CN118032052A

CN118032052A - Flexible circuit board production monitoring system, method and device and storage medium

Info

Publication number: CN118032052A
Application number: CN202410195445.3A
Authority: CN
Inventors: 李柏翰; 丁志华; 谭儒峰; 朱勇彬
Original assignee: Injection Precision Rubber Suzhou Co ltd
Current assignee: Injection Precision Rubber Suzhou Co ltd
Priority date: 2024-02-22
Filing date: 2024-02-22
Publication date: 2024-05-14

Abstract

The embodiment of the specification provides a flexible circuit board production monitoring system, a method, a device and a storage medium, wherein the system comprises: the system comprises a visual detection module, a characteristic monitoring module, an environment monitoring module and a processor; the visual detection module is configured to acquire image information of at least one layer of a copper foil layer, a substrate layer and an adhesive layer of the flexible circuit board; the feature monitoring module comprises at least one of a gravity sensor and a temperature sensor, and is configured to monitor physical and chemical features of an intermediate product of the flexible circuit board; the environment monitoring module is configured to monitor environment data of the production flexible circuit board; the processor is configured to: determining residual information of the contaminant based on the image information; determining an oxidation risk of the intermediate product based on at least one of the environmental data, the physicochemical characteristics of the intermediate product, and the residual information of the contaminant; and generating a control instruction in response to the oxidation risk meeting a first preset condition, wherein the control instruction is used for adjusting environmental data and/or temperature data of the intermediate product.

Description

Flexible circuit board production monitoring system, method and device and storage medium

Technical Field

The present disclosure relates to the field of flexible circuit boards, and in particular, to a system, a method, an apparatus, and a storage medium for monitoring production of a flexible circuit board.

Background

A flexible circuit board (FPC) is a printed circuit made of a flexible insulating substrate, and generally includes a multi-layered structure such as a plurality of PET protective layers, copper foil layers, etc., which can be freely bent, rolled, folded. However, in the production process of the flexible circuit board, due to the need of connecting the multi-layer structure, defects such as dislocation of drilling, scratch, poor dispensing, copper leakage and the like may exist. At present, the defects are usually identified by adopting a machine vision detection mode and the like, but for the problems of relatively concealed parts such as partial copper layer oxidation, insufficient silver paste printing quantity, excessively thin conductive adhesive and the like, the analysis by conventional image identification is often difficult.

Aiming at how to solve the detection problem of the flexible circuit board, CN109239102B provides a detection method for appearance defects of the flexible circuit board based on CNN, and the defects of the flexible circuit board can be identified based on convolutional neural networks (Convolutional Neural Network, CNN), so that the problems of appearance defects of the flexible circuit board under specific conditions, such as the defects of small size and complex characteristics, can be detected, but the method can not well detect the problems of insufficient silver paste printing quantity, excessively thin conductive adhesive and the like.

Therefore, the flexible circuit board production monitoring system and the flexible circuit board production monitoring method are beneficial to reducing defects of the flexible circuit board and guaranteeing high-efficiency and high-quality production of the flexible circuit board.

Disclosure of Invention

One or more embodiments of the present specification provide a flexible circuit board production monitoring system, the system comprising: the system comprises a visual detection module, a characteristic monitoring module, an environment monitoring module and a processor; the visual detection module is configured to acquire image information of at least one layer of a copper foil layer, a substrate layer and an adhesive layer of the flexible circuit board; the feature monitoring module comprises at least one of a weight sensor and a temperature sensor, and is configured to monitor physical and chemical features of an intermediate product of the flexible circuit board, wherein the physical and chemical features comprise at least one of temperature data and weight data of the intermediate product; the environment monitoring module is configured to monitor environment data of the flexible circuit board; the processor is configured to: determining residual information of the contaminant based on the image information; determining a risk of oxidation of the intermediate product based on at least one of the environmental data, the physicochemical characteristics of the intermediate product, and the residual information of the contaminant; and generating a control instruction in response to the oxidation risk meeting a first preset condition, wherein the control instruction is used for adjusting the environmental data and/or the temperature data of the intermediate product.

One or more embodiments of the present specification provide a flexible circuit board production monitoring method implemented by a processor of a flexible circuit board production monitoring system, the method comprising: determining residual information of the contaminant based on the image information; determining an oxidation risk of the intermediate product based on the environmental data, a materialized characteristic of the intermediate product, and residual information of the contaminant, the materialized characteristic including at least one of temperature data, weight data of the intermediate product; and generating a control instruction in response to the oxidation risk meeting a first preset condition, wherein the control instruction is used for adjusting the environmental data and/or the temperature data of the intermediate product.

Drawings

The present specification will be further elucidated by way of example embodiments, which will be described in detail by means of the accompanying drawings. The embodiments are not limiting, in which like numerals represent like structures, wherein:

FIG. 1 is a schematic diagram of a flexible circuit board production monitoring system according to some embodiments of the present disclosure;

FIG. 2 is an exemplary flow chart of a flexible circuit board production monitoring method according to some embodiments of the present description;

FIG. 3 is an exemplary schematic diagram of a risk assessment model shown in accordance with some embodiments of the present description;

FIG. 4 is an exemplary schematic illustration of determining the bend qualification of an intermediate product, shown in accordance with some embodiments of the present disclosure;

fig. 5 is an exemplary flow chart for determining early warning information according to some embodiments of the present disclosure.

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the drawings that are required to be used in the description of the embodiments will be briefly described below. It is apparent that the drawings in the following description are only some examples or embodiments of the present specification, and it is possible for those of ordinary skill in the art to apply the present specification to other similar situations according to the drawings without inventive effort. Unless otherwise apparent from the context of the language or otherwise specified, like reference numerals in the figures refer to like structures or operations.

It will be appreciated that "system," "apparatus," "unit" and/or "module" as used herein is one method for distinguishing between different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

As used in this specification and the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.

A flowchart is used in this specification to describe the operations performed by the system according to embodiments of the present specification. It should be appreciated that the preceding or following operations are not necessarily performed in order precisely. Rather, the steps may be processed in reverse order or simultaneously. Also, other operations may be added to or removed from these processes.

The flexible circuit board (FPC) is also called as a soft board, has excellent electrical performance, can meet the design requirement of smaller and higher-density installation, is also beneficial to reducing assembly production procedures and enhancing reliability, can bear millions of dynamic bending without damaging wires, can be arranged randomly according to space layout requirements, and is generally used for flexible keyboards, folding mobile phones and the like. However, the flexible circuit board often has a multi-layer structure, and defects such as dislocation of drilling holes, scratching, poor dispensing, copper leakage and the like may occur in the production process. At present, two modes of manual detection and traditional machine vision detection are mainly adopted for a flexible circuit board, wherein: the manual detection has the defects of high cost, low efficiency, low accuracy and the like; the flexible circuit board has various defects, different defect characteristic sizes and relatively complex defect definition, and the traditional machine vision detection mode is difficult to realize detection of defect types such as partial copper layer oxidation, insufficient silver paste printing quantity, excessively thin conductive adhesive and the like.

In view of this, some embodiments of the present disclosure provide a system and a method for monitoring production of a flexible circuit board, which monitor the flexible circuit board during the production process, obtain oxidation risk and bending qualification, and evaluate possible defects and risks of the flexible circuit board, thereby improving the production efficiency and quality of the flexible circuit board.

Fig. 1 is a schematic diagram of a flexible circuit board production monitoring system according to some embodiments of the present disclosure.

As shown in fig. 1, the flexible circuit board production monitoring system 100 may include a visual inspection module 110, a feature monitoring module 120, an environmental monitoring module 130, a bend detection module 140, and a processor 150.

In some embodiments, the flexible circuit board production monitoring system 100 (hereinafter referred to as system 100) may be applied to various fields of flexible circuit board inspection. For example, on a production line of a flexible circuit board, the system 100 can monitor the production flow of the flexible circuit board in real time, immediately warn when abnormality is found, and reduce the generation of unqualified products; for another example, in the production process of the flexible keyboard, the folding mobile phone and the like, the system 100 can automatically detect the flexible circuit board, screen out unqualified products and ensure the product quality.

The vision inspection module 110 is a device that collects and/or processes information related to the flexible circuit board during the manufacturing process. For example, the visual detection module 110 may include an imaging device, such as a high resolution camera or an image sensor, or the like.

In some embodiments, the visual detection module 110 may be configured to obtain image information of at least one of a copper foil layer, a substrate layer, and an adhesive layer of a flexible circuit board. For more content of image information, see the relevant description of fig. 2.

Wherein the copper foil layer is the substrate of the circuit wires and surface mount components of the flexible circuit board. The substrate layer is the base layer of the flexible circuit board for providing structural support to the circuit conductors and components. In some embodiments, the material of the substrate layer comprises a high temperature plastic such as polyimide, polyester, polyimide-polyester composite, or the like. An adhesive layer is a special layer of material that is used to bond layers of material together. The materials of the adhesive layer may include thermosetting resins, thermoplastic resins, adhesives, and the like. The adhesive layer can ensure stability and mechanical strength between the layers, and prevent relative sliding and peeling between the layers.

In some embodiments, the visual detection module 110 may further include an image processing device for processing and analyzing the image information. For example, the visual detection module 110 may extract feature information of the image by using a corresponding image processing algorithm, and perform positioning, identification, grading, and other processes of the surface defect of the flexible circuit board according to the feature information. Among other image processing algorithms, but not limited to, support vector machines, K nearest neighbors, decision trees, neural networks, and the like.

In some embodiments, the visual detection module 110 may acquire image information in a variety of possible ways, including, but not limited to, continuous acquisition, timed acquisition, and the like. In some embodiments, there may be multiple cameras, and multiple cameras may be placed in different locations to obtain image information at different angles at the same time.

In some embodiments, the production process of the flexible circuit board may include a plurality of production processes, and the processor 150 may control the visual detection module 110 to capture images of the respective production processes, respectively, to obtain image information corresponding to the respective production processes. The various production processes of the production process can include production processes of cutting, punching, exposing, developing, etching, laminating, punching, electrical testing, reinforcing film attaching, functional testing and the like. The production process refers to the various steps or stages through which a flexible circuit board is manufactured.

In some embodiments, the visual detection module 110 may be deployed in at least one location in a flexible circuit board manufacturing facility. In some embodiments, the number of deployments and deployment locations of the visual detection module 110 may be predetermined. For example, the number of deployments of the visual inspection modules 110 may be determined according to the production process of the flexible circuit board, and the number of visual inspection modules 110 is increased as the production process of the flexible circuit board is increased. For example, one visual inspection module 110 may correspond to one production process, or one visual inspection module 110 may correspond to a plurality of production processes.

The feature monitoring module 120 is a device for monitoring information about the intermediate product itself of the flexible circuit board. In some embodiments, the feature monitoring module 120 is configured to monitor a physicochemical feature of an intermediate product of the flexible circuit board. The intermediate product comprises intermediate products of various links of the flexible circuit board in the production flow. For more on intermediate products, physicochemical characteristics, see the relevant description of fig. 2.

In some embodiments, the feature monitoring module 120 may be deployed in at least one location in a flexible circuit board production plant. In some embodiments, the number and location of deployments of the feature monitoring module 120 may be predetermined. For example, the number of deployments of the feature monitoring modules 120 may be determined according to the production process of the flexible circuit board, the more production processes of the production process of the flexible circuit board, the more the number of feature monitoring modules 120. For example, one feature monitoring module 120 may correspond to one production process, or one feature monitoring module 120 may correspond to multiple production processes.

In some embodiments, the feature monitoring module 120 may include at least one of a weight sensor, a temperature sensor, etc., and the relevant information includes at least one of temperature data, weight data, etc. of the intermediate product, accordingly. The weight sensor may include a strain gauge load cell, a capacitive load cell, or the like. The temperature sensor may include a thermocouple, a resistance temperature detector, or the like.

For more on temperature data, weight data, see the relevant description of fig. 2.

In some embodiments, the feature monitoring module 120 may be communicatively coupled to the processor 150 for transmitting the measured physicochemical features of the intermediate product to the processor 150.

In some embodiments, the feature monitoring module 120 may further include a temperature regulating element (not shown) for cooling or heating the intermediate product to control the temperature of the intermediate product within a target temperature range. For example, the temperature regulating element may activate the heating device, control the power of the heating device, etc. to achieve a temperature increase. Taking a resistive heating device as an example, the temperature regulating element may increase or decrease the heating rate by increasing or decreasing the power of the resistive heating device. For another example, the temperature regulating element may turn on the cooling device, control the power of the cooling device, etc. Taking a water cooling device as an example, the temperature regulating element can reduce the temperature by controlling the power or water flow of the water cooling device, for example, the temperature regulating element can increase or decrease the cooling rate by increasing or decreasing the power or water flow of the water cooling device. The target temperature range may be a system default, or determined empirically or experimentally.

The environment monitoring module 130 is a related device for monitoring the space environment where the flexible circuit board is produced in real time. The space environment refers to the environments of a production workshop, a factory, a laboratory and the like. In some embodiments, the environmental monitoring module 130 is configured to monitor environmental data for the production of flexible circuit boards. The environmental data is a physical quantity describing the relevant environmental conditions inside/outside the space, such as temperature, humidity, pressure, etc.

In some embodiments, the environmental monitoring module 130 may include a temperature sensor, a humidity sensor, etc., and the environmental data may include an ambient temperature, an ambient humidity, etc.

In some embodiments, the environmental monitoring module 130 may be communicatively coupled to the processor 150 for transmitting measured environmental data to the processor 150.

In some embodiments, the environmental monitoring module 130 may include a temperature control module, a humidity control module (not shown). The temperature control module refers to a device for regulating the temperature inside the production environment. For example, the temperature control module may control heating or cooling of the temperature control module according to a control instruction of the processor 150, so as to achieve the purpose of adjusting the indoor temperature, and accordingly, the temperature control module may include: a heater and a refrigerator. The heater can heat up the production environment through electric current, and the refrigerator can realize the refrigeration in space through the circulation of refrigerant.

The humidity control module refers to a device for regulating the humidity inside the production environment. For example, the humidity control module may control dehumidification or humidification of the humidity control module according to control instructions of the processor 150 for the purpose of adjusting humidity in the production environment. For example, the humidity control module may include a humidifying device, a moisture absorbing device, or other device for changing the humidity in the room.

In some embodiments, the system 100 further includes a bend detection module 140. The bending detection module 140 is a device for detecting bending of the flexible circuit board.

In some embodiments, the bending detection module 140 is configured to perform bending detection on the flexible circuit board based on preset detection parameters to obtain detection data. For example, the bend detection module 140 may include a bend force applying unit, a sensor assembly, and the like. The bending force applying unit is a device for applying force to the flexible circuit board to bend and deform the flexible circuit board. For example, the bending urging unit may be a robot or the like. The sensor assembly is a related information device for monitoring the flexible circuit board when bending detection is carried out. For example, the sensor assembly may include a camera, an elastic force sensor, a sound sensor, etc., and the corresponding detection data may include sound data, elastic force data, image data, etc. For more on the detection data, see the relevant description of fig. 4.

Bending detection is a process of bending a flexible circuit board and is used for simulating the situation of bending stress born by the flexible circuit board in the actual use process. The bending test is used to test the performance of the flexible circuit board in a bent state.

In some embodiments, the bending detection module 140 may perform bending detection on each intermediate circuit of the flexible circuit board, and the bending detection module 140 may also perform bending detection on the final flexible circuit board.

The preset detection parameters refer to parameters adopted by the bending detection module 140 in bending detection. For example, the preset detection parameters may include a number of bends, a bending frequency, a bending angle, a bending duration, etc., or any combination thereof.

The rate of bending refers to the rate at which the flexible circuit board is bent. The greater the bending rate, the shorter the time from the beginning of bending to the completion of bending of the flexible circuit board. For example, the bending rate may include the degree or amount of change in angle of bending deformation of the flexible circuit board per unit time.

In some embodiments, the processor 150 may obtain the displacement of the bending force applying unit during one bending detection process, and the time period for the flexible circuit board to complete one bending, and determine the bending rate based on the displacement and the time period. Completing a bend refers to the process from unbent to complete.

In some embodiments, the processor 150 may also implement different bending rates of the flexible circuit board by controlling the force magnitude and the movement rate of the bending force applying unit.

The bending amplitude refers to the degree of bending deformation or the variation of angle when the flexible circuit board completes one bending.

In some embodiments, the processor 150 may obtain image data of the flexible circuit board when completing one bending through the camera, obtain a bending curve based on the image data through an image recognition algorithm, and determine a bending amplitude based on an average value of curvatures of respective sampling points on the bending curve. For example, the larger the average value, the larger the bending amplitude. The image recognition algorithm comprises, but is not limited to, a feature extraction algorithm, a template matching algorithm, a classification algorithm and the like.

The bending curve refers to a curve shape formed by bending and deforming the flexible circuit board.

The sampling points are the result of sampling the curve shape. In some embodiments, the processor 150 may sample the bending curve by a sampling algorithm to obtain a plurality of sampling points. The sampling algorithm may include random sampling, uniform sampling, gaussian sampling, and the like.

The curvature of a sampling point on a curved curve refers to the degree of curvature of the curve at that sampling point. In some embodiments, processor 150 may determine the curvature of each sample point on the curved line based on the rate of change of the angle of the curve from the plane in the tangential direction at that point.

The bending time period refers to the length of time that the flexible circuit board needs to be maintained in a bent state.

In some embodiments, the processor 150 may control the bending detection module 140 to perform bending detection on the flexible circuit board based on a preset detection parameter set. The preset detection parameter set is a set formed by each preset parameter. For example, the set of preset detection parameters may include a bending rate, a bending amplitude, a bending duration, and the like. The set of preset detection parameters may be determined experimentally or empirically.

In some embodiments, processor 150 may repeatedly perform a plurality of bend tests based on one or more sets of preset test parameters, respectively. The number of repetitions and the time interval between two adjacent bending detections may be a system preset value, a system default value, etc. For more on the time interval of the bend detection, see the relevant description of fig. 4.

Processor 150 refers to a system with computing capabilities, such as a computer, industrial personal computer, computing cloud platform, and the like. In some embodiments, processor 150 may include one or more sub-processors. Such as a Central Processing Unit (CPU), a Graphics Processor (GPU), or the like, or any combination thereof.

In some embodiments, the processor 150 may obtain data and/or information from the visual detection module 110, the feature monitoring module 120, the environmental monitoring module 130, the buckle detection module 140, etc. in the system 100. Processor 150 may execute program instructions based on such data, information, and/or processing results to perform one or more of the functions described in the embodiments herein.

In some embodiments, the processor 150 may be communicatively coupled to the vision inspection module 110, the feature monitoring module 120, the environment monitoring module 130, the bend detection module 140, etc., and the processor 150 may be configured to control the operation of the system 100: determining residual information of the contaminant based on the image information; determining the oxidation risk of the intermediate product based on the environmental data, the physicochemical characteristics of the intermediate product and the residual information of the pollutants; and generating a control instruction in response to the oxidation risk meeting a first preset condition, wherein the control instruction is used for adjusting environmental data and/or temperature data of the intermediate product.

In some embodiments, system 100 may include a network and/or other components that connect the system to external resources. Processor 150 may obtain data and/or information related to system 100 via a network.

In some embodiments, some logic of the visual detection module 110 may be implemented based on the processor 150. For example, the image processing logic in the visual inspection module 110 may be integrated into the execution program of the processor 150, and the processor 150 processes and analyzes the image information.

In some embodiments, the system 100 may also include a user terminal. A user terminal may refer to one or more terminal devices used by a user and the processor 150 may be integrated in the user terminal. A user may refer to an administrator or operator of the system 100, or the like.

In some embodiments, the user terminal may be used to display pre-warning information to the user and to obtain operational feedback of the user. In some embodiments, the user terminal may include input components, output components, such as buttons, touch sensors, a joystick, a keypad, a microphone, a display screen, and the like. In some embodiments, the user terminal may include a mobile device, a tablet computer, a laptop computer, other input and/or output enabled devices, etc., or any combination thereof.

In some embodiments, system 100 may also include a memory module (not shown) that may be used to store data, instructions, and/or any other information. For example, the storage module may store environmental data, control instructions, image information, and the like. In some embodiments, the memory module may include Random Access Memory (RAM), read Only Memory (ROM), mass storage, removable memory, volatile read-write memory, and the like, or any combination thereof. In some embodiments, the storage module may be integrated or included in one or more other components of the system 100 (e.g., the processor 150, the user terminal, the bend detection module 140, etc.).

In some embodiments of the present disclosure, the working states of the components in the flexible circuit board production monitoring system are adjusted by the processor, so that the production process can be optimized, the quality of the produced flexible circuit board can be improved, and the production efficiency can be further improved.

It should be noted that the above description of the flexible circuit board production monitoring system and the modules thereof is for convenience of description only, and is not intended to limit the present disclosure to the scope of the illustrated embodiments. It will be appreciated by those skilled in the art that, given the principles of the system, various modules may be combined arbitrarily or a subsystem may be constructed in connection with other modules without departing from such principles. In some embodiments, the storage module and the image processing apparatus disclosed in fig. 1 may be different modules in one system, or may be one module to implement the functions of two or more modules. For example, each module may share one memory module, or each module may have a respective memory module. Such variations are within the scope of the present description.

Fig. 2 is an exemplary flow chart of a flexible circuit board production monitoring method according to some embodiments of the present description.

In some embodiments, the process 200 may be implemented based on a processor of a flexible circuit board production monitoring system. As shown in fig. 2, the process 200 includes the steps of:

at step 210, residual information of the contaminant is determined based on the image information.

The contaminants refer to impurities, foreign substances, or the like remaining on the flexible circuit board. For example, the contaminants may include at least one of dust, fiber, swarf, or chemical residues, among others.

The image information refers to images of various intermediate products of the flexible circuit board during the production process.

In some embodiments, the production process of the production flow is different and the corresponding image information is different. Each production process corresponds to an image information or a group of image information. In some embodiments, the set of image information may be a sequence of images of the intermediate product at different times.

In some embodiments, the processor may obtain the image information through a visual detection module installed at various locations within the space, e.g., the image information may be uploaded to the processor through a network periodically or in real time after being collected by the visual detection module. In some embodiments, the image information may be uploaded to the storage module in real time after being collected by the visual detection module, and the processor may read the image information from the storage module periodically or in real time.

Residual information refers to information related to the residue. For example, the residual information may include the amount of the residue, the position of the residue, and the like.

In some embodiments, the processor determines residual information of the contaminant based on the image information in a variety of ways. The processor may also predict residual information of the contaminant by image recognition models, for example. The image recognition model may be a machine learning model such as a trained neural network, the input of the image recognition model may include a set of image information, and the output may include residual information of the contaminant. The image recognition model may be trained in various possible ways based on a number of first training samples with first labels. For example, parameter updates may be performed based on a gradient descent method. The first training sample may include a set of sample image information, may be obtained based on historical data, and the first label may be residual information of the contaminant to which the set of sample image information actually corresponds, and may be obtained by manual or processor labeling.

Step 220, determining the oxidation risk of the intermediate product based on the environmental data, the physicochemical characteristics of the intermediate product, and the residual information of the contaminant.

The environmental data is data related to the production environment of the flexible circuit board. For example, the environmental data may include an ambient temperature, an ambient humidity, and the like. The representation form of the environment data can be images, texts and the like, and the environment data can be obtained according to actual requirements. For example, the environmental data may be time-dependent. For example, the environmental data may be related data including (e.g., approximately 2 weeks, etc.) ambient temperature, ambient humidity, PM2.5 values, etc. Wherein ambient temperature is used to characterize the temperature within the finger space. Ambient humidity is used to characterize the humidity within the finger space.

In some embodiments, the environmental data may be obtained from an environmental monitoring module by a processor. For example, the environmental data produced is detected by the environmental monitoring module, and the processor may receive the environmental data detected by the environmental monitoring module in real time.

In some embodiments, the environmental data detected by the environmental monitoring module may be uploaded to the storage module for storage. The processor may take environmental data from the memory module on its own initiative (e.g., in real-time, at intervals, or triggered under certain circumstances).

The intermediate product refers to the product of each production process in the production flow. In some embodiments, the intermediate product may be a product or component in a manufacturing process that requires further processing, handling or inspection to become the final flexible circuit board. In some embodiments, the intermediate product may also be a product that is processed in a certain manufacturing process and is waiting for a bend test/function test/factory test to be performed.

Physicochemical characteristics are used to characterize the physical and chemical properties associated with the intermediate product. For example, the physicochemical characteristics may include, but are not limited to, weight data of the intermediate product, temperature data of the intermediate product, size and shape of the intermediate product, and the like.

It should be noted that, when the intermediate product is transferred from a region or plant with a high temperature to a region or plant with a low temperature, water mist may be condensed on the surface of the intermediate product to cause oxidation, so that the oxidation condition of the intermediate product is helpful to be known by obtaining physical and chemical characteristics.

In some embodiments, the physicochemical characteristics include at least one of temperature data, weight data, etc. of the intermediate product.

The temperature data is data characterizing the temperature of the intermediate product itself. The weight data is data characterizing the weight of the intermediate product itself.

The risk of oxidation is used to characterize the likelihood of oxidation of the various components on the various intermediate products during the production process. For example, oxidation may include oxidation of gold fingers on the intermediate product, oxidation of copper foil, and the like.

In some embodiments, the processor determines the oxidation risk of the intermediate product in a number of ways based on the environmental data, the physicochemical characteristics of the intermediate product, and the residual information of the contaminant. For example, the risk of oxidation of the intermediate product may be determined by a preset table or vector database built based on historical data. The preset table/vector database may be a table or database characterizing the correspondence of different environmental data, physicochemical characteristics of the intermediate products, and residual information of contaminants to oxidation risks of different intermediate products. For another example, the processor may model or employ various data analysis algorithms, such as regression analysis, to analyze the environmental data, the physicochemical characteristics of the intermediate product, and the residual information of the contaminant, to predict the oxidation risk of the intermediate product.

In some embodiments, the processor may determine an oxidation-sensitive area of the intermediate product based on layout data of the flexible circuit board; determining residual distribution information of the intermediate product based on the oxidation sensitive area; and determining the oxidation risk of the intermediate product based on the residual distribution information.

Layout data refers to data that electronic components are arranged and configured on a flexible circuit board according to specific rules and requirements. For example, the layout data may include parameters such as the location, orientation, spacing, and connection of the electronic components on the flexible circuit board.

In some embodiments, the layout data may be represented by way of vectors as (a ₁,A₂,A₃, …), where a ₁,A₂,A₃ represents the position, orientation, spacing, and connection of the electronic component a, respectively.

In some embodiments, the processor may flex circuit board layout data in a variety of ways. For example, the processor may obtain layout data of the flexible circuit board through manual input, a memory device, etc.

Oxidation sensitive areas refer to areas of the intermediate product that are susceptible to oxidation. For example, the oxidation-sensitive region may include a region where gold fingers are densely distributed, a region where wires are densely distributed, and the like.

In some embodiments, the processor may determine the at least one oxidation-sensitive region of the intermediate product in a variety of ways based on layout data of the flexible circuit board. For example, the processor may generate a first search vector based on layout data of the flexible circuit board, search in the circuit board database based on the first search vector, determine a first reference vector that meets a matching condition, determine the first reference vector that meets the matching condition as a target vector, and determine an actual oxidation region corresponding to the target vector as an oxidation sensitive region.

The matching condition may refer to a judgment condition for determining the target vector. The matching condition may include that the similarity with the search vector is greater than a similarity threshold, that the similarity is maximum, and so on. There are various methods for calculating the similarity, such as euclidean distance, cosine distance, and the like.

The circuit board database is a database for storing, indexing, and querying vectors. The circuit database may store a plurality of first reference vectors and a historical oxidation sensitive region corresponding to each first reference vector.

In some embodiments, the circuit board database may be obtained based on historical data. For example, it may be constructed based on layout data of a large number of flexible circuit boards and user feedback data of the respective flexible circuit boards in various application scenarios. The user feedback data refers to information fed back by a user in the process of using the flexible circuit board or related products. For example, the user feedback data may include the actual oxidized area of the flexible circuit board. The application scenario may refer to an actual application scenario of the flexible circuit board. For example, the application scenario may include industrial control, energy management, communication devices, audio devices, toys, and the like.

In some embodiments, the processor may divide the flexible circuit board based on a grid, a preset area, a preset rule, or the like, to obtain a plurality of areas. In some embodiments, the processor may further divide the location of the golden finger and the location of the dense lines into an area.

In some embodiments, during the actual use of the flexible circuit board, the processor may direct the user to feed back by displaying text information on the display screen that asks the user about the oxidation-sensitive area, and/or by playing audio information on the oxidation-sensitive area that asks the user.

In some embodiments, the manner in which the user enters the user feedback data includes, but is not limited to, any combination of one or more of typewriting, handwriting, selection, voice, scan-in, and the like. Taking a selection input as an example, in some embodiments, the processor may control the user terminal to display an option of at least one region for selection by the user.

In some embodiments, the processor may count the number of times that each region of the flexible circuit board actually oxidizes during the historical use according to the user feedback data, and determine the region that the number of times satisfies the number of times condition as the oxidation sensitive region.

The number of times condition is a determination condition for evaluating the oxidation-sensitive area. For example, the count condition may include a count greater than a count threshold. The number of times threshold may be a system preset value, a system default value, or the like.

It should be noted that, the design of the flexible circuit board includes materials of different layers (e.g., copper foil layer, substrate layer, adhesive layer), and oxidation conditions of each material are different, and determining the area susceptible to oxidation by considering the design and the component layout of the flexible circuit board can be beneficial to identifying potential oxidation risks.

In some embodiments, the residual information may include residual distribution information. Residual distribution information refers to the distribution of contaminants on different locations/areas of the intermediate product. For example, the residual profile information may include residual amounts of contaminants at various locations. Residual amounts refer to the residual amount of contaminants. For example, the residual amount may be expressed by the area, size, etc. of the contaminant.

In some embodiments, the residual profile information may include the residual amount of contaminants in each oxidation-sensitive zone and the residual amount of contaminants in each other zone. For example, the residual distribution information may be expressed as (a 1, B2, c3, d4, e 5) by vectors, where a1 refers to the amount of the contaminant remaining in the oxidation-sensitive area a, B2 refers to the amount of the contaminant remaining in the oxidation-sensitive area B, and c3, d4, e5 respectively represent the residual amounts of the other respective areas.

In some embodiments, the processor may determine the residual profile information based on the oxidation sensitive region in a variety of ways. For example, the processor may obtain the residual amounts of the pollutants of the intermediate product at various positions based on the oxidation sensitive area through an image recognition algorithm, and determine the residual distribution information of the intermediate product. For more on the image recognition algorithm, see the relevant description of fig. 1.

In some embodiments, the processor may determine the oxidation risk of the intermediate product based on the residual distribution information of the intermediate product in a variety of ways. For example, the processor may establish a linear formula based on the residue distribution information of the intermediate product and the oxidation risk of the intermediate product; and (3) carrying out linear regression analysis based on a linear formula to determine the oxidation risk of the intermediate product.

Illustratively, the linear formula is formula (1):

y＝β₀+β₁x+ε；(1)；

Where y is the risk of oxidation, β ₁ is the residual distribution information, β ₀ is the intercept, β ₁ is the slope, ε is the error term.

In some embodiments, the processor may determine β ₀、β₁ in linear equation (1) by a violence fit; the error term is estimated based on the residual between the actual risk of oxidation and the risk of oxidation output by the linear equation.

Violence fitting refers to the process of trying all possible combinations of linear formula parameters, either through exhaustive or search-by-search, to find the best fit.

In some embodiments, the processor may also determine the parameters in linear equation (1) by an optimization algorithm (e.g., gradient descent or genetic algorithm) or a heuristic search method (e.g., bayesian optimization).

In some embodiments, the residual profile information is positively correlated with the risk of oxidation, and the residual amount of contaminants in the oxidation-sensitive area is greater, so that the risk of oxidation in that area is higher.

In some embodiments, the processor may determine the oxidation risk of the intermediate product by weighted summation based on the residual amounts of the respective regional contaminants and the corresponding weights. The weights may be related to the type of region. The type of region may include one of an oxidation-sensitive region, other region. The weight of the oxidation-sensitive area is greater than the weight of the other areas.

In some embodiments, the processor may determine the oxidation risk of the intermediate product via a risk assessment model based on the residual profile information, for more details, see the relevant description of fig. 3.

In some embodiments of the present disclosure, the accuracy of determining the risk of oxidation is facilitated by the residual amount of contaminants in the oxidation-sensitive area, and the residual amount of contaminants in each other area, which is beneficial to accurately monitoring the production process of the flexible circuit board and improving the quality of the produced product.

In step 230, a control instruction is generated in response to the oxidation risk meeting a first preset condition.

The first preset condition is a judgment condition for evaluating whether or not to adjust the production process of the flexible circuit board. For example, the first preset condition may include that the risk of oxidation is greater than an oxidation threshold. The oxidation threshold may be determined experimentally or empirically.

The control instructions are instructions for controlling the operation of one or more components in the flexible circuit board production monitoring system.

In some embodiments, the control instructions may refer to instructions for controlling the operation of a feature monitoring module, an environmental monitoring module, a bend detection module, and the like. In some embodiments, the control instructions may include one or more instructions. For example, a feature regulation instruction corresponding to the feature monitoring module, or the like; an environment regulation instruction corresponding to the environment monitoring module; and a bending detection instruction corresponding to the bending detection module. The characteristic regulation and control instruction is an instruction for controlling the temperature regulation and control element to heat or cool the intermediate product. The environment control instruction is an instruction for controlling the temperature control module or the humidity control module to adjust the temperature and the humidity in the space. The bending detection command is a command for controlling the moving rate, the force application amount, and the like of the bending vision unit.

For more on the feature monitoring module, the environment monitoring module, the bend detection module, reference may be made to the relevant description of fig. 1.

In some embodiments, the control instructions may be used to adjust the environmental data and/or the temperature data of the intermediate product.

In some embodiments, in response to the oxidation risk meeting a first preset condition, the processor obtains a difference in temperature data of the intermediate product and the ambient temperature, and determines a corresponding characteristic control command or environmental regulation command based on the difference. The processor may preset a correspondence between different differences and corresponding different feature control instructions or corresponding environment regulation instructions.

In some embodiments, the processor may send control instructions to the corresponding device (e.g., feature monitoring module, environmental monitoring module, etc.) to control the operation of the corresponding device. For example, the processor may send environmental regulation instructions to a temperature control module that controls the temperature control module to regulate (e.g., raise or lower) the ambient temperature/humidity within the production environment. For another example, the processor may send a characteristic control command to the temperature control element to control the temperature control element to adjust (e.g., raise or lower) the temperature of the intermediate product.

In some embodiments of the present disclosure, by analyzing the oxidation risk, determining the control command may minimize the difference between the temperature of the intermediate product and the ambient temperature, thereby reducing the oxidation risk of the intermediate product; through monitoring and controlling the production process of the flexible circuit board, the temperature of the environment temperature or the temperature of intermediate products is adjusted in real time, oxidation caused by temperature difference is avoided, the quality of the final flexible circuit board can be improved, and the production efficiency is improved.

It should be noted that the above description of the flow is only for the purpose of illustration and description, and does not limit the application scope of the present specification. Various modifications and changes to the flow may be made by those skilled in the art under the guidance of this specification. However, such modifications and variations are still within the scope of the present description.

FIG. 3 is an exemplary schematic diagram of a risk assessment model shown in accordance with some embodiments of the present description.

In some embodiments, as shown in fig. 3, the processor may determine the oxidation risk 350 through the risk assessment model 340 based on the residual profile information 310.

The risk assessment model is a model for determining the risk of oxidation of the intermediate product. In some embodiments, the risk assessment model may be a machine learning model. For example, the risk assessment model may be a machine learning model of the custom structure hereinafter. The risk assessment model may also be a machine learning model of other structures, such as any one or combination of various possible models, e.g., a recurrent neural network (Recurrent Neural Network, RNN) model, a deep neural network (Deep Neural Network, DNN) model, a convolutional neural network (Convolutional Neural Network, CNN) model, etc.

In some embodiments, the input of the risk assessment model may include residual distribution information and the output may include oxidation risk of the intermediate product.

In some embodiments, as shown in fig. 3, the input of the risk assessment model 340 may also include an estimated bending morphology 320, and bending characteristics 330 of the intermediate product.

The estimated bending form refers to the bending form of the product when the estimated flexible circuit board is actually applied in the future. In some embodiments, estimating the bend morphology may include estimating a bend curve. For more on the bending curve, see the relevant description of fig. 1.

In some embodiments, the processor may determine the predicted buckle morphology based on manual input. In some embodiments, the processor presets the corresponding relation between different products and different predicted bending forms, and determines the current predicted bending form by a table look-up method based on the actually applied products.

The bending characteristics are data reflecting the characteristics of the flexible circuit board in the bent state. For more on the bending feature, see the relevant description of fig. 4.

In some embodiments of the present disclosure, the flexible circuit board changes in shape after bending, so that the oxidation risk occurring in the bending shape is different from the oxidation risk in the normal shape, and the accuracy of the oxidation risk predicted by the model can be improved by inputting the predicted bending shape and the bending characteristics of the intermediate product as the risk assessment model.

In some embodiments, the risk assessment model may be trained in various possible ways based on a number of second training samples with second labels. For example, parameter updates may be performed based on a gradient descent method. An exemplary training process includes: inputting a plurality of second training samples with second labels into the initial risk assessment model, constructing a loss function through the second labels and the results of the initial risk assessment model, and iteratively updating parameters of the initial risk assessment model through gradient descent or other methods based on the loss function. And when the preset conditions are met, model training is completed, and a trained risk assessment model is obtained. The preset condition may be that the loss function converges, the number of iterations reaches a threshold value, etc.

In some embodiments, the second training sample may include a plurality of training samples, the training samples including at least sample residual distribution information. The second training sample may be obtained based on historical data.

In some embodiments, the second label may include an actual risk of oxidation of the flexible circuit board. The second tag may be obtained by a processor or by manual labeling. For example, the evaluation may be performed manually based on the production process of the flexible circuit board and determined as the second tag.

The risk of oxidation may be caused by a variety of factors, such as environmental conditions, production parameters, material properties, etc., and may also be affected by production lots, process variations, or other factors, and thus flexible circuit boards present different risks of oxidation in different production processes.

In some embodiments, when the input of the risk assessment model includes an estimated bend morphology, and a bend feature of the intermediate product, the second training sample may further include a sample estimated bend morphology, and a sample bend feature of the sample flexible circuit board.

In some embodiments of the present disclosure, a risk assessment model may be used to obtain a proper risk of oxidation efficiently and accurately, so as to improve accuracy of determining a control instruction, facilitate accuracy of controlling environmental data and/or temperature data of an intermediate product, and reduce possibility of oxidation of a flexible circuit board.

FIG. 4 is an exemplary schematic diagram illustrating determination of bending qualification of an intermediate product according to some embodiments of the present disclosure.

In some embodiments, the flexible circuit board production monitoring system further comprises a bending detection module configured to perform bending detection on the intermediate product based on preset detection parameters. For more description of the bend detection module, see fig. 1 for relevant content.

In some embodiments, as shown in fig. 4, the processor may obtain detection data 410 through a bend detection module; based on the detection data 410, obtaining bending characteristics 330 of the intermediate product; based on the buckle characteristics 330, a buckle eligibility 440 of the intermediate product is determined.

In the production process of the flexible circuit board, random sampling inspection is required for the intermediate product, the sampling inspection content can include bending detection and the like, and the reliability of the final flexible circuit board is improved by determining the bending qualification degree of the intermediate product.

The detection data refer to related data generated in the bending process of the intermediate product. For example, the detection data may include sound data, elasticity data, image data of a curved surface of the intermediate product, and the like. The sound data refer to sound generated by the intermediate product in the bending process, the elastic data refer to elastic force of the intermediate product in the bending process, and the image data of the bending surface of the intermediate product refer to images related to the bending form of the intermediate product in the bending process. The curved surface refers to the side surface of the intermediate product, the surface of which is deformed when the intermediate product is bent under the force. For example, the curved surface may be a side surface curved toward both sides.

In some embodiments, the detection data may be obtained by a bend detection module. For example, the processor may obtain sound data through a sound sensor configured by the bend detection module. For another example, the processor may obtain the elastic force data of the intermediate product at each position based on a plurality of elastic force sensors disposed on the bending force applying unit. For another example, the processor may obtain image data of a curved surface of the intermediate product based on a camera configured with the bend detection module. In some embodiments, the detection data may be uploaded to the memory module in real time after being collected by each sensor, and the processor may read the detection data from the memory module periodically or in real time. For more on the bending detection module, see the relevant description of fig. 1.

The bending characteristics are data reflecting the characteristics of the intermediate product during bending detection. In some embodiments, the kink feature may include kink sound data, a kink spring profile, and a cluster of kink-deformation curves.

The bending sound data is data reflecting characteristics of sound data during bending. For example, the bending sound data may include frequency and amplitude of sound, etc. In some embodiments, the bending sound data may comprise a sequence of sound data at different moments in time.

The bending elastic force distribution is data reflecting characteristics of elastic force data in the bending process. For example, the bending spring force distribution may be a distribution of spring forces from different regions at different times. In some embodiments, the distribution of bending spring force may be represented in various forms such as a sequence or matrix. For example, the distribution of bending elasticity may be represented by the sequence { A, B, C, … }, where the elements A, B, C in the sequence represent the distribution of elasticity in different regions at different times. In some embodiments, each element in the sequence may include a plurality of sub-elements, and the distribution of the elastic force of the area a may be represented as (A1, A2, … …), by way of example only, where A1 represents the elastic force of the area a at time A1, the elastic force of time A2, and so on.

The bending deformation curve cluster is a feature reflecting the characteristics of the image data of the curved surface in the bending process. For example, a buckling deformation curve cluster may include a collection of buckling curves formed at different times by the curved surface of the intermediate product during buckling.

In some embodiments, the processor may determine the buckle characteristics based on the detection data in a variety of ways. For example, the processor may count sound data at various times during the bending process to determine bending sound data. For another example, the processor may count the elastic force data of the intermediate product at each position and each time to determine the bending elastic force distribution. For another example, the processor may obtain image data of the intermediate product at each moment in the bending process, and obtain bending curves at each moment based on an image recognition algorithm, so as to form bending deformation curve clusters. For more on the image recognition algorithm, see the relevant description of fig. 1.

In some embodiments, the processor may obtain the bending characteristics through a visual detection module. For example, the bending detection module may send the image data of the bending surface of the intermediate product detected in real time to the visual detection module, and the image processing device of the visual detection module processes and analyzes the image data of the bending surface of the intermediate product to determine bending characteristics and send the bending characteristics to the processor.

The bending qualification degree is used for measuring whether the intermediate product meets preset specifications and requirements in the bending detection process. In some embodiments, the bend eligibility may be expressed as a numerical value (e.g., eligibility, qualification, etc.) or a grade (e.g., eligibility grade).

In some embodiments, the processor may determine the bend qualification in a variety of ways. For example, the processor may construct a second search vector according to the bending characteristics of the intermediate product under at least one set of preset detection parameters, and search in the bending database based on the second search vector in a manner similar to the determination of the oxidation-sensitive area in fig. 2, to determine the bending qualification of the intermediate product.

A warp database is a database used to store, index, and query vectors. The bending database can store a plurality of second reference vectors and bending qualification degree corresponding to each second reference vector.

In some embodiments, the buckle database may be constructed based on historical data. For example, the processor may determine, based on the historical data, a historical bend characteristic of the historical intermediate product under a plurality of sets of historical preset detection parameters as the second reference vector and an actual bend qualification of the historical intermediate product as the historical bend qualification. In some embodiments, the actual bend-qualification of the historical intermediate product may be determined based on manual input.

In some embodiments, as shown in fig. 4, the processor may predict a bend qualification rate 440 of the intermediate product based on the bend characteristics 330 of the intermediate product via a qualification model 430.

The qualification model is a model for obtaining the bending qualification of the intermediate product. In some embodiments, the eligibility model may be a machine learning model. For example, neural network NN (Neural Networks, NN), convolutional neural network CNN (Convolutional Neural Networks, CNN), or the like, or any combination thereof.

In some embodiments, as shown in FIG. 4, the input of the eligibility model 430 may include bending characteristics 330 of the intermediate product under a plurality of preset inspection parameters, and the output may include bending eligibility 440 of the intermediate product.

In some embodiments, as shown in FIG. 4, the input to the eligibility model 430 may also include a distribution of bend spacing 430. In some embodiments, the bend interval distribution may include a time interval of two adjacent bend detections.

The bending interval distribution refers to the distribution condition of the time interval of two adjacent bending detection. For example, the bend interval distribution may be represented by a vector (t 1, t2, …), where t1 represents the time interval between the first bend test and the second bend test, t2 represents the time interval between the second bend test and the third bend test, etc.

In some embodiments, the bend spacing profile may be obtained based on a bend detection module. For example, the processing may obtain an equipment log of the bending detection module, determine the time of each bending detection performed by the bending detection module, and sequentially calculate the time intervals of two adjacent bending detections, to obtain the bending interval distribution. The equipment log is used for recording the running condition of the bending detection module.

In some embodiments, the processor may train the initial eligibility model to obtain the eligibility model by a gradient descent method or the like based on a plurality of third training samples and third labels thereof. The training process of the qualification model is similar to that of the risk assessment model, and for more details see the relevant description of FIG. 3.

In some embodiments, the third training sample may include a sample buckling feature of the sample intermediate product at a plurality of sample preset detection parameters. The third label corresponding to the third training sample may be an actual value of the bending qualification of the sample intermediate. In some embodiments, a third training sample may be obtained based on historical data, and a third label may be determined by the artificial annotation.

In some embodiments, when the input of the qualification model includes a buckle interval distribution, the third training sample may also include a sample buckle interval distribution.

In some embodiments of the present disclosure, the bending interval distribution is used as a parameter of the qualification model, so that whether the intermediate product meets the quality requirement can be more accurately determined, and in frequent bending detection, if the intermediate product always maintains higher bending qualification, the reliability of the final flexible circuit board can be determined.

In some embodiments of the present disclosure, the bending qualification degree is obtained through a qualification degree model, which can further help workers in the field to obtain the bending qualification degree more quickly and accurately, so as to ensure that the final flexible circuit board has good bending performance.

In some embodiments of the specification, the bending characteristics of the intermediate product are obtained through detecting data, the bending qualification degree of the intermediate product is determined, the bending performance of the intermediate product to be detected can be accurately analyzed, workers are helped to grasp the bending performance of the intermediate product more accurately and more efficiently through a reasonable quantification mode, the reliability of the final flexible circuit board is improved, and the product can better meet the demands of users.

In some embodiments, the process 500 may be implemented based on a processor of a flexible circuit board production monitoring system. As shown in fig. 5, the process 500 includes the steps of:

Step 510, determining a weight reference value based on the component data of the flexible circuit board.

The component data refers to information of respective constituent parts (e.g., materials, components, etc.) of the flexible circuit board. The component data is used to provide detailed information about the internal and external configuration of the flexible circuit board. For example, the component data may include density, volume, etc. of the individual components of the individual intermediate products of the flexible circuit board.

In some embodiments, the component data of the flexible circuit board includes component data of each intermediate product.

In some embodiments, the processor may obtain the component data in a variety of ways. For example, the processor may obtain component data for the flexible circuit board based on a production schedule. For another example, the processor may obtain the component data through the memory module. For another example, the processor may obtain the component data of each flexible circuit board through an image recognition algorithm through at least one set of image information corresponding to each production process. For more on the image recognition algorithm, see the relevant description of fig. 1.

The weight reference value is a reference value set in advance for comparing and evaluating the weight of each intermediate product. The weight reference value can be used for judging whether the weight of the intermediate product is in a reasonable range. In some embodiments, the weight reference value may include a weight reference value of an intermediate product of each production process.

In some embodiments, the intermediate products of different production processes correspond to different weight reference values.

In some embodiments, the processor may obtain the density, volume of the various components of the intermediate product based on the component data of the flexible circuit board; the mass of each component is obtained based on the product of the density of each component and the corresponding volume, and the corresponding weight reference value of the intermediate product is determined based on the sum of the masses of each component.

And step 520, generating first early warning information and sending the first early warning information to the user terminal in response to the deviation between the weight data of the intermediate product and the corresponding weight reference value meeting a second preset condition.

The deviation refers to the difference between the weight data of the intermediate product and the weight reference value of the same production process. In some embodiments, the processor may determine a deviation of the weight data of the intermediate product from the corresponding weight reference value based on a difference of the weight data of the intermediate product from the corresponding weight reference value. For more on weight data, see the relevant description of fig. 2.

The second preset condition is a judgment condition for evaluating whether the first warning information is generated. For example, the second preset condition may include that an absolute value of the deviation is greater than a deviation threshold.

The deviation threshold is a value for measuring whether a difference between the weight data of the intermediate product and the corresponding weight reference value is within a preset range. In some embodiments, the deviation threshold includes a first threshold and a second threshold, and accordingly, the weight data of the intermediate product is greater than the corresponding weight reference value, and the second preset condition may include the deviation being greater than or equal to the first threshold; the weight data of the intermediate product is smaller than the corresponding weight reference value, and the second preset condition may include a deviation being smaller than or equal to a second threshold value.

The first threshold value is a maximum threshold value condition of deviation of the weight data of the intermediate product from the corresponding weight reference value, and is used for representing an upper limit value of a part of the weight data of the intermediate product exceeding the weight reference value. In some embodiments, the first threshold is a value greater than zero.

The second threshold value is a minimum threshold value condition for a deviation of the weight data of the intermediate product from the corresponding weight reference value, and is used to represent a lower limit value of a portion of the weight data of the intermediate product below the weight reference value. When the weight data is smaller than the weight reference value, the actual weight of the intermediate product may be reduced due to insufficient thickness of the silver paste or the conductive paste or peeling off, etc. In some embodiments, the second threshold is a value less than zero.

In some embodiments, the processor may determine the first threshold, the second threshold in a variety of ways. For example, the processor may obtain the first threshold value, the second threshold value based on experimental data. For example, the first threshold value may be determined by experimentally simulating a situation that may cause an increase in the weight of the intermediate product or a situation that may cause a decrease in the weight of the intermediate product, based on manually measuring the increase in the weight of the intermediate product in each case or the decrease in each case. For another example, the processor may obtain a historical increase or decrease in weight of the intermediate product based on the historical data, determine a first threshold based on an average of the respective historical increases, or determine a second threshold based on an average of the respective historical decreases.

In some embodiments, the processor may determine the deviation threshold based on at least one of oxidation risk, historical deviation results, residual distribution information.

For more on oxidation risk, residual distribution information, see the relevant description of fig. 2.

The history deviation result refers to the deviation of the intermediate product of the previous production process in the production process. The preliminary production process means that each production process has been completed before.

Different processes/production processes have different intermediate products, and for a certain flexible circuit board, the weight deviation result of the previous production process in the production process may be accumulated into the deviation of the production process which is not yet executed in the next step.

In some embodiments, the processor may count various deviations from the previous manufacturing process and determine a historical deviation result.

In some embodiments, the processor may determine the deviation threshold in a variety of ways. For example, oxidation may result in an increase in weight of the intermediate product, the deviation becoming larger, the first threshold may be positively correlated to the risk of oxidation, the greater the first threshold.

Since the production process of the flexible circuit board is continuous, the weight deviation of the previous production process may accumulate in the subsequent production process, and thus if there is a larger weight deviation in the previous production process, the next production process may be significantly affected, and the deviation threshold of the production process needs to be increased (for example, the first threshold is increased and the second threshold is decreased) so as to avoid the influence of the production process on the next production process. In some embodiments, the processor may determine a target production process in the production flow, adjust a deviation threshold of the target production process by an adjustment amount. The adjustment amount may be determined empirically or experimentally.

The target production process is a production process having a large weight deviation in the previous production process. The target production process may be determined by manual input, or based on a priori knowledge, a historical database. For example, the target production process may be copper deposition, etching, or the like.

In some embodiments, the processor may determine the deviation threshold by querying a preset relationship table based on the oxidation risk, the historical deviation result, the residual distribution information. The preset relation table stores the corresponding relations of different oxidation risks, historical deviation results, residual distribution information and different deviation thresholds.

In some embodiments, the processor may construct a preset relationship table based on the historical data. For example, the processor may be constructed based on the relevant data of the qualified circuit board in the history data. The related data includes oxidation risk, historical deviation result, residual distribution information and corresponding deviation threshold.

The qualified circuit board refers to that the bending detection qualification degree of the flexible circuit board is larger than a qualification threshold value, the actual use time after the flexible circuit board is put into actual use is longer than a time threshold value, and no abnormality occurs. The qualification threshold, time threshold, may be a value determined based on experimentation or experience.

In some embodiments of the present disclosure, it may be determined whether data in a production or measurement process is within an acceptable range by setting a threshold, and by determining a deviation threshold by considering a plurality of factors, a threshold that meets an actual situation may be obtained, and it may be avoided that a threshold set only depending on a single factor may cause misunderstanding or misjudgment, and meanwhile, a large number of unqualified products are avoided, thereby improving quality stability of the products.

The first early warning information is used for reminding a user of a message related to abnormality of the intermediate product. Anomalies may include weight data anomalies (e.g., overweight) for intermediate products, and the like.

In some embodiments, the first early warning information may include a cause of the abnormality and specific information of the abnormality. The cause of the abnormality includes one of an excessively large deviation of the weight data of the intermediate product from the corresponding weight reference value and an excessively small deviation of the weight data of the intermediate product from the corresponding weight reference value. Specific information of the abnormality may include a numerical value of deviation, weight data, weight reference value, and the like.

In some embodiments, in response to the deviation between the weight data of the intermediate product and the corresponding weight reference value meeting the second preset condition, the processor may generate first early warning information and send the first early warning information to the user terminal, where the first early warning information may be prompted by displaying a popup window, instant information, playing voice, or other manners on the user terminal. For example, the first warning information may be "the weight deviation of the intermediate product has reached a threshold value".

And step 530, generating a fine acquisition instruction and sending the fine acquisition instruction to the visual detection module.

The fine acquisition instructions are instructions for controlling the vision inspection module to acquire higher resolution, higher quality images.

In some embodiments, the processor obtains images of various production processes in the production flow through the visual detection module. An image may comprise a series of frames. The frame rate of the image (also referred to as the number of frames captured per second) may be, for example, 20, 25, 40, etc. Each frame in the series of frames may include an intermediate product in a respective production process.

In some embodiments, a series of frames may be acquired by more than one camera. For example, the first camera device may be configured to acquire a low resolution video (or a low resolution frame of an image) for analysis of residual information of contaminants of the intermediate product. The second image pickup device may be configured to acquire one or more high resolution images for identifying information of the weight abnormality region.

The fine image information is an image capable of clearly and accurately reflecting details and features of a subject. For example, the fine image information may include one or more high resolution images.

In some embodiments, the processor may be connected to the visual detection module in a wired/wireless manner, so as to implement communication with the visual detection module, and in response to the deviation between the weight data of the intermediate product and the corresponding weight reference value meeting a second preset condition, the processor may generate a fine acquisition instruction, control the second image capturing device of the visual detection module to work, and acquire a high resolution image of the intermediate product.

Step 540, determining a weight anomaly area of the intermediate product based on the fine image information.

By weight anomaly area is meant an area of the intermediate product where there is a significant difference in weight relative to the surrounding area or the expected weight.

In some embodiments, the processor may determine the weight anomaly region of the intermediate product in a variety of ways. For example, the processor may perform statistical analysis on each color value in the fine image information based on existing image processing software (e.g., openCV) to obtain color distribution information; and comparing the color distribution information with preset color distribution information to obtain a region with abnormal color as a weight abnormal region. Wherein the color distribution information is used for representing the number of times each color value appears in the fine image information. The color value may be a color value of each pixel point in the fine image information in a certain color mode. Color modes include, but are not limited to, RGB mode, CMYK mode. For example, red corresponds to (255, 0) in the RGB color mode, and (C0, M100, Y100, K10) in the CMYK color mode. Wherein, different intermediate products correspond to different preset color distribution information. In some embodiments, the preset color distribution information may also be a system preset value, a system default value, etc., or the preset color distribution information may also be preset by a professional or determined from a large amount of historical data.

The abnormal color is used to characterize the color of the weight abnormal region. The region in which the abnormal color exists is a region constituted by pixel points of the abnormal color. For example, the color of the weight anomaly area may appear as a gradient, flashing, or other changing area.

And step 550, generating second early warning information based on the weight abnormality region and sending the second early warning information to the user terminal.

The second early warning information is used for reminding a user of a message related to the weight abnormality area of the intermediate product. When the weight abnormality exists in the area of the intermediate product, the processor can generate second early warning information to remind the user of local problems about the intermediate product so as to take appropriate measures in time for adjustment or repair.

In some embodiments, the second pre-warning information may include location information of the weight anomaly region. The position information may be represented by coordinates of the region in the fine image information, a region number, or the like.

In some embodiments, the processor may generate second early warning information based on the weight anomaly region and send the second early warning information to the user terminal, where the second early warning information may be prompted by displaying a pop-up window, instant message, or playing voice on the user terminal.

In some embodiments of the present disclosure, by monitoring the weight of the intermediate product in real time and finding areas of weight anomalies in time, quality problems with the product are facilitated and found, weight anomalies may be caused by errors, material defects, or other problems in the manufacturing process, and by pre-warning information, these problems can be facilitated and corrected in time, thereby ensuring the quality of the final flexible circuit board.

There is also provided in one or more embodiments of the present specification a flexible circuit board production monitoring apparatus including processing means for performing a flexible circuit board production monitoring method as described in any one of the embodiments above.

There is further provided in one or more embodiments of the present specification a computer readable storage medium storing computer instructions that, when read by a computer in the storage medium, the computer performs a flexible circuit board production monitoring method as described in any of the embodiments above.

While the basic concepts have been described above, it will be apparent to those skilled in the art that the foregoing detailed disclosure is by way of example only and is not intended to be limiting. Although not explicitly described herein, various modifications, improvements, and adaptations to the present disclosure may occur to one skilled in the art. Such modifications, improvements, and modifications are intended to be suggested within this specification, and therefore, such modifications, improvements, and modifications are intended to be included within the spirit and scope of the exemplary embodiments of the present invention.

Meanwhile, the specification uses specific words to describe the embodiments of the specification. Reference to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the present description. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the present description may be combined as suitable.

Furthermore, the order in which the elements and sequences are processed, the use of numerical letters, or other designations in the description are not intended to limit the order in which the processes and methods of the description are performed unless explicitly recited in the claims. While certain presently useful inventive embodiments have been discussed in the foregoing disclosure, by way of various examples, it is to be understood that such details are merely illustrative and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements included within the spirit and scope of the embodiments of the present disclosure. For example, while the system components described above may be implemented by hardware devices, they may also be implemented solely by software solutions, such as installing the described system on an existing server or mobile device.

Likewise, it should be noted that in order to simplify the presentation disclosed in this specification and thereby aid in understanding one or more inventive embodiments, various features are sometimes grouped together in a single embodiment, figure, or description thereof. This method of disclosure does not imply that the subject matter of the present description requires more features than are set forth in the claims. Indeed, less than all of the features of a single embodiment disclosed above.

In some embodiments, numbers describing the components, number of attributes are used, it being understood that such numbers being used in the description of embodiments are modified in some examples by the modifier "about," approximately, "or" substantially. Unless otherwise indicated, "about," "approximately," or "substantially" indicate that the number allows for a 20% variation. Accordingly, in some embodiments, numerical parameters set forth in the specification and claims are approximations that may vary depending upon the desired properties sought to be obtained by the individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and employ a method for preserving the general number of digits. Although the numerical ranges and parameters set forth herein are approximations that may be employed in some embodiments to confirm the breadth of the range, in particular embodiments, the setting of such numerical values is as precise as possible.

Each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., referred to in this specification is incorporated herein by reference in its entirety. Except for application history documents that are inconsistent or conflicting with the content of this specification, documents that are currently or later attached to this specification in which the broadest scope of the claims to this specification is limited are also. It is noted that, if the description, definition, and/or use of a term in an attached material in this specification does not conform to or conflict with what is described in this specification, the description, definition, and/or use of the term in this specification controls.

Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments of this specification. Other variations are possible within the scope of this description. Thus, by way of example, and not limitation, alternative configurations of embodiments of the present specification may be considered as consistent with the teachings of the present specification. Accordingly, the embodiments of the present specification are not limited to only the embodiments explicitly described and depicted in the present specification.

Claims

1. A flexible circuit board production monitoring system, the system comprising: the system comprises a visual detection module, a characteristic monitoring module, an environment monitoring module and a processor;

the visual detection module is configured to acquire image information of at least one layer of a copper foil layer, a substrate layer and an adhesive layer of the flexible circuit board;

the feature monitoring module comprises at least one of a weight sensor and a temperature sensor, and is configured to monitor physical and chemical features of an intermediate product of the flexible circuit board, wherein the physical and chemical features comprise at least one of temperature data and weight data of the intermediate product;

the environment monitoring module is configured to monitor environment data of the flexible circuit board;

the processor is configured to:

Determining residual information of the contaminant based on the image information;

determining a risk of oxidation of the intermediate product based on at least one of the environmental data, the physicochemical characteristics of the intermediate product, and the residual information of the contaminant;

and generating a control instruction in response to the oxidation risk meeting a first preset condition, wherein the control instruction is used for adjusting the environmental data and/or the temperature data of the intermediate product.

2. The system of claim 1, wherein the residual information comprises residual distribution information, the processor further configured to:

Determining an oxidation sensitive area of the intermediate product based on layout data of the flexible circuit board;

determining residual distribution information of the intermediate product based on the oxidation sensitive area;

And determining the oxidation risk of the intermediate product based on the residual distribution information.

3. The system of claim 2, wherein the processor is further configured to:

and determining the oxidation risk through a risk assessment model based on the residual distribution information, wherein the risk assessment model is a machine learning model.

4. The system of claim 1, further comprising a bend detection module configured to perform bend detection on the flexible circuit board based on preset detection parameters to obtain detection data, the processor further configured to:

Based on the detection data, obtaining bending characteristics of the intermediate product;

and determining the bending qualification degree of the intermediate product based on the bending characteristics.

5. The system of claim 1, wherein the processor is further configured to:

determining a weight reference value based on the component data of the flexible circuit board;

Responding to the deviation between the weight data of the intermediate product and the corresponding weight reference value to meet a second preset condition, generating first early warning information and sending the first early warning information to a user terminal;

Generating a fine acquisition instruction and sending the fine acquisition instruction to the visual detection module, wherein the fine acquisition instruction is used for controlling the visual detection module to acquire fine image information;

determining a weight abnormality region of the intermediate product based on the fine image information;

and generating second early warning information based on the weight abnormal region and sending the second early warning information to the user terminal.

6. A flexible circuit board production monitoring method, wherein the method is implemented by a processor of a flexible circuit board production monitoring system, the method comprising:

Determining an oxidation risk of the intermediate product based on the environmental data, a materialized characteristic of the intermediate product, and residual information of the contaminant, the materialized characteristic including at least one of temperature data, weight data of the intermediate product;

7. The method of claim 6, wherein determining a risk of oxidation of an intermediate product based on at least one of environmental data, physicochemical characteristics of the intermediate product, and residual information of the contaminant comprises:

Determining the residual distribution information based on the oxidation sensitive area;

and determining the oxidation risk based on the residual distribution information.

8. The method of claim 1, wherein the method further comprises:

9. A flexible circuit board production monitoring device, the device comprising at least one processor and at least one memory;

the at least one memory is configured to store computer instructions;

The at least one processor is configured to execute at least some of the computer instructions to implement the method of any one of claims 6-8.

10. A computer readable storage medium storing computer instructions which, when read by a computer in the storage medium, perform the method of any one of claims 6 to 8.