CN117010671B - Distributed flexible workshop scheduling method and device based on blockchain - Google Patents

Abstract

The embodiment of the present disclosure discloses a blockchain-based distributed flexible workshop scheduling method and device, wherein the method includes: obtaining a processing request, the processing request includes: multiple job tasks, each job task includes: a product to be processed, The processing type of the product to be processed and the number of workpieces of the product to be processed; based on the production process, obtain the first production parameter from the blockchain; based on the processing type in the job task, determine the second production parameter; based on the production process, the first production Parameters, second production parameters and the number of workpieces for each job task, use the pre-trained distributed flexible workshop scheduling model to determine the production plan. Among them, the distributed flexible workshop scheduling model includes: objective function and preset constraints; based on production The plan is to carry out production and processing to complete each operation task and obtain the products to be processed corresponding to the number of workpieces for each operation task. Embodiments of the present disclosure realize efficient production and processing of multiple work tasks.

Description

Distributed flexible workshop scheduling method and device based on blockchain

Technical field

The present disclosure relates to the field of blockchain technology, the field of workshop scheduling technology and the field of artificial intelligence technology, especially a distributed flexible workshop scheduling method and device based on blockchain.

Background technique

The distributed production model is widely used in the production and manufacturing of industrial products because it has the advantages of high resource utilization efficiency, strong risk resistance, and the ability to leverage the advantageous manufacturing industries of various regions. In the distributed production model, when an industrial product is processed and manufactured, each production step of the industrial product is processed by different factories. Since different factories are usually set up in different regions, this makes the interaction between the various production steps Scheduling is crucial to the efficiency of industrial product processing and manufacturing, so how to achieve efficient distribution and scheduling is an urgent problem to be solved.

Contents of the invention

Embodiments of the present disclosure provide a blockchain-based distributed flexible workshop scheduling method and device to solve the above technical problems.

One aspect of an embodiment of the present disclosure provides a distributed flexible workshop scheduling method based on blockchain, including: obtaining a processing request, wherein the processing request includes: multiple job tasks, among the multiple job tasks Each job task, the job task includes: the product to be processed, the processing type of the product to be processed, and the number of workpieces of the product to be processed; the multiple job tasks all have the same production process, and the production process It includes multiple production steps with a production sequence; based on the production process, the first production parameters are obtained from the blockchain, wherein the first production parameters include: corresponding to each production step in the multiple production steps. The number of processing equipment and the transportation time of the semi-finished product to be processed between the processing equipment of each two adjacent production steps in the multiple production steps; based on the processing type in the job task, determine the second production parameter, Wherein, the second production parameters include: the operating time range for the processing equipment to complete a production step, the variation range of the starting time of the processing equipment, and the residence time range. The residence time range represents: in the production process of the product to be processed, from The time distribution range between the completion of the processing equipment of the first production step and the start of the processing equipment of the last production step; according to the production process, the first production parameter, the second production parameter and each of the According to the number of workpieces of the job tasks, the pre-trained distributed flexible shop scheduling model is used to determine the production plan of each job task so as to minimize the total time of the multiple job tasks, wherein the distributed flexible shop scheduling model It includes: an objective function and preset constraint conditions, the objective function is used to minimize the time to complete the multiple job tasks, the preset constraint conditions are used to constrain the variables in the objective function; execute all the tasks based on the production plan. Describe a plurality of work tasks, and obtain the products to be processed corresponding to the number of workpieces in each of the work tasks.

Optionally, in the method of any of the above embodiments of the present disclosure, the preset constraints include: constraints on the production and processing of the processing equipment; constraints on the type of processing to be produced and processed by the processing equipment; constraints on starting processing Constraints on the continuous processing of the processing equipment corresponding to each production and processing step; Constraints on the continuous processing of the processing equipment corresponding to each production and processing step when producing products to be processed of the same processing type; Constraints on the start of processing on the processing equipment Constraints on the start time of operations of each processing type; Constraints on the processing sequence of two consecutive production steps of the same product to be processed; Constraints on the continuous processing sequence on the same processing equipment; Constraints on the continuous operations on the same processing equipment Constraints on the start sequence; constraints on the time intervals between operations of each processing type on the processing equipment; constraints on the residence time of operations of multiple processing types on the processing equipment; constraints on the operations of multiple processing types on the processing equipment start time constraints.

Optionally, in the method of any of the above embodiments of the present disclosure, the production and processing based on the production plan is performed to execute the plurality of job tasks to complete the respective job tasks and obtain the workpieces corresponding to the respective job tasks. After the number of target products to be processed, it also includes: obtaining equipment information of each processing equipment, wherein the equipment information of any of the processing equipment includes: within a preset time period, by any of the processing equipment The qualification rate of the products to be processed obtained by the processing equipment; according to the qualification rate of the products to be processed in each equipment information, the number of processing equipment corresponding to each production step in the first production parameter is updated.

Optionally, in the method of any of the above embodiments of the present disclosure, the distributed flexible workshop scheduling model is trained in the following manner: obtaining a training data set and a mixed integer linear programming model to be trained, wherein the training data The set includes: multiple pieces of training data; each training data in the multiple pieces of training data includes a node bipartite graph respectively; the mixed integer linear programming model to be trained includes: an initial objective function and an initial preset constraint condition; using all The training data set and the strong branch strategy are described, and the mixed integer linear programming model to be trained is iteratively trained until the training results meet the training stop conditions, and the distributed flexible workshop scheduling model is obtained.

Optionally, in the method of any of the above embodiments of the present disclosure, the training data set and the strong branch strategy are used to iteratively train the mixed integer linear programming model to be trained until the training results meet the training stop condition, Obtaining the distributed flexible workshop scheduling model includes: obtaining the target branch decision corresponding to the mixed integer linear programming model to be trained that satisfies the training stop condition; parameterizing the target branch decision to obtain model parameters; based on the The distributed flexible workshop scheduling model is obtained by using the above model parameters and the mixed integer linear programming model to be trained that satisfies the training stop condition.

Optionally, in the method of any of the above embodiments of the present disclosure, the obtaining a training data set includes: using a preset solver and the strong branch strategy to solve the mixed integer linear programming model to be trained, Obtain the training data set.

Another aspect of the embodiment of the present disclosure provides a distributed flexible workshop scheduling device based on blockchain, including: a first acquisition module, used to acquire a processing request, wherein the processing request includes: multiple job tasks , each of the multiple job tasks, the job task includes: the product to be processed, the processing type of the product to be processed, and the number of workpieces of the product to be processed; the multiple job tasks all have the same The production process includes a plurality of production steps with a production sequence; a first parameter acquisition module is used to obtain the first production parameter from the blockchain based on the production process, wherein the first production The parameters include: the number of processing equipment corresponding to each production step in the multiple production steps and the transportation time of the semi-finished product to be processed between the processing equipment of each two adjacent production steps in the multiple production steps; The second parameter acquisition module is used to determine second production parameters based on the processing type in the operation task, where the second production parameters include: the operation duration range of the processing equipment to complete one production step, and the start-up time of the processing equipment. The change range and residence time range, the residence time range represents: in the production process of the product to be processed, the time distribution range from the end of the processing equipment of the first production step to the start of the processing equipment of the last production step ; A plan generation module, configured to use a pre-trained distributed flexible workshop scheduling model to determine each workpiece based on the production process, the first production parameter, the second production parameter and the number of workpieces of each job task. The production plan of the job tasks is to minimize the total time of the multiple job tasks, wherein the distributed flexible workshop scheduling model includes: an objective function and preset constraints, and the objective function is used to minimize the completion of all tasks. Describe the time of multiple job tasks, and the preset constraint conditions are used to constrain variables in the objective function; the production and processing module is used to execute the multiple job tasks based on the production plan and obtain the workpieces corresponding to each job task. Quantity of product to be processed.

Optionally, in the device of any of the above embodiments of the present disclosure, the preset constraints include: constraints on the production and processing of the processing equipment; constraints on the type of processing to be produced and processed by the processing equipment; constraints on starting processing Constraints on the continuous processing of the processing equipment corresponding to each production and processing step; Constraints on the continuous processing of the processing equipment corresponding to each production and processing step when producing products to be processed of the same processing type; Constraints on the start of processing on the processing equipment Constraints on the start time of operations of each processing type; Constraints on the processing sequence of two consecutive production steps of the same product to be processed; Constraints on the continuous processing sequence on the same processing equipment; Constraints on the continuous operations on the same processing equipment Constraints on the start sequence; constraints on the time intervals between operations of each processing type on the processing equipment; constraints on the residence time of operations of multiple processing types on the processing equipment; constraints on the operations of multiple processing types on the processing equipment start time constraints. Another aspect of the embodiment of the present disclosure provides an electronic device, including: a memory for storing a computer program; a processor for executing the computer program stored in the memory, and when the computer program is executed, Implement the above-mentioned distributed flexible workshop scheduling method based on blockchain.

Another aspect of the embodiments of the present disclosure provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned blockchain-based distributed flexible workshop scheduling method is implemented.

In the embodiment of the present disclosure, the first production parameters and the second production parameters are first determined through the production process corresponding to each job task and the processing type of each job task, and then the distributed flexible workshop scheduling model is used to calculate multiple production processes with the same production process. Optimizing the production and scheduling of multiple job tasks of each processing type can minimize the total time to complete multiple job tasks and achieve efficient production and processing of multiple job tasks.

The technical solution of the present disclosure will be described in further detail below through the accompanying drawings and examples.

Description of drawings

The accompanying drawings, which constitute a part of the specification, illustrate embodiments of the disclosure and, together with the description, serve to explain principles of the disclosure.

The present disclosure may be more clearly understood from the following detailed description with reference to the accompanying drawings, in which:

Figure 1 shows a flow chart of an embodiment of a blockchain-based distributed flexible workshop scheduling method according to an embodiment of the present disclosure;

Figure 2 shows a flow chart of another embodiment of the blockchain-based distributed flexible workshop scheduling method according to the embodiment of the present disclosure;

Figure 3 shows a flow chart of another embodiment of the blockchain-based distributed flexible workshop scheduling method according to the embodiment of the present disclosure;

Figure 4 shows a schematic diagram of a node bipartite graph according to an embodiment of the present disclosure;

Figure 5 shows a flow chart of step S320 in an embodiment of the present disclosure;

Figure 6 shows a schematic structural diagram of an embodiment of a blockchain-based distributed flexible workshop scheduling device according to an embodiment of the present disclosure;

FIG. 7 is a schematic structural diagram of an application embodiment of the electronic device of the present disclosure.

Detailed ways

Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of components and steps, numerical expressions, and numerical values set forth in these examples do not limit the scope of the disclosure unless otherwise specifically stated.

Those skilled in the art can understand that terms such as "first" and "second" in the embodiments of the present disclosure are only used to distinguish different steps, devices or modules, etc., and do not represent any specific technical meaning, nor do they represent the differences between them. necessary logical sequence.

It should also be understood that in the embodiments of the present disclosure, "plurality" may refer to two or more than two, and "at least one" may refer to one, two, or more than two.

It should also be understood that any component, data or structure mentioned in the embodiments of the present disclosure can generally be understood to mean one or more unless there is an explicit limitation or contrary inspiration is given in the context.

In addition, the term "and/or" in this disclosure is only an association relationship describing associated objects, indicating that there can be three relationships, for example, A and/or B, which can mean: A alone exists, and A and B exist simultaneously. , there are three situations of B alone. In addition, the character "/" in this disclosure generally indicates that the related objects are in an "or" relationship.

It should also be understood that the description of various embodiments in this disclosure focuses on the differences between the various embodiments, and the similarities or similarities between the embodiments can be referred to each other. For the sake of brevity, they will not be repeated one by one.

At the same time, it should be understood that, for convenience of description, the dimensions of various parts shown in the drawings are not drawn according to actual proportional relationships.

The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the disclosure, its application or uses.

Techniques, methods and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, such techniques, methods and devices should be considered a part of the specification.

It should be noted that similar reference numerals and letters refer to similar items in the following figures, so that once an item is defined in one figure, it does not need further discussion in subsequent figures.

Embodiments of the present disclosure may be applied to electronic devices such as terminal devices, computer systems, servers, etc., which may operate with numerous other general or special purpose computing system environments or configurations. Examples of well-known terminal devices, computing systems, environments and/or configurations suitable for use with terminal devices, computer systems, servers and other electronic devices include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients Computers, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, networked personal computers, small computer systems, mainframe computer systems and distributed cloud computing technology environments including any of the above systems, etc.

Electronic devices such as terminal devices, computer systems, servers, etc. may be described in the general context of computer system executable instructions (such as program modules) being executed by the computer system. Generally, program modules may include routines, programs, object programs, components, logic, data structures, etc., that perform specific tasks or implement specific abstract data types. The computer system/server may be implemented in a distributed cloud computing environment where tasks are performed by remote processing devices linked through a communications network. In a distributed cloud computing environment, program modules may be located on local or remote computing system storage media including storage devices.

In the embodiment of the present disclosure, the production work corresponding to each production step of each product to be processed is called a job. The processing type of each operation is the same as the processing type of the product to be processed corresponding to the operation.

In the process of producing a product to be processed, the products obtained by other production steps except the last production step are called intermediate products of the product to be processed.

In Distributed Flexible Flow Shop Scheduling, each production step in the production process can correspond to multiple processing equipment used to implement the production step. Each processing equipment can have multiple processing locations, each The processing position is used to complete a production step, that is, each processing position can realize the production step corresponding to the processing equipment where the processing position is located. Multiple processing equipment corresponding to each production step can be set up in a factory.

Block Chain is a chain data structure that combines data blocks in a chronological order and is a distributed ledger that cryptographically ensures that the data cannot be tampered with or forged.

Figure 1 shows a schematic flowchart of a distributed flexible workshop scheduling method in an embodiment of the present disclosure. This embodiment can be applied to computing devices. As shown in Figure 1, the distributed flexible workshop scheduling method in this embodiment includes the following steps:

Step S110: Obtain the processing request.

The processing request includes: multiple job tasks. For each of the multiple job tasks, the job task includes: the product to be processed, the processing type of the product to be processed, and the number of workpieces of the product to be processed. Each job task has the same production process, that is, the products to be processed by each job task all have the same production process. The production process includes a plurality of production steps in a production sequence.

The products to be processed can be any products. For example, the products to be processed can be industrial products, daily products, electronic products, etc. The processing type can be the model, size, product specifications of the product to be processed, etc. For example, when the product to be processed is a bolt, the processing type can be the bolt model, such as the bolt model can be M18, M6, M8, etc. When job task 1 includes: the product to be processed is bolts, the processing type is M18, and the number of workpieces is 20, then job task 1 means that 20 bolts of type M18 need to be processed.

The production process includes: multiple production steps with a production sequence. For example, the production process includes three production steps: manufacturing, assembly and spraying. The production sequence of these three production steps is: ① manufacturing, ② assembly, ③ spraying. That is, after three production steps of manufacturing, assembly, and spraying, the product to be processed is obtained. The number of workpieces is the number of products to be processed that need to be produced, that is, the number of products to be processed that is finally processed.

Step S120: Obtain the first production parameters from the blockchain based on the production process.

Wherein, the first production parameters include: the number of processing equipment corresponding to each production step in the plurality of production steps, the distance between the processing equipment of each two adjacent different production steps in the semi-finished product to be processed in the plurality of production steps. Transportation time. Multiple first production parameters can be stored in the blockchain.

In one embodiment, a production process may have a process identifier used to uniquely identify the production process. The first production parameter may have a parameter identification that uniquely identifies the first production parameter. The above-mentioned process identifiers and parameter identifiers can be decentralized identifiers (Decentralized Identifier, DID) or custom codes.

The correspondence between the process identifier and the parameter identifier can be set in advance. According to the process identifier of the above-mentioned production process, in the corresponding relationship between the process identifier and the parameter identifier, the parameter identifier corresponding to the process identifier is searched as the target parameter identifier. Based on the target parameter identifier, the third parameter identifier is obtained from the blockchain. a production parameter.

Step S130: Determine second production parameters based on the processing type in the job task.

Among them, the second production parameters include: the operating time range of the processing equipment to complete a production step, the variation range of the starting time of the processing equipment, and the residence time range. The residence time range represents: in the production process of the product to be processed, from the first The time distribution range between the end of the processing equipment of the first production step and the start of the processing equipment of the last production step. For example, when the production process includes three production steps with a production sequence, the residence time range is the residence time range between the intermediate product of the product to be processed finishing working on the first processing equipment and starting working on the third processing equipment.

In one implementation, the second production parameter can be obtained as follows:

For each job task, you can customize the operation time for the processing equipment to complete a production step and the start-up time of the processing equipment based on the processing type and product to be processed in the job task, production experience, performance of the processing equipment, production requirements, etc. range of change. The residence time range can be customized based on the performance of the processing equipment, the production requirements of the products to be processed, production specifications, etc. The second production parameter is generated based on the operation time of each processing equipment to complete a production step, the variation range of the start-up time and the residence time range of each processing equipment. Among them, the operating time range of the processing equipment in the second production parameter to complete a production step covers the operating time of each processing equipment to complete a production step; the variation range of the start-up time of the processing equipment in the second production parameter covers the operating time of each processing equipment. The variation range of startup time.

Step S140: Based on the production process, the first production parameter, the second production parameter and the number of workpieces of each operation task, use the pre-trained distributed flexible workshop scheduling model to determine the production plan to minimize the total time of multiple operation tasks. change.

Among them, the distributed flexible workshop scheduling model includes: an objective function and preset constraints. The objective function is used to minimize the total time to complete multiple job tasks, that is, the objective function is used to minimize the total time to complete each job task. Minimum. Preset constraints are used to constrain the variables in the objective function. The production plan includes production and processing information for each operation task and production and processing information for each processing equipment. For example, the production plan may include: the production sequence of each product to be processed on each processing equipment in each job task, each processing equipment for each production step, the duration of production and processing of each product to be processed, etc.

The distributed flexible workshop scheduling model is used to output a production plan that optimizes the production and processing methods of each task. That is, the distributed flexible workshop scheduling model can output a production plan that minimizes the total time to complete each task. The distributed flexible workshop scheduling model can solve distributed flexible workshop scheduling problems based on genetic algorithm (Genetic Algorithm, GA), hybrid optimization algorithm (Genetic Algorithm Variable Neighborhood Search, GAVNS), branch-and-bound algorithm (Branch-andBound, B&B), etc. get.

In one implementation, the production process includes three production steps as an example for description. Other examples can be found here. For convenience of explanation, the three production steps included in the production process are respectively referred to as the first production step, the second production step and the third production step according to the production order. The processing equipment corresponding to the first production step is called first processing equipment, the processing equipment corresponding to the second production step is called second processing equipment, and the processing equipment corresponding to the third production step is called third processing equipment.

The objective function is formula (1), and the constraints can be expressed by formula (2) to formula (14);

;

;

;

;

;

;

;

;

;

;

;

;

;

.

in, are all variables of the objective function. specific, Can be a binary decision variable,/> is a ternary decision variable.

f is the processing type index; i is the job index; s is the index of the production step; m is the index of the processing equipment; k is the index of the processing location.

m _n is the index of the first processing equipment; M is the set of first processing equipment, M={1,...,m _n }; M′ is the set of some first processing equipment, M′={2,...,m _n }; K _mn is the processing position index, indicating the processing position n on the first processing equipment m; K _m is the processing position set of the first processing equipment m, K _m = {1,..., K _mn }; K _m ′ is the partial set of processing positions of the first processing equipment m, K _m ′={1,...,K _mn-1 }; f _n is the index of the processing type f; F is the set of processing types, F={1,... , f _n }; I _fn is the index of the job of processing type f; I _f is the set of jobs with processing type f, I _f ={1,...,I _fn }; I _f ′ is the job of processing type f The partial set of I _f ={1,...,I _fn-1 }; △ _m is the startup time of the m-th first equipment; [α _{1, f} , α _{2, f} ] is the operation of processing type f at the The time variation range of the first start on the third processing equipment; p _f,i,m is the processing time of the i-th job with processing type m on the third processing equipment m; p _f,i,1 is the processing type is the processing time of the i-th job of m on the first third processing equipment; q _{f, i} is the processing time of job i of processing type f on the second processing equipment; [w _{1, f, i} , w _{2, f, i} ] is the variation range of the processing time of job i on the second processing equipment of processing type f; d _m is the maximum residence time of job m from the end of processing by the first processing equipment to the start of processing by the third processing equipment; t _1,2 is the transportation time from the first production step (first processing equipment) to the second production step (second processing equipment); t _2,3 is the transportation time from the second production step (second processing equipment) to the third production step (The third processing equipment) transportation time; X f _{, 1,1,1} is the processing position 1 assigned to the first processing equipment 1 by job 1; When job i of processing type f is assigned to processing position k, X _f,i,m,k is set to 1, otherwise, X _f,i,m,k is set to 0; ST _f,i,s is a continuous variable, which defines the start time of starting to process job i of processing type f in production step s; PT _f,i,3 is a continuous variable, which defines the start time of job i of processing type f in the third production step Duration; minCThe minimum total duration of multiple job tasks; The start time of starting processing operation I _fn for the third production step;/> It is the operation duration of the third production step of operation I _fn of processing type f; It is the operation i + 1 of the processing type f processed at the processing position of the first processing equipment r + 1; It is the processing operation i+1 of processing type f at the processing position m′ of the first processing equipment r + 1;/> is the start time of starting processing of the i-th job on the first processing equipment;/> The start time of starting the i-th job on the second processing equipment;/> is the start time of starting processing of the i-th job on the third processing equipment;/> It is the start time of starting the i+1th job on the second processing equipment;/> It is the start time of starting the i+1th job on the third processing equipment;/> is the operation duration of operation i of processing type f in the third production step; M ₁ is a set of indexes of processing positions of the first processing equipment. Constraint condition 1 (corresponding to equation (2)) is: each job of each processing type can only be processed at one processing position on one first processing equipment; constraint condition 2 (corresponding to equation (3)) is: each third Each processing position of a processing equipment can only process one processing type of job; constraint 3 (corresponding to equation (4)) is: the first job can only be assigned to the first processing position on the first processing device; Constraint 4 (corresponding to equation (5)) is: Currently, only when job i with processing type f is processed on one of the first processing equipment with index {1,···,r}, it can be processed at index The first processing position of the first processing equipment of r + 1 processes the operation i + 1 with the processing type f; the constraint 5 (corresponding to equation (6)) is: if and only if the operation i with the processing type f is at the index When processing on the first processing equipment with index {1,···,r}, or when processing on the first processing equipment indexed before index {1,···,r+1}, it can be processed on the first processing equipment with index r The operation i+1 of processing type f is processed on the first processing equipment of +1; constraint condition 6 (corresponding to equation (7)) is: the start time of starting processing of operations of each processing type on the first processing equipment; constraint condition 7 (corresponding to equation (8)) and constraint 8 (corresponding to equation (9)) are used to constrain that in two consecutive production steps of the same product to be processed, the latter production step can only be completed in the previous production step and has been transmitted It can only start when the processing equipment corresponding to the latter production step is reached; the constraint (9) (corresponding to equation (10)) is: for two consecutive operations on the same second processing equipment, the second operation can only be performed on the first Start after each job is completed; constraint condition (10) (corresponding to equation (11)) is: for two consecutive jobs on the same third processing equipment, the second job should be started immediately after the first job is completed; constraint condition 11 (corresponding to equation (12)) is: the time interval between operations of each processing type on the third processing equipment; constraint 12 (corresponding to equation (13)) is: the time interval between operations of each processing type on the processing equipment The maximum residence time of Ensure that for two jobs of the same processing type, the latter job is processed after the previous job.

Step S150: Execute multiple job tasks based on the production plan to obtain products to be processed corresponding to the number of workpieces for each job task.

Among them, processing can be performed based on the production plan to complete each operation task in the workpiece processing request, and obtain the number of workpieces corresponding to each operation task to be processed.

In the embodiment of the present disclosure, the first production parameters and the second production parameters are first determined through the production process corresponding to each job task and the processing type of each job task, and then the distributed flexible workshop scheduling model is used to calculate multiple production processes with the same production process. Optimizing the production and scheduling of multiple job tasks of each processing type can minimize the total time to complete multiple job tasks and achieve efficient production and processing of multiple job tasks.

In an optional embodiment, the preset constraints in the distributed flexible workshop scheduling model in this embodiment include:

Regarding the constraints on the production and processing of the processing equipment, in this embodiment, this constraint corresponds to constraint 1 in step S140.

Constraints on the type of processing to be produced by the processing equipment. In this embodiment, this constraint corresponds to constraint 2 in step S140.

Regarding the constraint on starting processing, in this embodiment, this constraint corresponds to constraint 3 in step S140.

Regarding the constraints on the continuous processing of the processing equipment corresponding to each production and processing step, in this embodiment, this constraint corresponds to constraint 4 in step S140.

Regarding the constraint on continuous processing of processing equipment corresponding to each production and processing step when producing products to be processed of the same processing type, in this embodiment, this constraint corresponds to constraint 5 in step S140.

In this embodiment, in this embodiment, this constraint corresponds to the constraint 6 in step S140 as to the constraint on the start time of processing operations of each processing type on the first processing equipment.

Regarding the constraints on the processing sequence of two consecutive production steps of the same product to be processed, in this embodiment, this constraint corresponds to constraint 7 and constraint 8 in step S140.

Regarding the constraints on the continuous processing sequence on the same processing equipment, in this embodiment, this constraint corresponds to constraint 9 in step S140.

Regarding the constraint on the startup sequence during continuous operations on the same processing equipment, in this embodiment, this constraint corresponds to constraint 10 in step S140.

Regarding the constraints on the time intervals between operations of each processing type on the processing equipment, in this embodiment, this constraint corresponds to the constraint 11 in step S140.

Constraints on the residence time of multiple processing types of jobs on the processing equipment. In this embodiment, this constraint corresponds to constraint 12 in step S140.

Constraints on the start time of multiple processing types of jobs on the processing equipment. In this embodiment, this constraint corresponds to constraint 13 in step S140.

In an optional embodiment, as shown in Figure 2, the following steps are included after step S150 in the embodiment of the present disclosure:

Step S210: Obtain equipment information of each processing equipment.

Wherein, the equipment information of any one of the processing equipments includes: within a preset time period, the qualification rate of the products to be processed processed by any one of the processing equipments. The preset time period can be set according to actual needs, for example, it can be 7 days, 15 days, etc.

In one embodiment, for any product to be processed, when the quality of the product to be processed is qualified, the quality of the product to be processed is recorded in the equipment information of each processing equipment that processes the product to be processed; when the product to be processed is qualified When the quality of the product is unqualified, the unqualified quality of the product to be processed is recorded in the equipment information of each processing equipment that processes the product to be processed. For example, product A to be processed is produced through three production steps, which are manufacturing, assembly, and spraying. When the quality of product A to be processed is qualified, the production steps corresponding to manufacturing, assembly, and spraying are respectively The quality of product A to be processed is recorded in the equipment information of the processing equipment; when the quality of product A to be processed is unqualified, the quality of product A to be processed is recorded in the equipment information of the processing equipment corresponding to the production steps of manufacturing, assembly and spraying respectively. The quality is substandard. The qualification rate of the products to be processed is obtained by dividing the number of products to be processed with qualified quality processed by each processing equipment within a preset period by the total number of products to be processed processed by the processing equipment.

Step S220: Update the number of processing equipment corresponding to each production step in the first production parameter according to the qualification rate of the product to be processed in each equipment information.

In one implementation, the pass rate threshold can be set in advance. Determine the available processing equipment for which the qualification rate of the products to be processed in the preset equipment information is greater than or equal to the preset qualification rate threshold, and update the corresponding production steps in the first production parameters according to the number of available processing equipment. Number of processing equipment.

In an optional embodiment, as shown in Figure 3, the method for obtaining the distributed flexible workshop scheduling model in the embodiment of the present disclosure includes the following steps:

Step S310: Obtain the training data set and the mixed integer linear programming model to be trained.

Among them, the mixed integer linear programming model to be trained includes: an initial objective function and initial preset constraints.

The Mixed-Integer Linear Programs (MILP) model is a data modeling method for optimization problems, which includes an initial objective function and initial constraints. The goal of the mixed integer programming model is to find an integer solution that optimizes the initial objective function under given initial constraints. Among them, the initial objective function is linear, that is, it is initialized by a linear combination of decision variables; the constraints are also linear, including equality constraints and inequality constraints.

In this embodiment, the initial objective function in the mixed integer linear programming model to be trained can be the same as the objective function in the distributed flexible workshop scheduling model, that is, the objective function shown in formula (1); the mixed integer linear programming model to be trained The initial preset constraints in the planning model can be the same as the constraints in the distributed flexible workshop scheduling model, that is, the constraints represented by equations (2) to (14).

The above training data set includes: multiple pieces of training data. Each of the plurality of pieces of training data respectively includes a node bipartite graph.

In one implementation, the Strong BranchDecision/Strategy (Strong BranchDecision/Strategy) in the Markov Decision Process (MDP) and the Branch-and-Bound (B&B) algorithm can be used, using the solver , solve the mixed integer linear programming model to be trained, and obtain each training data in the training data set. Among them, the branch-and-bound algorithm recursively divides the solution space into a tree search, and calculates the slack bound in the process to prune those subtrees that do not contain the optimal solution; the strong branch strategy is a branch-and-bound algorithm. The strategy used for branching.

The branch result obtained by each branch or split of the node in the branch-and-bound tree corresponding to the mixed integer linear programming model to be trained is a piece of training data. The branch result can be encoded to obtain the corresponding node bipartite graph. For ease of explanation, the branch-and-bound tree of the mixed integer linear programming model to be trained, generated by the solver, is referred to as the target branch-and-bound tree below. When there are a preset number of nodes in the target branch-and-bound tree, the solution of the mixed integer linear programming model to be trained can be stopped to obtain a training data set.

Node bipartite graphs can be used to represent the states of nodes. Each node bipartite graph includes: a plurality of first nodes, a plurality of second nodes and edge features. The edge features include: a feature matrix corresponding to the preset constraint conditions, a feature matrix corresponding to the variables in the mixed integer linear programming model to be trained, and a feature tensor for the edge connecting the first node and the second node. The characteristic matrix corresponding to the preset constraints is used as the first node, and the characteristic matrix corresponding to the variables in the mixed integer linear programming model to be trained is used as the second node. When a variable participates in constraining any constraint, then any The first node corresponding to the constraint condition and the second node corresponding to the variable are connected by an edge, and the edge has a characteristic tensor. Exemplarily, FIG. 4 shows a schematic diagram of a node bipartite graph in an embodiment of the present disclosure. As shown in Figure 4, C ₁ and C ₂ represent the feature matrices corresponding to the preset constraints, which are the first nodes. V ₁ , V ₂ and V ₃ represent the characteristics corresponding to the variables in the mixed integer linear programming model to be trained. The matrix is the second node, and e _1,1 , e _1,2 , e _1,3 , e _2,2 , e _2,3 are the characteristic tensors of the edges connecting the first node and the second node.

Each piece of training data can also include: node branch status and node branch results. The node branch status indicates whether the nodes of the target branch and bound tree of the mixed integer linear programming model to be trained can still branch; the node branch result indicates the number and characteristics of the nodes of the target branch and bound tree of the mixed integer linear programming model to be trained. Information etc.

Step S320: Use the training data set and the strong branch strategy to iteratively train the mixed integer linear programming model to be trained until the training results meet the training stop conditions, and obtain the distributed flexible workshop scheduling model.

In one implementation, the method of training the mixed integer linear programming model each time includes:

Run a strong branching strategy on the mixed integer linear programming model to be trained to generate multiple branching decisions. Any branch decision among the plurality of branch decisions represents the branch result obtained by branching or splitting the nodes in the decision tree generated by running the strong branching strategy on the mixed integer linear programming model to be trained. Branch decision and training data pairs can be determined based on preset pairing rules. For example, training data and branch decisions including processing results for the same at least one node may be combined into a pair of branch decisions and training data.

According to multiple branch decisions and each training data in the training data set, the cross-entropy loss value is calculated using Equation (15); the smaller the cross-entropy loss value, the closer the branch strategy is to the training data;

in, represents the cross entropy loss value, N represents the number of training data in the training data set, s represents the branch decision, a represents the training data (i.e., node bipartite graph), and D represents the set of branch decision and training data pairs, the branch decision and the training data The pair set includes: multiple pairs of branch decisions and training data pairs.

Iteratively perform the above-mentioned operations of running the strong branch strategy and cross-entropy loss value on the mixed integer linear programming model to be trained, and iteratively adjust the parameters of the mixed integer linear programming model to be trained so that the cross-entropy loss value continues to decrease, Until the cross-entropy loss value no longer decreases, it is determined that the mixed integer linear programming model to be trained meets the conditions for stopping training, and the distributed flexible workshop scheduling model is obtained.

In an optional embodiment, as shown in Figure 5, step S320 in the embodiment of the present disclosure also includes the following steps:

Step S321: Obtain the target branch decision corresponding to the mixed integer linear programming model to be trained that meets the training stop condition.

Among them, the target branch decision can be the branch decision obtained by running the strong branch strategy on the mixed integer linear programming model to be trained that satisfies the training stop condition. The target branch decision may include: a bipartite graph of the decision tree of the mixed integer linear programming model to be trained that satisfies the training stop condition.

Step S322: Parameterize the target branch decision to obtain model parameters.

Among them, the pre-trained parametric model can be used to parameterize the target branch decision to obtain the model parameters. That is, the target branch decision is input into the parametric model, and the parametric model outputs the model parameters.

The parameterized model may be a Graph Convolution Neural Network (GCNN). In one implementation, multiple bipartite graph samples labeled with parameter information can be used to train an image neural network to obtain a parameterized model.

Step S323: Obtain a distributed flexible workshop scheduling model based on the model parameters and the mixed integer linear programming model to be trained that satisfies the training stop condition.

Among them, the distributed flexible workshop scheduling model is composed of model parameters and the mixed integer linear programming model to be trained that meets the training stop conditions.

In an optional embodiment, step S310 in the embodiment of the present disclosure may include: using a preset solver and a strong branch strategy to solve the mixed integer linear programming model to be trained to obtain a training data set.

Among them, the preset solver can be any solver that can solve the integer linear programming model. For example, the preset solver can be: SCIP solver, Gurobi solver, MOSEK solver, CMIP solver, etc.

In one implementation, the mixed integer linear programming model to be trained can be input into a preset solver, and the preset solver is set to use the Markov decision process and the strong branch strategy in the branch and bound algorithm. The integer linear programming model is solved, and the preset solver outputs the branch results of each branch or split of the node in the branch-and-bound tree corresponding to the mixed integer linear programming model to be trained, that is, multiple pieces of training data are obtained. Training data builds a training data set.

Figure 6 shows a block diagram of a blockchain-based distributed flexible workshop scheduling device in an embodiment of the present disclosure. As shown in Figure 6, the distributed flexible workshop scheduling device based on blockchain in this embodiment includes:

The first acquisition module 410 is used to acquire a processing request, where the processing request includes: a plurality of work tasks, each of the plurality of work tasks, the work tasks include: a product to be processed, the product to be processed, The processing type of the processed product and the number of workpieces of the product to be processed; the multiple job tasks all have the same production process, and the production process includes multiple production steps with a production sequence;

The first parameter obtaining module 420 is used to obtain first production parameters from the blockchain based on the production process, where the first production parameters include: processing corresponding to each production step in the plurality of production steps. The number of equipment and the transportation time of semi-finished products of the product to be processed between the processing equipment of each two adjacent production steps in the multiple production steps;

The second parameter acquisition module 430 is used to determine second production parameters based on the processing type in the operation task, where the second production parameters include: the operation duration range of the processing equipment to complete a production step, the start-up of the processing equipment The change range of time and the residence time range. The residence time range represents: in the production process of the product to be processed, the time distribution from the end of the processing equipment of the first production step to the start of the processing equipment of the last production step. scope;

The plan generation module 440 is configured to use a pre-trained distributed flexible workshop scheduling model to determine each workpiece based on the production process, the first production parameter, the second production parameter and the number of workpieces of each job task. The production plan of the job tasks is to minimize the total time of the multiple job tasks, wherein the distributed flexible workshop scheduling model includes: an objective function and preset constraints, and the objective function is used to minimize the completion of all tasks. Describe the time of multiple job tasks, and the preset constraints are used to constrain variables in the objective function;

The production and processing module 450 is configured to execute the plurality of work tasks based on the production plan and obtain the number of products to be processed corresponding to the number of workpieces for each work task.

In an optional embodiment, the preset constraints in the embodiment of the present disclosure include: constraints on the production and processing of the processing equipment; constraints on the type of processing to be produced and processed by the processing equipment; constraints on starting processing. Constraints; Constraints on the continuous processing of the processing equipment corresponding to each production and processing step; Constraints on the continuous processing of the processing equipment corresponding to each production and processing step when producing products to be processed of the same processing type; Constraints on the processing of each process on the processing equipment. Constraints on the start time of processing type operations; Constraints on the processing sequence of two consecutive production steps of the same product to be processed; Constraints on the continuous processing sequence on the same processing equipment; For the start of continuous operations on the same processing equipment Sequence constraints; constraints on the time intervals between operations of various processing types on processing equipment; constraints on the residence time of operations of multiple processing types on processing equipment; constraints on operations of multiple processing types on processing equipment Start time constraints.

In an optional embodiment, the blockchain-based distributed flexible workshop scheduling device in the embodiment of the present disclosure also includes: a second acquisition module, used to acquire equipment information of each processing equipment, wherein each processing equipment The equipment information of any processing equipment in the equipment includes: within a preset time period, the qualification rate of the products to be processed processed by any of the processing equipment; an update module for based on the products to be processed in each equipment information According to the pass rate, the number of processing equipment corresponding to each production step in the first production parameter is updated.

In an optional embodiment, the blockchain-based distributed flexible workshop scheduling device in the embodiment of the present disclosure also includes:

The third acquisition module is used to acquire a training data set and a mixed integer linear programming model to be trained, wherein the training data set includes: multiple pieces of training data; each training data in the multiple pieces of training data includes node two. Part diagram; the mixed integer linear programming model to be trained includes: an initial objective function and an initial preset constraint condition;

A training module is used to use the training data set and the strong branch strategy to iteratively train the mixed integer linear programming model to be trained until the training results meet the conditions for stopping training to obtain the distributed flexible workshop scheduling model. In an optional embodiment, the training module in the embodiment of the present disclosure is also used to: obtain the target branch decision corresponding to the mixed integer linear programming model to be trained that satisfies the training stop condition; The decision is parameterized to obtain model parameters; based on the model parameters and the mixed integer linear programming model to be trained that satisfies the training stop condition, the distributed flexible workshop scheduling model is obtained.

In an optional embodiment, the third acquisition module in the embodiment of the present disclosure is also used to use a preset solver and the strong branch strategy to solve the mixed integer linear programming model to be trained, and obtain The training data set.

In the distributed flexible workshop scheduling device based on the blockchain of the present disclosure, the various optional embodiments, optional implementations and optional examples disclosed above can be flexibly selected and combined as needed to achieve corresponding The functions and effects are not listed one by one in this disclosure.

The blockchain-based distributed flexible workshop scheduling device of the present disclosure corresponds to the above-mentioned embodiments of the blockchain-based distributed flexible workshop scheduling method of the present disclosure. Relevant content can be referred to each other and will not be described again here. .

The beneficial technical effects corresponding to the exemplary embodiments of the image annotation device can be found in the corresponding beneficial technical effects in the above exemplary method section, and will not be described again here.

In addition, embodiments of the present disclosure also provide an electronic device, including:

Memory, used to store computer programs;

A processor, configured to execute a computer program stored in the memory, and when the computer program is executed, implement the blockchain-based distributed flexible workshop scheduling method described in any of the above embodiments of the present disclosure.

FIG. 7 is a schematic structural diagram of an application embodiment of the electronic device of the present disclosure. Next, an electronic device according to an embodiment of the present disclosure is described with reference to FIG. 7 . The electronic device may be either or both of the first device and the second device, or a stand-alone device independent of them. The stand-alone device may communicate with the first device and the second device to receive the collected information from them. input signal.

As shown in Figure 7, an electronic device includes one or more processors and memory.

The processor may be a central processing unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

Memory may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and/or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor may execute the program instructions to implement the blockchain-based distributed flexibility of various embodiments of the present disclosure described above. Shop scheduling methods and/or other desired functionality.

In one example, the electronic device may further include an input device and an output device, and these components are interconnected through a bus system and/or other forms of connection mechanisms (not shown).

In addition, the input device may also include, for example, a keyboard, a mouse, and the like.

The output device can output various information to the outside, including determined distance information, direction information, etc. The output devices may include, for example, displays, speakers, printers, and communication networks and remote output devices to which they are connected, among others.

Of course, for simplicity, only some of the components in the electronic device related to the present disclosure are shown in FIG. 7 , and components such as buses, input/output interfaces, etc. are omitted. In addition to this, the electronic device may include any other suitable components depending on the specific application.

In addition to the above methods and devices, embodiments of the present disclosure may also be a computer program product, which includes computer program instructions that, when executed by a processor, cause the processor to perform the steps described in the above part of this specification. Steps in the blockchain-based distributed flexible workshop scheduling method of various embodiments of the present disclosure.

The computer program product may be written with program code for performing operations of embodiments of the present disclosure in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc. , also includes conventional procedural programming languages, such as the "C" language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server execute on.

In addition, embodiments of the present disclosure may also be a computer-readable storage medium having computer program instructions stored thereon. The computer program instructions, when executed by a processor, cause the processor to perform the steps described in the above part of this specification according to the present invention. Steps in the blockchain-based distributed flexible workshop scheduling method of various embodiments are disclosed.

The computer-readable storage medium may be any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: electrical connection with one or more conductors, portable disk, hard disk, random access memory (RAM), read only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.

Those of ordinary skill in the art can understand that all or part of the steps to implement the above method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, It includes the steps of the above method embodiment; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other various media that can store program codes.

The basic principles of the present disclosure have been described above in conjunction with specific embodiments. However, it should be pointed out that the advantages, advantages, effects, etc. mentioned in the present disclosure are only examples and not limitations. These advantages, advantages, effects, etc. cannot be considered to be Each embodiment of the present disclosure must have. In addition, the specific details disclosed above are only for the purpose of illustration and to facilitate understanding, and are not limiting. The above details do not limit the present disclosure to be implemented by using the above specific details.

Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on its differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple. For relevant details, please refer to the partial description of the method embodiment.

The block diagrams of the devices, devices, equipment, and systems involved in the present disclosure are only illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, devices, equipment, and systems may be connected, arranged, and configured in any manner. Words such as "includes," "includes," "having," etc. are open-ended terms that mean "including, but not limited to," and may be used interchangeably therewith. As used herein, the words "or" and "and" refer to the words "and/or" and are used interchangeably therewith unless the context clearly dictates otherwise. As used herein, the word "such as" refers to the phrase "such as, but not limited to," and may be used interchangeably therewith.

The methods and apparatus of the present disclosure may be implemented in many ways. For example, the methods and devices of the present disclosure may be implemented through software, hardware, firmware, or any combination of software, hardware, and firmware. The above order for the steps of the methods is for illustration only, and the steps of the methods of the present disclosure are not limited to the order specifically described above unless otherwise specifically stated. Furthermore, in some embodiments, the present disclosure can also be implemented as programs recorded in recording media, and these programs include machine-readable instructions for implementing methods according to the present disclosure. Thus, the present disclosure also covers recording media storing programs for executing methods according to the present disclosure.

It should also be noted that in the devices, equipment and methods of the present disclosure, each component or each step can be decomposed and/or recombined. These decompositions and/or recombinations should be considered equivalent versions of the present disclosure.

The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

The foregoing description has been presented for the purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of the present disclosure to the form disclosed herein. Although various example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims (10)

1. A distributed flexible workshop scheduling method based on blockchain, which is characterized by including: Obtain a processing request, wherein the processing request includes: a plurality of work tasks, each of the plurality of work tasks, the work tasks include: a product to be processed, a processing type of the product to be processed, and the The number of workpieces of the product to be processed; the multiple job tasks all have the same production process, and the production process includes multiple production steps with a production sequence; Based on the production process, first production parameters are obtained from the blockchain, where the first production parameters include: the number of processing equipment corresponding to each production step in the plurality of production steps and the semi-finished products of the product to be processed. The transportation time between the processing equipment of each two adjacent production steps in the plurality of production steps; Based on the processing type in the operation task, the second production parameters are determined, wherein the second production parameters include: the operation duration range of the processing equipment to complete a production step, the variation range of the start-up time of the processing equipment, and the residence time range, The residence time range represents: in the production process of the product to be processed, the time distribution range from the end of the processing equipment of the first production step to the start of the processing equipment of the last production step; According to the production process, the first production parameter, the second production parameter and the number of workpieces of each operation task, a pre-trained distributed flexible workshop scheduling model is used to determine the production plan of each operation task, so as to Minimize the total time of the multiple job tasks, wherein the distributed flexible workshop scheduling model includes: an objective function and preset constraints, the objective function is used to minimize the time to complete the multiple job tasks , the preset constraints are used to constrain the variables in the objective function; The plurality of work tasks are executed based on the production plan to obtain products to be processed corresponding to the number of workpieces for each work task. 2. The method according to claim 1, characterized in that the preset constraints include: Constraints on production and processing of processing equipment; Constraints on the type of processing to be produced by the processing equipment; Constraints on starting processing; Constraints on continuous processing of processing equipment corresponding to each production and processing step; Constraints on the continuous processing of processing equipment corresponding to each production and processing step when producing products to be processed of the same processing type; Constraints on the start time for starting processing of each processing type on the processing equipment; Constraints on the processing sequence of two consecutive production steps of the same product to be processed; Constraints on the sequence of consecutive processing on the same processing equipment; Constraints on the starting sequence for continuous operations on the same processing equipment; Constraints on the time intervals between operations of each processing type on processing equipment; Constraints on the residence time of multiple processing types on processing equipment; Constraints on start times for jobs of multiple processing types on processing equipment. 3. The method according to claim 1, wherein after executing the plurality of work tasks based on the production plan and obtaining the number of products to be processed corresponding to the number of workpieces corresponding to each work task, the method further includes: Obtain equipment information of each processing equipment, wherein the equipment information of any one of the processing equipment includes: within a preset time period, the qualification rate of the products to be processed processed by the any processing equipment; According to the qualification rate of the products to be processed in each equipment information, the number of processing equipment corresponding to each production step in the first production parameter is updated. 4. The method according to claim 1, characterized in that the distributed flexible workshop scheduling model is trained in the following manner: Obtain a training data set and a mixed integer linear programming model to be trained, wherein the training data set includes: multiple pieces of training data; each training data in the multiple pieces of training data respectively includes a node bipartite graph; the to-be-trained The mixed integer linear programming model includes: initial objective function and initial preset constraints; Using the training data set and the strong branch strategy, the mixed integer linear programming model to be trained is iteratively trained until the training results meet the training stop conditions, and the distributed flexible workshop scheduling model is obtained. 5. The method of claim 4, wherein the mixed integer linear programming model to be trained is iteratively trained using the training data set and a strong branching strategy until the training result satisfies the training stop condition, to obtain The distributed flexible workshop scheduling model includes: Obtain the target branch decision corresponding to the mixed integer linear programming model to be trained that meets the training stop condition; Parameterize the target branch decision to obtain model parameters; Based on the model parameters and the mixed integer linear programming model to be trained that satisfies the training stop condition, the distributed flexible workshop scheduling model is obtained. 6. The method according to claim 4, characterized in that said obtaining a training data set includes: The mixed integer linear programming model to be trained is solved using a preset solver and the strong branch strategy to obtain the training data set. 7. A distributed flexible workshop scheduling device based on blockchain, characterized by including: The first acquisition module is used to acquire a processing request, where the processing request includes: a plurality of job tasks, each of the plurality of job tasks, the job task includes: a product to be processed, the product to be processed The processing type of the product and the number of workpieces of the product to be processed; the multiple job tasks all have the same production process, and the production process includes multiple production steps with a production sequence; A first parameter acquisition module, configured to obtain first production parameters from the blockchain based on the production process, where the first production parameters include: processing equipment corresponding to each of the multiple production steps. The quantity and transportation time of the semi-finished products to be processed between the processing equipment of each two adjacent production steps in the multiple production steps; The second parameter acquisition module is used to determine second production parameters based on the processing type in the operation task, where the second production parameters include: the operation duration range of the processing equipment to complete one production step, and the start-up time of the processing equipment. The change range and residence time range, the residence time range represents: in the production process of the product to be processed, the time distribution range from the end of the processing equipment of the first production step to the start of the processing equipment of the last production step ; A solution generation module, configured to use a pre-trained distributed flexible workshop scheduling model to determine each job based on the production process, the first production parameter, the second production parameter and the number of workpieces of each job task. The production plan of the task is to minimize the total time of the multiple job tasks, wherein the distributed flexible workshop scheduling model includes: an objective function and preset constraints, and the objective function is used to minimize the completion of the The time of multiple job tasks, the preset constraints are used to constrain the variables in the objective function; A production and processing module is used to execute the plurality of work tasks based on the production plan and obtain the number of products to be processed corresponding to the number of workpieces for each work task. 8. The device according to claim 7, characterized in that the preset constraints include: Constraints on production and processing of processing equipment; Constraints on the type of processing to be produced by the processing equipment; Constraints on starting processing; Constraints on continuous processing of processing equipment corresponding to each production and processing step; Constraints on the continuous processing of processing equipment corresponding to each production and processing step when producing products to be processed of the same processing type; Constraints on the start time for starting processing of each processing type on the processing equipment; Constraints on the processing sequence of two consecutive production steps of the same product to be processed; Constraints on the sequence of consecutive processing on the same processing equipment; Constraints on the starting sequence for continuous operations on the same processing equipment; Constraints on the time intervals between operations of each processing type on processing equipment; Constraints on the residence time of multiple processing types on processing equipment; Constraints on start times for jobs of multiple processing types on processing equipment. 9. An electronic device, characterized in that it includes: Memory, used to store computer programs; A processor, configured to execute a computer program stored in the memory, and when the computer program is executed, implement the blockchain-based distributed flexible workshop scheduling method described in any one of claims 1-6. 10. A computer-readable storage medium with a computer program stored thereon, characterized in that, when executed by a processor, the computer program implements the blockchain-based distributed flexibility described in any one of claims 1-6. Shop floor scheduling methods.