one of the preceding embodiments, wherein the optimization target is at least one property of the workpiece.

Embodiment 14 The method according to any one of the preceding embodiments, wherein the method further comprises outputting the predicted process parameter and/or a result of the comparison of the actual process parameter and the predicted process parameter via at least one output interface or port.

Embodiment 15 The method according to any one of the preceding embodiments, wherein parameters of the simulation model are generated by using at least one artificial neural network.

Embodiment 16 The method according to any one of the preceding embodiments, wherein the external processing unit is and/or comprises a cloud computing system.

Embodiment 17 A computer program comprising instructions which, when the program is executed by a computer or computer system, cause the computer or computer system to carry out the method according to any one of the preceding embodiments. Embodiment 18 A computer-readable storage medium comprising instructions which, when executed by a computer or computer network, cause to carry out the method according to any one of the preceding embodiments referring to a method.

Embodiment 19 Automated control system for an particle foam molding process in at least one particle foam molding machine, wherein the particle foam molding process is based on a plurality of process parameters, wherein the control system comprises at least one external processing unit, wherein the external processing unit is configured for simulating an particle foam molding process based on a set of input parameters comprising at least one simulation model, material specific parameters and particle foam molding machine parameters by applying an optimizing algorithm in terms of at least one optimization target on the simulation model, wherein the control system comprises at least one interface configured for providing the predicted process parameter to the particle foam molding machine, wherein the control system is configured for performing at least one particle foam molding process using the particle foam molding machine based on the predicted process parameter for generating at least one workpiece, wherein the control system is configured for determining at least one property of the generated workpiece, for comparing the property with the optimization target and for adapting at least one process parameter of the particle foam molding machine depending on the comparison, wherein the control system is configured for repeating the particle foam molding process, the determining of the property, the comparing of the property and the optimization target and the adapting of the process parameters until the property of the generated workpiece is in accordance with the optimization target at least within pre-defined tolerances, wherein the control system is configured for determining at least one actual process parameter of the particle foam molding process, wherein the control system is configured for comparing the actual process parameter and the predicted process parameter and for adapting the simulation model based on the comparison.

Embodiment 20 The automated control system according to the preceding embodiment, wherein the automated control system is configured for performing the method according to any one of the preceding embodiments referring to a method.

Further optional features and embodiments will be disclosed in more detail in the subsequent description of embodiments, preferably in conjunction with the dependent claims. Therein, the respective optional features may be realized in an isolated fashion as well as in any arbitrary feasible combination, as the skilled person will realize. The scope of the invention is not restricted by the preferred embodiments. Detailed of the embodiments

The particle foam molding machine is configured for performing at least one particle foam molding process. The particle foam molding process may comprise at least one process or procedure of shaping at least one material into an arbitrary form or shape. The particle foam molding process may be a molding process performed by filling particle foam material into a mold. The mold may be a die or form, e.g. a form giving matrix or frame. In particular, as used herein, the mold may refer to an arbitrary die and/or form comprising at least one cavity, such as at least one form giving structure and/or cut-out. The mold may specifically be used in the particle foam molding process, wherein at least one particle foam material may be filled into the at least one cavity of the mold. As an example, the mold having the at least one cavity may be used in the molding process for forming the material. In particular, the particle foam material filled into the cavity of the mold may be given a negative form and/or geometry of the cavity. Specifically, the mold may be used for manufacturing at least one workpiece, wherein the manufactured workpiece may have a negative form and/or shape of the mold cavity.

The molding process may be configured for manufacturing at least one workpiece. The workpiece may be an arbitrary part or element. In particular, the workpiece may be or may comprise a constituent member of an arbitrary machine or apparatus. The workpiece may, for example, at least partially have a negative shape of the mold or of a cavity of the mold used in the molding process for manufacturing the component. Thus, the particle foam molding process may be or may refer to a form-giving procedure for creating the workpiece.

The particle foam molding process is based on a plurality of process parameters. The process parameters may be settable and/or selectable and/or adjustable and/or configurable parameter influencing the particle foam molding process. The process parameters may relate to operating conditions of the particle foam molding machine. In particular, the process parameter may be an particle foam molding machine parameter. For example, the process parameters may comprise one or more of a polymer melt temperature, barrel temperature, particle foam forming unit temperature, steam pressure, holding pressure, holding time, cooling or curing time, cooling or curing parameters such as cooling or curing medium throughput, cooling or curing medium temperature.

The method comprises the following steps: a) providing a set of input parameters by at least one external processing unit, wherein the set of input parameters comprises at least one simulation model, material specific parameters and particle foam molding machine parameters; b) the external processing unit, simulating a particle foam molding process based on the set of input parameters and determining at least one predicted process parameter of the simulated particle foam molding process by applying an optimizing algorithm in terms of at least one optimization target on the simulation model, wherein the predicted process parameter is provided to the particle foam molding machine via at least one interface; c) performing at least one particle foam molding process using the particle foam molding machine based on the predicted process parameter for generating at least one workpiece, determining at least one property of the generated workpiece and comparing the property with the optimization target, wherein, in case the property of the generated workpiece deviates from the optimization target, at least one process parameter of the particle foam molding machine is adapted depending on the comparison, and the particle foam molding process, determining of the property of the generated workpiece, and comparing the property with the optimization target is repeated with adapted process parameter until the property of the generated workpiece is in accordance with the optimization target at least within predefined tolerances; d) determining at least one actual process parameter of the particle foam molding process and comparing the actual process parameter and the predicted process parameter and adapting the simulation model based on the comparison.

The external processing unit may be at least one processing unit designed separately from the particle foam molding machine. The particle foam molding machine may comprise an internal processing unit, not shown here, which, in particular, is configured for controlling and monitoring machine parameters. The external processing unit may be configured for transferring and/or receiving data to the internal processing unit via at least one communication interface. The internal processing unit may be configured to transfer and/or to receive data to the external processing unit via at least one communication interface. The external processing unit may comprise a plurality of processors. The external processing unit may be and/or comprises a cloud computing system.

The external processing unit may comprise at least one database. The database may be an arbitrary collection of information. The database may be stored in at least one data storage device. The external processing unit may comprise the at least one data storage device with the information stored therein. In particular, the database may contain an arbitrary collection of information. The data storage device may be or may comprise at least one element selected from the group consisting of: at least one server, at least one server system comprising a plurality of servers, at least one cloud server or cloud computing infrastructure. The providing of the set of input parameters may comprise retrieving and/or selecting the set of input parameters. The retrieving may comprise a process of a system, specifically a computer system, generating data and/or obtaining data from an arbitrary data source, such as from a data storage, from a network or from a further computer or computer system. The retrieving specifically may take place via at least one computer interface, such as via a port such as a serial or parallel port. The retrieving may comprise several sub-steps, such as the sub-step of obtaining one or more items of primary information and generating secondary information by making use of the primary information, such as by applying one or more algorithms to the primary information, e.g. by using a processor.

The set of input parameters may comprise information about the simulation model, material specific parameters and particle foam molding machine parameters. The particle foam molding machine parameters may be parameters influencing the operating conditions of the particle foam molding machine. The particle foam molding machine parameters may comprise setting of machine components of the particle foam molding machine. The particle foam molding machine parameters may comprise specific values and/or parameter profiles. The particle foam molding machine parameters may comprise at least one parameter selected from the group consisting of: polymer melt temperature, barrel temperature, particle foam forming unit temperature, steam pressure, holding pressure, holding time, cooling or curing time, cooling or curing parameters such as cooling or curing medium throughput, cooling or curing medium temperature. The particle foam molding machine parameters may further comprise dimensions of the machine.

The material specific parameters may be information about the material or materials used for the particle foam molding process. The material specific parameters may be provided by material suppliers and/or may be downloaded from a website or other database. Material suppliers may have a lot of product specific data, like rheological data, viscosity, tensile strength of the particle foam, particle foam material data, and lot specific data for every material produced. The material specific parameters comprise at least one parameter selected from the group consisting of: compressibility, flow characteristics, temperature characteristics. The material, specifically the material used in the molding process, e.g. for manufacturing the workpiece, may for example be or may comprise a plastic material. Specifically, the plastic material may be or may comprise a thermoplastic material. Additionally or alternatively, the plastic material may be or may comprise a thermosetting material. Additionally or alternatively, the plastic material may comprise an elastomer material.

The simulation model may be generated by the software on the external processing unit or the simulation model may be a data set in the software. The simulation model may comprise at least one trained and trainable model. The external processing unit may be configured for per- forming and/or executing at least one machine-learning algorithm. The simulation model may be based on the results of at least one machine-learning algorithm. The machine-learning algorithm may comprise decision trees, naive bayes classifications, nearest neighbors, neural networks, convolutional neural networks, generative adversarial networks, support vector machines, linear regression, logistic regression, random forest and/or gradient boosting algorithms. Preferably, the machine-learning algorithm is organized to process an input having a high dimensionality into an output of a much lower dimensionality. The algorithm may be trained using records of training data. The simulation model may comprise at least one algorithm and model parameters. Parameters of the simulation model may be generated by using at least one artificial neural network. The simulation model, in particular model parameters, may be adapted, and thus, may be further trained, in step d).

The simulation model may comprise a digital twin of the particle foam molding process. The simulation model is configured for simulating a particle foam modeling process. The simulation model may comprise a filling simulation. Specifically, the simulation model may be configured for simulating of a filling of the mold cavity with a particle foam mass of at least one material. The simulation model may be configured for simulating of a manufacturing of the workpiece. The simulation model may be configured for simulating geometry and/or shape of the workpiece. The simulation model may comprise a strength analysis.

The simulation model may be configured for considering material specific properties. The simulation model may comprise a digital twin of the material. The simulation model may be configured for considering batch properties of raw material batches such as viscosity of the material batch.

Using simulation data, process data and product related data in a cloud based process optimizing of the particle foam molding process may be possible. As outlined above, material suppliers may have a lot of product specific data, like rheological data, viscosity, tensile strength of the particle foam, particle foam material data, and lot specific data for every material produced. The present invention proposes a closed loop between the simulation and the particle foam molding process such that parameters from the simulation can directly be used in the particle foam molding process. Moreover, the other way round, process data can be used to optimize the modelling process using machine learning models. The lot specific information of the material may be further linked to the simulation of the manufacturing process by using a cloud based digital twin of the material and the particle foam molding process such that the efficiency of the particle foam molding process can be even further improved. The predicted process parameter of the simulated particle foam molding process may be expected values of the process parameters, in particular for reaching an optimal manufacturing result and/or optimal usage of resources.

Step b) may comprise at least one optimization step. The optimization may be a process of selecting of a best parameter set with regard to the optimization target from a parameter space of possible parameters. The optimization target may be at least one criterion under which the optimization is performed. The optimization target may comprise at least one optimization goal and accuracy and/or precision. The optimization target may be at least one property of the workpiece. The property of the workpiece may be at least one element selected from the group consisting of: weight of the workpiece, dimensions of the workpiece, warping. The optimization target may be pre-specified such as by at least one customer and/or at least one user of the particle foam molding machine. The optimization target may be at least one user’s specification. The user may select the optimization goal and a desired accuracy and/or precision. The predicted process parameter is provided to the particle foam molding machine via at least one interface, in particular via a communication interface.

In step c), the manufactured workpiece may be measured, e.g. by using optical or tactile measurement techniques such as scanning. The scanning may comprise determining shape and dimensions of the workpiece. The scanning may specifically be performed automatically. The scanning may be performed autonomously by a computer or computer network.

The determined property of the workpiece may be compared to the optimization target. The comparison may comprise determining deviation from a target-shape and/or target-dimensions. The generated workpiece is considered to deviate from the target-shape and/or targetdimensions if a difference of the determined property and the optimization target is above a tolerance limit. The tolerance limit may depend on accuracy such as of the determining of the property and/or customer requirements and the like.

In case the property of the generated workpiece deviates from the optimization target, at least one process parameter of the particle foam molding machine is adapted depending on the comparison. The particle foam molding process, determining of the property of the generated workpiece, and comparing the property with the optimization target is repeated with adapted process parameter until the property of the generated workpiece is in accordance with the optimization target at least within pre-defined tolerances.

Step d) comprises determining at least one actual process parameter of the particle foam molding process. The particle foam molding machine may be configured for measuring and/or monitoring process at least one process parameter during the particle foam molding process. The particle foam molding machine may be configured for measuring the process parameters in real time and to adapt the process parameters on the run. The particle foam molding machine may comprise at least one sensor. Measured parameters of the particle foam molding machine may be registered and transferred to the external processing unit. The particle foam molding machine may comprise at least one element selected from the group consisting of: a temperature sensor; a pressure sensor; a clock.

Step d) further comprises comparing the actual process parameter and the predicted process parameter and adapting the simulation model based on the comparison. The comparison may comprise determining deviation of the predicted process parameter from the actual process parameter or view versa. The actual process parameter is considered to deviate from the predicted process parameter if a difference is above a tolerance limit. The tolerance limit may depend on measurement accuracy. The comparison may be performed by the internal processing unit of the particle foam molding machine. The information about the deviation and/or the actual process parameters may be transferred to the external processing unit. The external processing unit may be configured for adapting the simulation model, in particular the model parameters, based on the information about the deviation and/or the actual process parameters.

The method further may comprise outputting the predicted process parameter and/or a result of the comparison of the actual process parameter and the predicted process parameter via at least one output interface or port. The outputting may comprise a process of making information available to another system, data storage, person or entity. As an example, the output may take place via one or more interfaces, such as a computer interface or a human-machine interface. The output, as an example, may take place in one or more of a computer-readable format, a visible format or an audible format.

The particle foam molding process is based on a plurality of process parameters. The control system comprises the at least one external processing unit. The external processing unit is configured for simulating a particle foam molding process based on a set of input parameters comprising at least one simulation model, material specific parameters and particle foam molding machine parameters by applying an optimizing algorithm in terms of at least one optimization target on the simulation model. The control system comprises at least one interface, denoted with arrow, configured for providing the predicted process parameter to the particle foam molding machine. The control system is configured for performing at least one particle foam molding process using the particle foam molding machine based on the predicted process parameter for generating at least one workpiece. The control system is configured for determining at least one property of the generated workpiece, for comparing the property with the optimization target and for adapting at least one process parameter of the particle foam molding machine depending on the comparison. The control system is configured for repeating the particle foam molding process, the determining of the property, the comparing of the property and the optimization target and the adapting of the process parameters until the property of the generated workpiece is in accordance with the optimization target at least within pre-defined tolerances. The control system is configured for determining at least one actual process parameter of the particle foam molding process. The control system is configured for comparing the actual process parameter and the predicted process parameter and for adapting the simulation model based on the comparison.

The automated control system may be configured for performing the method according to the present invention. Thus, for possible embodiments reference is made to the description of the method.

For example, the comparison of the determined property of the workpiece with the optimization target may reveal that the workpiece deviates from the desired shape. At least one of the following process parameters of the particle foam molding machine may be adapted as follows depending on the comparison: changing temperatures for the mold halves and sliding cores, increasing the cooling time, adapting the process such that the molding is not catching or being held with negative draft, changing the holding pressure, and changing the holding time. Moreover, in view of the comparison the materials used may be changed. Moreover, the workpiece design may be changed. The process parameters of the particle foam molding machine may be adapted with respect to a pre-determined hierarchy. For example, first the mold temperature may be adapted, then the cooling time may be adapted. Subsequently the further process parameters may be adapted.

The invention is further described by examples. The examples relate to practical and in some cases preferred embodiments of the invention that do not limit the scope of the invention.

1. The following raw materials were used:

Isocyanate: 4,4‘-methylene diphenyl diisocyanate (MDI)

Chain extender: 1 ,4-butanediol

Polyol: poly tetrahydrofuran (PolyTHF) 1000 Further additives such as catalysts, stabilizers and/or antioxidants can be added in particular without deviation of the target result.

2. Manufacture of thermoplastic polyurethane (TPU)

The production of the following example TPU 1 was carried out in a twin-screw extruder, ZSK58 MC, of the company Coperion with a process length of 48D (12 housings). The discharge of the melt (polymer melt) from the extruder was carried out by means of a gear pump. After the melt filtration, the polymer melt was processed into granules by means of underwater granulation, which were dried continuously in a heating vortex bed, at 40 - 90°C. The polyol, the chain extender and the diisocyanate as well as a catalyst were dosed into the first zone. The addition of further additives, as described above, takes place in Zone 8. The housing temperatures range from 150 to 230 °C. The melting and underwater-granulation are carried out with melting temperatures of 210 - 230°C. The screw speed is between 180 and 240 rpm. The throughput ranges from 180 to 220 kg/h.

3. Manufacture of foamed granules (expanded thermoplastic polyurethane (eTPU))

3.1 For the production of the expanded particles (foamed granules) from the thermoplastic polyurethane, a twin-screw extruder with a screw diameter of 44 mm and a ratio of length to diameter of 42 was used with subsequent melting pump, a start-up valve with screen changer, a perforated plate and an underwater granulation. The thermoplastic polyurethane was dried before processing at 80 °C for 3 h in order to obtain a residual moisture of less than 0.02 wt.%.

The thermoplastic polyurethane used is dosed via a gravimetric dosing device into the feed of the twin-screw extruder.

After dosing the materials into the feed of the twin-screw extruder, the materials were melted and mixed. Subsequently, the propellants CO2 and N2 were added via one injector each. The remaining extruder length was used for homogeneous incorporation of the propellant into the polymer melt. After the extruder, the polymer/propellant mixture was pressed into a perforated plate (LP) by means of a gear pump (ZRP) via a start-up valve with screen changer (AV) into a perforated plate. Via the perforated plate individual strands are produced. These strands were conveyed to the pressurized cutting chamber of the underwater granulation (UWG) unit, in which the strands are cut into granules and further transported with the water while the granules expanded. The separation of the expanded particles I granules from the process water is ensured by means of a centrifugal dryer.

The total throughput of the extruder, polymers and propellants was 40 kg/h. The quantities of polymers and propellants used are listed in Table 1. Here, the polymers are always counted as 100 parts while the propellant is additionally counted, so that total compositions above 100 parts are obtained.

Table 1: Proportions of dosed polymers and propellants where the polymers/solids always yield

100 part and the propellants are counted additionally

The temperatures used by the extruder and the subsequent devices as well as the pressure in the cutting chamber of the UWG are listed in Table 2.

Table 2: Temperature data of plant parts

After the separation of the expanded granules from the water by means of a centrifugal dryer, the expanded granules are dried at 60 °C for 3 h to remove the remaining surface water as well as possible moisture in the particle in order to not distort a further analysis of the particles.

3.2 In addition to processing in the extruder, expanded particles were also produced in an autoclave. For this purpose, the pressure vessel was filled with a filling degree of 80% with the solid/liquid phase, wherein the phase ratio was 0.32. Solid phase is the TPLI1 and the liquid phase is a mixture of water with calcium carbonate and a surface-active substance. With pressure onto this solid/liquid phase, the blowing agent / propellant (butane) was pressed into the tight pressure vessel, which was previously rinsed with nitrogen. The quantity is given in Table 3 and calculated in relation to the solid phase (TPLI1). The pressure vessel was heated by stirring the solid/liquid phase at a temperature of 50 °C and then nitrogen was pressed into the pressure vessel up to a pressure of 8 bar. Subsequently, further heating was carried out until the desired impregnation temperature (IMT) was reached. When the impregnation temperature and the impregnation pressure were reached, the pressure vessel was relaxed via a valve after a given holding time. The exact manufacturing parameters of the manufacturing of foamed granules in an autoclave (pressure vessel, impregnation vessel) are listed in Table 3.

Table 3: Manufacturing parameters of the impregnated material TPLI1

4. Particle Foam Molding (Fusing of foam beads)

4.1 Manufacture of moldings by steam chest molding I water vapour fusing to obtain a mold I particle foam based molded article

The expanded granules were then fused on a molding machine from Kurtz ersa GmbH (Energy Foamer) to square plates with a side length of 200 mm and a thickness of 10 mm or 20 mm by covering with water vapor. With regard to plate thickness, the fusing parameters differ only in terms of cooling. The fusing parameters of the different materials were chosen in such a way that the plate side of the final molded part facing the moving side (Mil) of the tool had as few collapsed eTPU particles as possible. Usually, steaming times in the range of 3 to 50 seconds were used for the respective steps. Through the movable side of the tool, a slit steaming was also carried out if necessary. Irrespective of the experiment, regarding the fixed (Ml) and the movable side of the tool, at the end a cooling time of 120 s was always set at a plate thickness of 20 mm and a cooling time of 100 s was always set with a 10 mm thick plate. The respective molding I steaming conditions are listed in Table 4 as steam pressures. The plates are stored in the oven for 4 hours at 70 °C. Table 4: Steaming conditions (steam pressures)

4.2. Fusing via electromagnetic radiation

For fusing via electromagnetic radiation according to the invention it is referred to US2018251621A1, which discloses process parameter that can be applied in the context of the present invention.

5. Measuring methods and performance and/or quality parameter of the material:

In the following, parameter and methods for characterizing the product (e-TPU foam particles and/or mold from e-TPU particles) are listed: a. All considerable measurement methods for characterizing the product I material regarding performance and/or quality are listed. The measurement results I data can be used as input data I input parameter for determination of product I material performance and/or quality:

E-TPU particle foam (bulk particles and/or molded article):

- particle weight or bead weight,

- split tear,

- dimensional stability test or shrinkage test,

- tensile test,

- resilience or rebound resilience,

- abrasion,

- bulk density,

- bead density or particle density or foam density,

- hardness

- compression properties (e.g. stiffness, measured via compression set or compre- sion stress, cushioning),

- tensile strength, - elongation at break,

- tear strength,

- DSC (Differential Scanning Calorimetry),

- DMA (dynamic mechanic analysis),

- TMA (thermo mechanic analysis),

- NMR (nuclear magnetic resonance spectroscopy),

- FT-IR (Fourier-Transformation Infrared Spectroscopy),

- GPC (gel permeation chromatography),

- hydrolysis measurement,

- sun test,

- visual appearance (e.g. 3D structure)

- particle size distribution (PSD), b. Particle size distribution (PSD) and/or bulk density of the foamed particle are in particular suitable as parameter for “inline measurements" in connection with the manufacturing process (controlling, monitoring). c. Preferred material parameter for determining the material properties after production and to characterize the product regarding performance and/or quality are:

- tensile strength,

- elongation at break,

- rebound resilience,

- compression properties, and also

- particle size distribution (PSD) and/or

- bulk density.

These data can act as “historical data", can be regularly updated to train the model and to enable that the computing unit can determine the production settings I monitor the manufacturing process I control product quality (in-line, particularly based on particle size distribution (PSD) and/or bulk density).

Claims

1 . A computer-implemented method for controlling and/or monitoring at least one particle foam molding process in at least one particle foam molding machine, wherein the particle foam molding process is based on a plurality of process parameters, wherein the method comprises the following steps: a) providing a set of input parameters by at least one external processing unit, wherein the set of input parameters comprises at least one simulation model, material specific parameters and particle foam molding machine parameters; b) the external processing unit, simulating a particle foam molding process based on the set of input parameters and determining at least one predicted process parameter of the simulated particle foam molding process by applying an optimizing algorithm in terms of at least one optimization target on the simulation model, wherein the predicted process parameter is provided to the particle foam molding machine via at least one interface; c) performing at least one particle foam molding process using the particle foam molding machine based on the predicted process parameter for generating at least one workpiece, determining at least one property of the generated workpiece and comparing the property with the optimization target, wherein, in case the property of the generated workpiece deviates from the optimization target, at least one process parameter of the particle foam molding machine is adapted depending on the comparison, and the particle foam molding process, determining of the property of the generated workpiece, and comparing the property with the optimization target is repeated with adapted process parameter until the property of the generated workpiece is in accordance with the optimization target at least within pre-defined tolerances; d) determining at least one actual process parameter of the particle foam molding process and comparing the actual process parameter and the predicted process parameter and adapting the simulation model based on the comparison.

2. The method according to the preceding claim, wherein method steps a) to d) are repeated, wherein the adapted simulation model is used in step a).

3. The method according to any one of the preceding claims, wherein the particle foam molding machine parameters comprise at least one parameter selected from the group consisting of: polymer melt temperature, barrel temperature, particle foam forming unit temperature, steam pressure, holding pressure, holding time, cooling or curing time, cooling or curing parameters.

4. The method according to any one of the preceding claims, wherein measured parameters of the particle foam molding machine are registered and transferred to the external processing unit, wherein the particle foam molding machine comprises at least one element selected from the group consisting of: a temperature sensor; a pressure sensor; a clock.

5. The method according to any one of the preceding claims, wherein the simulation model comprises a filling simulation.

6. The method according to any one of the preceding claims, wherein the simulation model is configured for simulating a filling of a mold cavity with a particle foam mass of at least one material.

7. The method according to any one of the preceding claims, wherein the simulation model is configured for simulating geometry and/or shape of the workpiece.

8. The method according to any one of the preceding claims, wherein the simulation model comprises a strength analysis.

9. The method according to any one of the preceding claims, wherein the material specific parameters comprise at least one parameter selected from the group consisting of: compressibility, flow characteristics, temperature characteristics.

10. The method according to any one of the preceding claims, wherein the simulation model is configured for considering material specific properties.

11. The method according to the preceding claim, wherein the simulation model is configured for considering batch properties of raw material batches.

12. The method according to any one of the preceding claims, wherein the method further comprises outputting the predicted process parameter and/or a result of the comparison of the actual process parameter and the predicted process parameter via at least one output interface or port.

13. The method according to any one of the preceding claims, wherein the external processing unit is and/or comprises a cloud computing system.

14. A computer program comprising instructions which, when the program is executed by a computer or computer system, cause the computer or computer system to carry out the method according to any one of the preceding claims.

15. Automated control system for an particle foam molding process in at least one particle foam molding machine, wherein the particle foam molding process is based on a plurality of process parameters, wherein the control system comprises at least one external processing unit, wherein the external processing unit is configured for simulating an particle foam molding process based on a set of input parameters comprising at least one simulation model, material specific parameters and particle foam molding machine parameters by applying an optimizing algorithm in terms of at least one optimization target on the simulation model, wherein the control system comprises at least one interface configured for providing the predicted process parameter to the particle foam molding machine, wherein the control system is configured for performing at least one particle foam molding process using the particle foam molding machine based on the predicted process parameter for generating at least one workpiece, wherein the control system is configured for determining at least one property of the generated workpiece, for comparing the property with the optimization target and for adapting at least one process parameter of the particle foam molding machine depending on the comparison, wherein the control system is configured for repeating the particle foam molding process, the determining of the property, the comparing of the property and the optimization target and the adapting of the process parameters until the property of the generated workpiece is in accordance with the optimization target at least within pre-defined tolerances, wherein the control system is configured for determining at least one actual process parameter of the particle foam molding process, wherein the control system is configured for comparing the actual process parameter and the predicted process parameter and for adapting the simulation model based on the comparison.