Full-process cooperative control method for electronic component production line

Abstract

The invention discloses an electronic component production line full-process cooperative control method, and relates to the technical field of production line control, and the method comprises the steps: carrying out the data cleaning of collected data, and carrying out the formatting and standardization preprocessing of the data; integrating and fusing the data of each device; based on audience demands of the components, intelligent manufacturing service of a customized production line is provided; establishing an equipment fault prediction model, and predicting a future fault trend and a possible occurrence time point of the equipment; and establishing a component performance prediction model, predicting future performance and market competitiveness of the component, and optimizing the intelligent manufacturing service based on the market competitiveness. The intelligent manufacturing service of the customized production line is provided, the future performance and market competitiveness of the components are predicted, the intelligent manufacturing service is optimized, the production parameters of the components are controlled according to market feedback, and therefore it can be guaranteed that the produced components have good market benefits.

Description

Technical Field

[0001] This invention relates to the field of production line control technology, specifically to a method for collaborative control of the entire process of an electronic component production line. Background Technology

[0002] Electronic components are a general term for electronic elements and devices that constitute the basic functional units of electronic circuits or equipment. They include resistors, capacitors, inductors, diodes, transistors, integrated circuits, etc. Based on function, they can be divided into passive components and active components. Integrated circuits, which achieve complex functions through semiconductor technology, are considered the core components of modern electronic technology.

[0003] With the development of the global economy and the intensification of market competition, manufacturing enterprises are facing increasing challenges. Customers' demands for personalized components are constantly increasing, component lifecycles are shortening, and quality requirements are rising. At the same time, enterprises also need to cope with issues such as fluctuating raw material prices and rising labor costs. To survive and thrive in this environment, manufacturing enterprises must seek innovative technologies and methods to improve production efficiency, optimize supply chain management, enhance component quality, and strengthen innovation capabilities. Summary of the Invention

[0004] To address the aforementioned technical problems, a collaborative control method for the entire process of electronic component production lines is provided. This technical solution resolves the issues raised in the background section.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows: A method for collaborative control of the entire process of an electronic component production line, comprising: Through Internet of Things (IoT) technology, production data, equipment status, and process information on electronic component production lines can be collected in real time. The collected data is cleaned to remove invalid and redundant data, and the data is preprocessed by formatting and standardization. The data from various devices are integrated and fused to obtain a smart manufacturing dataset, and a comprehensive data view is drawn. Based on the needs of the component market, we provide customized intelligent manufacturing services for production lines. Deeply analyze the intelligent manufacturing dataset to identify the operating status and potential faults of the equipment. Through machine learning algorithms, establish an equipment fault prediction model to predict the future fault trends and possible timing of equipment failures. By using machine learning algorithms, a component performance prediction model is established to predict the future performance and market competitiveness of components. Based on market competitiveness, intelligent manufacturing services are optimized. Establish a data sharing mechanism among nodes in the supply chain, and realize information sharing and collaborative operation among nodes in the supply chain through the collaborative function of the cloud computing platform, wherein the supply chain provides raw materials for the production line; The technical architecture required for building intelligent manufacturing services is constructed on a cloud computing platform, and the production line control platform is configured and debugged based on the service solution.

[0006] Preferably, the step of data cleaning, removing invalid and redundant data, and formatting and standardizing the data preprocessing specifically includes: Use data processing tools on the cloud computing platform to traverse the collected data, identify and remove data that does not conform to business logic; For purely numerical data, the Euclidean distance formula is used to calculate the numerical similarity between the collected data points; For multi-feature data, the data is converted into feature vectors, and the feature similarity between each collected data point is calculated using the cosine similarity formula. Determine whether the similarity between each collected data point is higher than the preset similarity threshold. If so, mark the group of data points as redundant data and delete the group of data points until only one data point remains. If not, do not output anything. Based on business needs and data characteristics, data format specifications are formulated, including date format, numeric format, and string format; Using data processing tools on cloud computing platforms, the collected data is preprocessed in a formatted manner based on data format specifications; Based on the distribution characteristics of the data and business needs, the collected data is standardized and preprocessed to convert the data into dimensionless numerical values. The Euclidean distance formula is as follows: , In the formula, Let be the numerical similarity between the i-th collected data point and the j-th collected data point. , Let be the values ​​of the i-th collected data point and the j-th collected data point, respectively. , These are the data collection times for the i-th and j-th data points, respectively. The cosine similarity formula is: , In the formula, For the first The collected data points and the first Feature similarity between the collected data points For the first The collected data points are converted into feature vectors. For the first The collected data points are converted into feature vectors.

[0007] Preferably, the process of integrating and fusing data from various devices to obtain a smart manufacturing dataset and drawing a comprehensive data view specifically includes: Data integration combines data from various devices with different sources into a unified dataset for storage. Based on data integration, further processing and analysis are performed on the data to extract features, patterns, and trends from the raw data; By utilizing visualization tools and technologies, the operational status of intelligent manufacturing systems can be monitored in real time by creating comprehensive data views.

[0008] Preferably, the intelligent manufacturing service that provides customized production lines based on the needs of the component audience specifically includes: Based on the needs of the audience, obtain the lower limit values ​​of the component's index parameters, and set the parameters of at least one piece of equipment in the electronic component production line so that the actual value of the index parameters of the component produced by at least one piece of equipment is greater than the lower limit value of the component's index parameters.

[0009] Preferably, the step of performing in-depth analysis of the intelligent manufacturing dataset to identify the operating status and potential faults of the equipment, and establishing an equipment fault prediction model through machine learning algorithms to predict future fault trends and possible time points, specifically includes: Define maintenance objectives and identify the equipment that needs to be monitored; Obtain the type, function, operating environment, and potential failure modes of the equipment to be monitored; When training the model, the collected historical fault data is used as the training set, and the performance of the equipment fault prediction model is improved by adjusting the model parameters and optimizing the algorithm. Based on historical data and current status, machine learning algorithms are used to predict the likelihood and timing of future failures. Based on the prediction results, a maintenance plan is developed, which includes maintenance time, maintenance content, and spare parts required for maintenance. By comparing data before and after maintenance, the effectiveness of maintenance actions can be analyzed, and potential areas for improvement can be identified. Based on equipment operation and maintenance experience, adjust and optimize the equipment failure prediction model.

[0010] Preferably, the step of establishing a component performance prediction model using machine learning algorithms to predict the future performance and market competitiveness of the components specifically includes: The entire lifecycle data of component design, production and sales is obtained from the smart manufacturing dataset, including user feedback, quality inspection reports and market trends; The dataset is divided into a training set, a validation set, and a test set; The component performance prediction model is trained using the training set, the parameters of the component performance prediction model are adjusted and optimized using the validation set, and the capability of the component performance prediction model is evaluated using the test set. The average value of the indicator parameters of at least one component in the market is taken to obtain the reference value of the indicator parameters. The actual values ​​of the index parameters of the electronic components produced by the electronic component production line are input into the component performance prediction model to obtain the first performance parameter of the component. The first performance parameter is used as the performance indicator. The reference value of the index parameter is input into the component performance prediction model to obtain the second performance parameter of the component. The proportion of electronic components produced by electronic component production lines to the total number of electronic components in the market is used as the characteristic proportion. If the first performance parameter is greater than the second performance parameter, then the number of audiences whose performance requirements for components are lower than the second performance parameter is taken as the first value, and the number of audiences whose performance requirements for components are between the first performance parameter and the second performance parameter is taken as the second value. The first value is multiplied by the feature ratio and then added to the second value to obtain the first occupancy value. The first value and the second value are added to obtain the first comprehensive value. The first occupancy value is divided by the first comprehensive value to obtain the audience ratio. Otherwise, the number of audiences whose performance requirements for components are lower than the first performance parameter is taken as the third value, and the number of audiences whose performance requirements for components are between the first and second performance parameters is taken as the second value. The third value is multiplied by the feature ratio to obtain the second occupancy value. The third value and the second value are added together to obtain the second comprehensive value. The second occupancy value is divided by the second comprehensive value to obtain the audience ratio. The proportion of the target audience is used as a measure of the market competitiveness of the components produced by the electronic component production line.

[0011] Preferably, the optimization of intelligent manufacturing services based on market competitiveness specifically includes: If the audience share is lower than the target value, the parameters of at least one piece of equipment in the electronic component production line will be upgraded by a preset value, which is based on experience. After each upgrade, the audience share will be recalculated. When the audience share exceeds the target value for the first time, the current parameter settings of the equipment will be used as the optimization result for the smart manufacturing service. The target value is the market share target value of the component manufacturer.

[0012] Preferably, the establishment of a data sharing mechanism among nodes in the supply chain, and the realization of information sharing and collaborative operations among nodes in the supply chain through the collaborative functions of the cloud computing platform, specifically includes: Clearly define the goals and scope of sharing; A data exchange protocol is established, which includes data format, data encoding rules, and transmission protocol; By signing data sharing agreements, the responsibilities and obligations of data sharing are clarified, a data sharing supervision mechanism is established, and a trust mechanism is built. Establish cross-functional teams to enable collaborative operations among all nodes in the supply chain; Enterprises can optimize their supply chain processes by leveraging the collaborative capabilities of cloud computing platforms.

[0013] Compared with the prior art, the beneficial effects of the present invention are as follows: By providing customized intelligent manufacturing services for production lines, establishing equipment failure prediction models, predicting the future performance and market competitiveness of components, and optimizing intelligent manufacturing services, the system can predict market feedback based on the performance predictions of components on the production line. This allows for the control of component production parameters based on market feedback, thereby ensuring that the produced components have good market benefits. Attached Figure Description

[0014] Figure 1 This is a flowchart of the electronic component production line collaborative control method of the present invention; Figure 2 This is a flowchart of the preprocessing method for cleaning, formatting, and standardizing collected data according to the present invention. Figure 3 This is a flowchart of the method for integrating and fusing data from various devices according to the present invention; Figure 4 This is a flowchart of the method for predicting future failure trends and possible timing points of a device according to the present invention. Figure 5 This is a flowchart of the method for predicting the future performance and market competitiveness of components according to the present invention. Figure 6 This is a diagram illustrating the data sharing mechanism among various nodes in the supply chain as described in this invention. Detailed Implementation

[0015] The following description is intended to disclose the invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art.

[0016] Reference Figure 1 As shown, a collaborative control method for the entire process of an electronic component production line includes: Through Internet of Things (IoT) technology, production data, equipment status, and process information on electronic component production lines can be collected in real time. The collected data is cleaned to remove invalid and redundant data, and the data is preprocessed by formatting and standardization. The data from various devices are integrated and fused to obtain a smart manufacturing dataset, and a comprehensive data view is drawn. Based on the needs of the component market, we provide customized intelligent manufacturing services for production lines. Deeply analyze the intelligent manufacturing dataset to identify the operating status and potential faults of the equipment. Through machine learning algorithms, establish an equipment fault prediction model to predict the future fault trends and possible timing of equipment failures. By using machine learning algorithms, a component performance prediction model is established to predict the future performance and market competitiveness of components. Based on market competitiveness, intelligent manufacturing services are optimized. Establish a data sharing mechanism among nodes in the supply chain, and realize information sharing and collaborative operation among nodes in the supply chain through the collaborative function of the cloud computing platform, wherein the supply chain provides raw materials for the production line; The technical architecture required for building intelligent manufacturing services is constructed on a cloud computing platform, and the production line control platform is configured and debugged based on the service solution.

[0017] Reference Figure 2 As shown, the collected data undergoes data cleaning to remove invalid and redundant data, and the data is preprocessed by formatting and standardizing. Specifically, this includes: Use data processing tools on the cloud computing platform to traverse the collected data, identify and remove data that does not conform to business logic; For purely numerical data, the Euclidean distance formula is used to calculate the numerical similarity between the collected data points; For multi-feature data, the data is converted into feature vectors, and the feature similarity between each collected data point is calculated using the cosine similarity formula. Determine whether the similarity between each collected data point is higher than the preset similarity threshold. If so, mark the group of data points as redundant data and delete the group of data points until only one data point remains. If not, do not output anything. Based on business needs and data characteristics, data format specifications are formulated, including date format, numeric format, and string format; Using data processing tools on cloud computing platforms, the collected data is preprocessed in a formatted manner based on data format specifications; Based on the distribution characteristics of the data and business needs, the collected data is standardized and preprocessed to convert the data into dimensionless numerical values. The Euclidean distance formula is as follows: , In the formula, Let be the numerical similarity between the i-th collected data point and the j-th collected data point. , Let be the values ​​of the i-th collected data point and the j-th collected data point, respectively. , These are the data collection times for the i-th and j-th data points, respectively. The cosine similarity formula is: , In the formula, For the first The collected data points and the first Feature similarity between the collected data points For the first The collected data points are converted into feature vectors. For the first The collected data points are converted into feature vectors.

[0018] The data is converted into feature vectors, which are a set of values ​​representing data points. Each value corresponds to a feature. Redundant data points are removed until only one data point remains in each set of similar data points to ensure the uniqueness and validity of the data. Statistical analysis is performed on the collected data to understand its distribution characteristics, including the maximum, minimum, average, and standard deviation of the data. The data is then converted into a standard normal distribution, i.e., the mean is 0 and the standard deviation is 1.

[0019] Reference Figure 3 As shown, the data from various devices are integrated and fused to obtain a smart manufacturing dataset, and a comprehensive data view is drawn, specifically including: Data integration combines data from various devices with different sources into a unified dataset for storage. Based on data integration, further processing and analysis are performed on the data to extract features, patterns, and trends from the raw data; By utilizing visualization tools and technologies, the operational status of intelligent manufacturing systems can be monitored in real time by creating comprehensive data views.

[0020] Data is collected from various IoT devices, which is usually done through the application programming interfaces (APIs) provided by the devices. The APIs allow access to and retrieval of the data generated by the devices. Visualization tools are used to present the processed and analyzed data in the form of charts, reports or dashboards. The data view should include key indicators of the smart manufacturing system, real-time data, historical data and early warning information.

[0021] Based on the needs of the component users, providing customized smart manufacturing services for production lines specifically includes: Based on the needs of the audience, obtain the lower limit values ​​of the component's index parameters, and set the parameters of at least one piece of equipment in the electronic component production line so that the actual value of the index parameters of the component produced by at least one piece of equipment is greater than the lower limit value of the component's index parameters.

[0022] Reference Figure 4 As shown, a deep analysis of the intelligent manufacturing dataset is performed to identify the operating status and potential faults of the equipment. Through machine learning algorithms, a fault prediction model is established to predict future fault trends and possible time points. Specifically, this includes: Define maintenance objectives and identify the equipment that needs to be monitored; Obtain the type, function, operating environment, and potential failure modes of the equipment to be monitored; When training the model, the collected historical fault data is used as the training set, and the performance of the equipment fault prediction model is improved by adjusting the model parameters and optimizing the algorithm. Based on historical data and current status, machine learning algorithms are used to predict the likelihood and timing of future failures. Based on the prediction results, a maintenance plan is developed, which includes maintenance time, maintenance content, and spare parts required for maintenance. By comparing data before and after maintenance, the effectiveness of maintenance actions can be analyzed, and potential areas for improvement can be identified. Based on equipment operation and maintenance experience, adjust and optimize the equipment failure prediction model.

[0023] First, it is necessary to identify the key equipment in the intelligent manufacturing system. These devices are usually core components in the production process, and once they fail, they will have a significant impact on production. Therefore, these devices should be the focus of monitoring and maintenance. Preprocessed historical fault data should be used as the training set, and machine learning algorithms (such as decision trees, random forests, neural networks, etc.) should be used to train the equipment fault prediction model. During the training process, the model parameters and optimization algorithms should be continuously adjusted to improve the model's predictive performance.

[0024] Reference Figure 5As shown, a component performance prediction model is established using machine learning algorithms to predict the future performance and market competitiveness of components, specifically including: The entire lifecycle data of component design, production and sales is obtained from the smart manufacturing dataset, including user feedback, quality inspection reports and market trends; The dataset is divided into a training set, a validation set, and a test set; The component performance prediction model is trained using the training set, the parameters of the component performance prediction model are adjusted and optimized using the validation set, and the capability of the component performance prediction model is evaluated using the test set. The average value of the indicator parameters of at least one component in the market is taken to obtain the reference value of the indicator parameters. The actual values ​​of the index parameters of the electronic components produced by the electronic component production line are input into the component performance prediction model to obtain the first performance parameter of the component. The first performance parameter is used as the performance indicator. The reference value of the index parameter is input into the component performance prediction model to obtain the second performance parameter of the component. The proportion of electronic components produced by electronic component production lines to the total number of electronic components in the market is used as the characteristic proportion. If the first performance parameter is greater than the second performance parameter, then the number of audiences whose performance requirements for components are lower than the second performance parameter is taken as the first value, and the number of audiences whose performance requirements for components are between the first performance parameter and the second performance parameter is taken as the second value. The first value is multiplied by the feature ratio and then added to the second value to obtain the first occupancy value. The first value and the second value are added to obtain the first comprehensive value. The first occupancy value is divided by the first comprehensive value to obtain the audience ratio. Otherwise, the number of audiences whose performance requirements for components are lower than the first performance parameter is taken as the third value, and the number of audiences whose performance requirements for components are between the first and second performance parameters is taken as the second value. The third value is multiplied by the feature ratio to obtain the second occupancy value. The third value and the second value are added together to obtain the second comprehensive value. The second occupancy value is divided by the second comprehensive value to obtain the audience ratio. The proportion of the target audience is used as a measure of the market competitiveness of the components produced by the electronic component production line.

[0025] SWOT analysis is a situational analysis based on the internal and external competitive environment and conditions. It lists and arranges the major internal strengths, weaknesses and external opportunities and threats closely related to the research object in a matrix form. Then, using the idea of ​​system analysis, it matches and analyzes the various factors to draw a series of corresponding conclusions, which are usually decision-making.

[0026] Optimizing intelligent manufacturing services based on market competitiveness specifically includes: If the audience share is lower than the target value, the parameters of at least one piece of equipment in the electronic component production line will be improved by a preset value, which is based on experience. After each improvement, the audience share will be recalculated. When the audience share exceeds the target value for the first time, the current parameter settings of the equipment will be used as the optimization result of the smart manufacturing service. The target value is the market share target value of the component manufacturer.

[0027] Reference Figure 6 As shown, establishing a data sharing mechanism among various nodes in the supply chain, and leveraging the collaborative functions of a cloud computing platform to achieve information sharing and collaborative operations among these nodes specifically includes: Clearly define the goals and scope of sharing; A data exchange protocol is established, which includes data format, data encoding rules, and transmission protocol; By signing data sharing agreements, the responsibilities and obligations of data sharing are clarified, a data sharing supervision mechanism is established, and a trust mechanism is built. Establish cross-functional teams to enable collaborative operations among all nodes in the supply chain; Enterprises can optimize their supply chain processes by leveraging the collaborative capabilities of cloud computing platforms.

[0028] To ensure the continuous improvement and optimization of the collaborative functions of data sharing mechanisms and cloud computing platforms, enterprises need to establish corresponding continuous improvement mechanisms. This includes developing continuous improvement plans, clarifying improvement goals and measures, and establishing improvement effect evaluation mechanisms. Through continuous improvement mechanisms, enterprises can continuously promote the collaborative functions of data sharing mechanisms and cloud computing platforms to a higher level.

[0029] Furthermore, this solution also proposes a computer-readable storage medium storing a computer-readable program, which, when invoked, executes the aforementioned collaborative control method for the entire electronic component production line.

[0030] It is understandable that the storage medium can be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; an optical medium, such as a DVD; or a semiconductor medium, such as a solid-state drive (SSD).

[0031] In summary, the advantages of this invention are as follows: by providing customized intelligent manufacturing services for production lines, establishing equipment failure prediction models, predicting the future performance and market competitiveness of components, and optimizing intelligent manufacturing services, the invention can predict market feedback based on the performance prediction of components on the production line, thereby controlling the parameters of component production based on market feedback, and thus ensuring that the produced components have good market benefits.

[0032] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention. The scope of protection claimed by the appended claims and their equivalents is defined.

Claims

1. A method for collaborative control of the entire process of an electronic component production line, characterized in that, include: Through Internet of Things (IoT) technology, production data, equipment status, and process information on electronic component production lines can be collected in real time. The collected data is cleaned to remove invalid and redundant data, and the data is preprocessed by formatting and standardization. The data from various devices are integrated and fused to obtain a smart manufacturing dataset, and a comprehensive data view is drawn. Based on the needs of the component market, we provide customized intelligent manufacturing services for production lines. Deeply analyze the intelligent manufacturing dataset to identify the operating status and potential faults of the equipment. Through machine learning algorithms, establish an equipment fault prediction model to predict the future fault trends and possible timing of equipment failures. By using machine learning algorithms, a component performance prediction model is established to predict the future performance and market competitiveness of components. Based on market competitiveness, intelligent manufacturing services are optimized. Establish a data sharing mechanism among all nodes in the supply chain, and realize information sharing and collaborative operation among all nodes in the supply chain through the collaborative function of the cloud computing platform. The supply chain provides raw materials for the production line. The technical architecture required for building intelligent manufacturing services is constructed on a cloud computing platform, and the production line control platform is configured and debugged based on the service solution.

2. The method for collaborative control of the entire process of an electronic component production line according to claim 1, characterized in that, The process of cleaning the collected data, removing invalid and redundant data, and formatting and standardizing the data preprocessing specifically includes: Use data processing tools on the cloud computing platform to traverse the collected data, identify and remove data that does not conform to business logic; For purely numerical data, the Euclidean distance formula is used to calculate the numerical similarity between the collected data points; For multi-feature data, the data is converted into feature vectors, and the feature similarity between each collected data point is calculated using the cosine similarity formula. Determine whether the similarity between each collected data point is higher than the preset similarity threshold. If so, mark the group of data points as redundant data and delete the group of data points until only one data point remains. If not, do not output anything. Based on business needs and data characteristics, data format specifications are formulated, including date format, numeric format, and string format; Using data processing tools on cloud computing platforms, the collected data is preprocessed in a formatted manner based on data format specifications; Based on the distribution characteristics of the data and business needs, the collected data is standardized and preprocessed to convert the data into dimensionless numerical values. The Euclidean distance formula is as follows: ， In the formula, Let be the numerical similarity between the i-th collected data point and the j-th collected data point. , Let be the values ​​of the i-th collected data point and the j-th collected data point, respectively. , These are the data collection times for the i-th and j-th data points, respectively. The cosine similarity formula is: ， In the formula, For the first The collected data points and the first Feature similarity between the collected data points For the first The collected data points are converted into feature vectors. For the first The collected data points are converted into feature vectors.

3. The method for collaborative control of the entire process of an electronic component production line according to claim 2, characterized in that, The process of integrating and fusing data from various devices to obtain a smart manufacturing dataset and creating a comprehensive data view specifically includes: Data integration combines data from various devices with different sources into a unified dataset for storage. Based on data integration, further processing and analysis are performed on the data to extract features, patterns, and trends from the raw data; By utilizing visualization tools and technologies, the operational status of intelligent manufacturing systems can be monitored in real time by creating comprehensive data views.

4. The method for collaborative control of the entire process of an electronic component production line according to claim 3, characterized in that, The smart manufacturing services that provide customized production lines based on the needs of the target audience for components specifically include: Based on the needs of the audience, obtain the lower limit values ​​of the component's index parameters, and set the parameters of at least one piece of equipment in the electronic component production line so that the actual value of the index parameters of the component produced by at least one piece of equipment is greater than the lower limit value of the component's index parameters.

5. The method for collaborative control of the entire process of an electronic component production line according to claim 4, characterized in that, The process of conducting in-depth analysis of intelligent manufacturing datasets to identify equipment operating status and potential faults, and establishing equipment fault prediction models through machine learning algorithms to predict future fault trends and possible timing points, specifically includes: Define maintenance objectives and identify the equipment that needs to be monitored; Obtain the type, function, operating environment, and potential failure modes of the equipment to be monitored; When training the model, the collected historical fault data is used as the training set, and the performance of the equipment fault prediction model is improved by adjusting the model parameters and optimizing the algorithm. Based on historical data and current status, machine learning algorithms are used to predict the likelihood and timing of future failures. Based on the prediction results, a maintenance plan is developed, which includes maintenance time, maintenance content, and spare parts required for maintenance. By comparing data before and after maintenance, the effectiveness of maintenance actions can be analyzed, and potential areas for improvement can be identified. Based on equipment operation and maintenance experience, adjust and optimize the equipment failure prediction model.

6. The method for collaborative control of the entire process of an electronic component production line according to claim 5, characterized in that, The aforementioned method of establishing a component performance prediction model using machine learning algorithms to predict the future performance and market competitiveness of components specifically includes: The entire lifecycle data of component design, production and sales is obtained from the smart manufacturing dataset, including user feedback, quality inspection reports and market trends; The dataset is divided into a training set, a validation set, and a test set; The component performance prediction model is trained using the training set, the parameters of the component performance prediction model are adjusted and optimized using the validation set, and the capability of the component performance prediction model is evaluated using the test set. The average value of the indicator parameters of at least one component in the market is taken to obtain the reference value of the indicator parameters. The actual values ​​of the index parameters of the electronic components produced by the production line are input into the component performance prediction model to obtain the first performance parameter of the component. The first performance parameter is used as the performance indicator. The reference value of the index parameter is input into the component performance prediction model to obtain the second performance parameter of the component. The proportion of electronic components produced by electronic component production lines to the total number of electronic components in the market is used as the characteristic proportion. If the first performance parameter is greater than the second performance parameter, then the number of audiences whose performance requirements for components are lower than the second performance parameter is taken as the first value, and the number of audiences whose performance requirements for components are between the first performance parameter and the second performance parameter is taken as the second value. The first value is multiplied by the feature ratio and then added to the second value to obtain the first occupancy value. The first value and the second value are added to obtain the first comprehensive value. The first occupancy value is divided by the first comprehensive value to obtain the audience ratio. Otherwise, the number of audiences whose performance requirements for components are lower than the first performance parameter is taken as the third value, and the number of audiences whose performance requirements for components are between the first and second performance parameters is taken as the second value. The third value is multiplied by the feature ratio to obtain the second occupancy value. The third value and the second value are added together to obtain the second comprehensive value. The second occupancy value is divided by the second comprehensive value to obtain the audience ratio. The proportion of the target audience is used as a measure of the market competitiveness of the components produced by the electronic component production line.

7. The method for collaborative control of the entire process of an electronic component production line according to claim 6, characterized in that, The optimization of intelligent manufacturing services based on market competitiveness specifically includes: If the audience share is lower than the target value, the parameters of at least one piece of equipment in the electronic component production line will be improved by a preset value, which is based on experience. After each improvement, the audience share will be recalculated. When the audience share exceeds the target value for the first time, the current parameter settings of the equipment will be used as the optimization result of the smart manufacturing service. The target value is the market share target value of the component manufacturer.

8. The method for collaborative control of the entire process of an electronic component production line according to claim 7, characterized in that, The establishment of a data sharing mechanism among nodes in the supply chain, and the realization of information sharing and collaborative operations among nodes in the supply chain through the collaborative functions of the cloud computing platform, specifically includes: Clearly define the goals and scope of sharing; A data exchange protocol is established, which includes data format, data encoding rules, and transmission protocol; By signing data sharing agreements, the responsibilities and obligations of data sharing are clarified, a data sharing supervision mechanism is established, and a trust mechanism is built. Establish cross-functional teams to enable collaborative operations among all nodes in the supply chain; Optimize supply chain processes through the collaborative capabilities of cloud computing platforms.

Images