AI analysis system for pressing range selection and product insurance data collection in pressing process
By designing an AI analysis system in the pressing process in the PCB industry, using data collection and model establishment, combining temperature and pressure adjustment, the large workload problem of improving the pressing yield is solved, and the automated optimization and production of the pressing process is realized. Improve efficiency.
Patent Information
- Application Number
- CN202410971623.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-19
- Publication Date
- 2024-11-08
AI Technical Summary
In the implementation of Industry 4.0 in the PCB industry, despite a complete detection and collection system, there are still challenges in how to use the quality data of the pressing process to improve the pressing yield with effective tools, and engineering personnel need to invest a lot of work to carry out Analysis and model building.
Design an AI analysis system for pressure selection and quality assurance data collection in the pressing process, through data collection and sorting, yield model establishment, AI analysis system application, result analysis and countermeasure optimization, long-term SPC analysis and countermeasure optimization, combined with Temperature and pressure adjust the pressure stroke and establish a smart analysis model to optimize the pressure stroke process.
The automatic optimization of the pressing process is achieved, abnormal problems are reduced, production efficiency and new product development efficiency are improved, costs and failure rates are reduced, labor and material consumption are reduced, and the number of pressed layers and process capabilities are improved.
Smart Images

Figure CN118917600A_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to the field of pressing processes, and in particular to an AI analysis system for pressing process selection and quality assurance data collection in a pressing process. [Background technology]
[0002] In view of the current PCB industry's promotion of Industry 4.0, which focuses on the linkage between hardware equipment and stations, the intelligent production management system has replaced the heavy work of production management, a large number of equipment has replaced manufacturing manpower, and automatic testing equipment has replaced quality assurance manpower, which has played a huge role in the development of the industry; the industry currently has a complete detection and collection system for the collection of quality data such as board thickness and target distance, but how to apply these data to become an effective tool is still lacking and needs to be improved. The test result data collected in each process should be analyzed and a yield model should be established, and AI intelligent analysis technology should be provided for the development of new material number work orders. It also requires engineering personnel to invest a lot of work to improve the pressing yield. [Summary of the invention]
[0003] The purpose of the present invention is to solve the above-mentioned problems existing in the implementation of Industry 4.0 in the current PCB industry, and to provide an AI analysis system for pressing process selection and quality assurance data collection in the pressing process.
[0004] The present invention is realized by the following technical scheme: an AI analysis system for pressing process selection and quality assurance data collection in a pressing process, the specific steps are as follows:
[0005] S1. Data collection and collation: It is necessary to comprehensively collect various quality data in the lamination process, collect detailed data on plate thickness, target distance, plate surface abnormal items, and reliability abnormal items, and analyze the location of abnormality according to the stacking position and the arrangement position on the steel plate surface;
[0006] S2. Yield model establishment: Conduct in-depth analysis on the accumulated data to find out the rules and influencing factors. Based on the results of yield data analysis, reflect the yield correlation between the pressing hardware and the pressing process data, and establish a related yield model.
[0007] S3. AI analysis system application: Input the collected data into the AI analysis system, which will automatically accumulate data and continuously analyze all data and output the results. This AI analysis system performs regression analysis on a large amount of accumulated production history data to form a deep learning model or other machine learning algorithm.
[0008] S4. Result analysis and countermeasure optimization: According to the results output by the AI analysis system, conduct detailed analysis to find out the factors that may affect the yield, and then formulate corresponding countermeasures to optimize the pressing process;
[0009] S5. Long-term SPC analysis and countermeasure optimization: Continuously collect data and conduct long-term SPC analysis to monitor the stability of the process, identify potential problems in a timely manner, predict the pressing process design of new material numbers, and update and improve the model to improve the yield of existing products and improve the development efficiency and success rate of new products.
[0010] Furthermore, in S1, the thermal insulation effect must be considered in the pressing process. Heat conduction to the buffer material, carrier plate, steel plate and material all have a certain heat capacity ratio, resulting in differences in heat dissipation and thermal insulation. The effects of temperature and pressure on the colloid are recorded, understood and integrated, and temperature and pressure are used as two available tools to adjust the pressing process. Then, the product characteristics of the circuit board are understood. The number of board layers, board size, board thickness, inner layer board thickness, stacking characteristics, residual copper rate on the glue filling surface, surface copper thickness, bottom copper thickness, number of single-layer PP sheets, and material gelling time designed according to the requirements of various product application characteristics will be different, so that hundreds of different pressing methods can be combined, and different empirical values are generated for the pressing process design method. The glue flow characteristics and control methods of temperature and pressure for different types of products are summarized and applied in actual production.
[0011] Furthermore, the specific steps for optimizing the S4 pressing process are as follows:
[0012] S4-1. Obtain product categories and characteristics;
[0013] S4-2. Obtain production process conditions and prerequisites;
[0014] S4-3, input and analyze the pressing program;
[0015] S4-4, input abnormal points and yield of pressing results;
[0016] S4-5. Analyze and optimize the pressure process according to the process conditions of S4-2;
[0017] S4-6. Repeat steps S4-4 and S4-5 and perform PDCA until the pressing process yield is optimized.
[0018] Furthermore, the purpose of optimizing the pressing process in S4-5 is to solve abnormal problems, solve quality costs and yields in production, increase production, save materials and labor, control target distance, improve alignment, increase the number of pressing layers and process capabilities, reduce failure rate, reduce glue flow, optimize board thickness, reduce glue overflow, reduce board surface defects, improve reliability, and eliminate white spot explosion.
[0019] Furthermore, the board surface abnormal items in S1 include pits and depressions, copper wrinkles, and the reliability abnormal items include poor glue filling, board bursting, and white spots.
[0020] Furthermore, the pressing hardware of S1 is a hot plate, a cover bottom plate, a steel plate and a buffer material.
[0021] The beneficial effects of the present invention are as follows: the present application is mainly aimed at the pressing process, starting from the fluidity of the glue, collecting and analyzing empirical data on various factors affecting the pressing procedure, improving the pressing process selection model of the pressing process, and integrating the fool-proof mechanism of the pressing process indicated by the work order and the pressing machine parameter system in series, thereby establishing a set of intelligent analysis models for pressing process optimization. AI intelligent analysis of the pressing process becomes feasible, and there is no need to invest a large number of senior engineers to detect and sort abnormal boards and find the causes of layer abnormalities. The experience can be accumulated directly through the production of big data to achieve the matching pressing process of new product material numbers, thereby improving the efficiency of new product development and reducing costs.
Brief Description of the Drawings
[0022] Figure 1 It is a schematic diagram of the present invention. [Specific implementation method]
[0023] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments:
[0024] like Figure 1 As shown, an AI analysis system for pressing process selection and quality assurance data collection in the pressing process, the specific steps are as follows:
[0025] S1. Data collection and collation: It is necessary to comprehensively collect various quality data in the lamination process, collect detailed data on plate thickness, target distance, plate surface abnormal items, and reliability abnormal items, and analyze the location of abnormality according to the stacking position and the arrangement position on the steel plate surface;
[0026] S2. Yield model establishment: Conduct in-depth analysis on the accumulated data to find out the rules and influencing factors. Based on the results of yield data analysis, reflect the yield correlation between the pressing hardware and the pressing process data, and establish a related yield model.
[0027] S3. AI analysis system application: Input the collected data into the AI analysis system, which will automatically accumulate data and continuously analyze all data and output the results. This AI analysis system performs regression analysis on a large amount of accumulated production history data to form a deep learning model or other machine learning algorithm.
[0028] S4. Result analysis and countermeasure optimization: According to the results output by the AI analysis system, conduct detailed analysis to find out the factors that may affect the yield, and then formulate corresponding countermeasures to optimize the pressing process;
[0029] S5. Long-term SPC analysis and countermeasure optimization: Continuously collect data and conduct long-term SPC analysis to monitor the stability of the process, identify potential problems in a timely manner, predict the pressing process design of new material numbers, and update and improve the model to improve the yield of existing products and improve the development efficiency and success rate of new products.
[0030] Preferably, in said S1, the thermal insulation effect must be considered in the pressing process. The heat conduction to the buffer material, carrier plate, steel plate and material all have a certain heat capacity ratio, resulting in differences in heat dissipation and thermal insulation. The influence of temperature and pressure on the colloid is recorded, understood and integrated, and temperature and pressure are used as two available tools to adjust the pressing process. Then, the product characteristics of the circuit board are understood. The number of board layers, board size, board thickness, inner layer board thickness, stacking characteristics, residual copper rate of the glue filling surface, surface copper thickness, bottom copper thickness, number of single-layer PP sheets, and material gelling time designed according to the requirements of various product application characteristics will be different, so that hundreds of different pressing methods can be combined, and different empirical values are generated for the pressing process design method. The glue flow characteristics and control methods of temperature and pressure for different types of products are summarized and applied in actual production.
[0031] Preferably, the specific steps for optimizing the pressure process of S4 are as follows:
[0032] S4-1. Obtain product categories and characteristics;
[0033] S4-2. Obtain production process conditions and prerequisites;
[0034] S4-3, input and analyze the pressing program;
[0035] S4-4, input abnormal points and yield of pressing results;
[0036] S4-5. Analyze and optimize the pressure process according to the process conditions of S4-2;
[0037] S4-6. Repeat steps S4-4 and S4-5 and perform PDCA until the pressing process yield is optimized.
[0038] Preferably, the purpose of optimizing the pressing process in S4-5 is to solve abnormal problems, solve quality costs and yields in production, increase output, save materials and labor, control target distance, improve alignment, increase the number of pressing layers and process capabilities, reduce failure rate, reduce glue flow, optimize board thickness, reduce glue overflow, reduce board surface defects, improve reliability, and eliminate white spot explosion.
[0039] Preferably, the board surface abnormal items in S1 include pits and depressions, copper wrinkles, and the reliability abnormal items include poor glue filling, board bursting, and white spots.
[0040] Preferably, the pressing hardware of S1 is a hot plate, a cover bottom plate, a steel plate and a buffer material.
[0041] According to the disclosure and teaching of the above description, those skilled in the art to which the present invention belongs may also make appropriate changes and modifications to the above embodiments. Therefore, the present invention is not limited to the specific embodiments disclosed and described above, and some modifications and changes to the present invention should also fall within the scope of protection of the claims of the present invention. In addition, although some specific terms are used in this specification, these terms are only for the convenience of description and do not constitute any limitation to the present invention.
Claims
1. An AI analysis system for selecting the pressing process and collecting quality assurance data in the pressing process, characterized in that: The specific steps are as follows: S1. Data collection and collation: It is necessary to comprehensively collect various quality data in the lamination process, collect detailed data on plate thickness, target distance, plate surface abnormal items, and reliability abnormal items, and analyze the location of abnormality according to the stacking position and the arrangement position on the steel plate surface; S2. Yield model establishment: Conduct in-depth analysis on the accumulated data to find out the rules and influencing factors. Based on the results of yield data analysis, reflect the yield correlation between the pressing hardware and the pressing process data, and establish a related yield model. S3. AI analysis system application: Input the collected data into the AI analysis system, which will automatically accumulate data and continuously analyze all data and output the results. This AI analysis system performs regression analysis on a large amount of accumulated production history data to form a deep learning model or other machine learning algorithm. S4. Result analysis and countermeasure optimization: According to the results output by the AI analysis system, conduct detailed analysis to find out the factors that may affect the yield, and then formulate corresponding countermeasures to optimize the pressing process; S5. Long-term SPC analysis and countermeasure optimization: Continuously collect data and conduct long-term SPC analysis to monitor the stability of the process, identify potential problems in a timely manner, predict the pressing process design of new material numbers, and update and improve the model to improve the yield of existing products and improve the development efficiency and success rate of new products.
2. The AI analysis system for selecting the pressing process and collecting quality assurance data in the pressing process according to claim 1, characterized in that: In S1, the thermal insulation effect must be considered in the pressing process. Heat is transferred to the buffer material, carrier plate, steel plate and material, and there is a certain heat capacity ratio, which leads to the difference between heat dissipation and thermal insulation. The influence of temperature and pressure on the colloid is recorded, understood and integrated, and temperature and pressure are used as two available tools to adjust the pressing process. Then, the product characteristics of the circuit board are understood. The number of board layers, board size, board thickness, inner layer thickness, stacking characteristics, residual copper rate of the filling surface, surface copper thickness, bottom copper thickness, number of single-layer PP sheets, and material gelling time designed according to the requirements of various product application characteristics will be different, so that hundreds of different pressing methods can be combined, and different empirical values are generated for the pressing process design method. The glue flow characteristics and control methods of temperature and pressure for different types of products are summarized and applied in actual production.
3. The AI analysis system for selecting the pressing process and collecting quality assurance data in the pressing process according to claim 2, characterized in that: The specific steps for optimizing the S4 pressure process are as follows: S4-1. Obtain product categories and characteristics; S4-2. Obtain production process conditions and prerequisites; S4-3, input and analyze the pressing program; S4-4, input abnormal points and yield of pressing results; S4-5. Analyze and optimize the pressure process according to the process conditions of S4-2; S4-6. Repeat steps S4-4 and S4-5 and perform PDCA until the pressing process yield is optimized.
4. The AI analysis system for selecting the pressing process and collecting quality assurance data in the pressing process according to claim 3, characterized in that: The purpose of optimizing the pressing process in S4-5 is to solve abnormal problems, solve quality costs and yields in production, increase production, save materials and labor, control target distance, improve alignment, increase the number of pressing layers and process capabilities, reduce failure rate, reduce glue flow, optimize board thickness, reduce glue overflow, reduce board surface defects, improve reliability, and prevent white spot explosion.
5. The AI analysis system for selecting the pressing process and collecting quality assurance data in the pressing process according to claim 1, characterized in that: The abnormal items on the board surface in S1 include pits and depressions, copper wrinkles, and the abnormal items on the reliability include poor glue filling, board bursting, and white spots.
6. The AI analysis system for selecting the pressing process and collecting quality assurance data in the pressing process according to claim 1, characterized in that: The pressing hardware of S1 is a hot plate, a cover bottom plate, a steel plate and a buffer material.
