Virtual technology-based printed circuit board simulation production system and method

Abstract

The invention discloses a printed circuit board simulation production system and method based on a virtual technology. The virtual simulation model is used for production analysis of the printed circuit board, production simulation is performed on the printed circuit board in a reproduction model by collecting real world production data and constructing the virtual production model, and various production parameters can be continuously adjusted, so that the production of the printed circuit board reaches the optimal production efficiency.

Description

Technical Field

[0001] The present invention relates to the field of virtual simulation, and in particular to a printed circuit board simulation production system and method based on virtual technology. Background Art

[0002] Traditional printed circuit board production is a manufacturing process based on chemical etching methods, which generally includes the following steps: First, a layer of conductive copper foil is coated on a substrate, and then through processes such as photolithography, etching, deposition, and soldering, circuit patterns and connection holes are formed, and finally inspection and packaging are carried out. In this process, materials such as chemical reagents, photoresists, and etching solutions are required, and processing is carried out with the aid of equipment such as exposure machines, etching machines, and gold plating machines.

[0003] Traditional printed circuit board production has some challenges and limitations, such as high trial-and-error costs, low production efficiency, difficult quality control, and lack of flexibility. Since the production process cannot be monitored and adjusted in real time, a large number of tests and adjustments are often required, resulting in waste of time and cost. In addition, quality control relying on manual experience and sampling inspection is prone to uncertainty, affecting product stability. Facing the rapid changes in market demand and the requirements of personalized customization, traditional production methods are often difficult to meet. Summary of the Invention

[0004] To solve these problems, the present invention adopts a printed circuit board simulation production system based on virtual technology, which effectively improves production efficiency, quality stability, and flexibility.

[0005] A printed circuit board simulation production system based on virtual technology according to the present invention includes the following modules: Data collection module: This module is responsible for collecting data required to construct a virtual environment, including: equipment type, specifications and performance parameters, production rate, failure rate and maintenance records, material characteristics and process parameters, operation logs, and production reports; cleaning, sorting, and standardizing the data; Virtual modeling and simulation module: Establish a virtual model of printed circuit board production, including equipment models, process flow models, and material models, ensuring that the virtual model can accurately reflect various factors in the actual production environment, supporting simulation and optimization; and performing simulation prediction, constructing a prediction model, and evaluating production efficiency and product quality under different parameter settings; Optimization adjustment and control module: According to the simulation prediction results, adjust and optimize the parameters of production machines, provide suggestions for improving the process flow, and optimize production steps and material usage methods; Performance evaluation and continuous optimization module: Evaluate and verify the performance of the optimized production system, simulate production scenarios under different working conditions, collect actual production data, analyze problems and bottlenecks, and propose suggestions for continuous improvement and optimization.

[0006] As a further solution of the present invention, a method for simulating the production of printed circuit boards based on virtual technology includes the following steps: S1: Collect and prepare data. Collect various data of printed circuit board production machines in the real world, including: equipment type, specifications and performance parameters, production rate, failure rate and maintenance records, material characteristics and process parameters, operation logs and production reports. After data collection, perform data cleaning, sorting and standardization processing on the data. S2: Build a virtual production model. According to the processed data above, build a virtual model for the production of printed circuit boards, including: physical characteristics and performance models of production equipment, process flows and parameter settings, production material characteristics and formulas, quality control and detection mechanisms. S3: Simulate pre-production. Conduct a pre-production model in the virtual model for the production report, set different process parameters and production conditions, and evaluate and analyze production quality and production efficiency. S4: Parameter adjustment and optimization. By continuously adjusting the parameters of production machines, including: equipment parameters, temperature, pressure, production process, material ratio, make the production system reach the best production efficiency, and the best efficiency is provided by the production efficiency prediction model. As a further solution of the present invention, the steps for the production efficiency prediction model to provide the best production efficiency in step S4 are as follows: S41: Data collection and preparation: Collect historical production data, including different process parameters, equipment parameters, production efficiency values and other factors affecting production efficiency, and perform data cleaning, conversion and feature engineering processing on the data. S42: Feature selection and modeling: Select appropriate feature production parameters as input variables of the model, select production efficiency as the target variable, and use machine learning algorithms for modeling. S43: Model training and evaluation: Divide the data set into a training set and a test set, use the training set to train the production efficiency prediction model, use the test set to verify the prediction accuracy of the model, and evaluate the performance indicators of the model. S44: Predict the best production efficiency value: After the model training is completed, input different production parameters, predict the corresponding production efficiency values, and through the production efficiency prediction results output by the model, find the combination of production parameters that makes the production efficiency reach the best state, that is, the parameter settings corresponding to the best production efficiency value. Beneficial effects

[0007] Reduce the trial-and-error cost: Through the pre-production simulation of the virtual production model, multiple optimizations and adjustments can be made before actual production, reducing the trial-and-error cost and improving production efficiency.

[0008] Improve production efficiency: Optimize parameters, processes, and machine adjustments to make the production process more intelligent and precise, thereby improving production efficiency and shortening the production cycle.

[0009] Strengthen quality control: With the help of virtual simulation technology, the production process can be monitored in real time, various parameters can be precisely controlled, quality stability can be improved, and the defective rate can be reduced.

[0010] Enhance production adaptability: The digital twin system has strong flexibility and adaptability, and can automatically adjust production parameters according to different product requirements to meet the needs of personalized customization. Specific implementation manners

[0011] The present invention will be further described in detail below in conjunction with embodiments.

[0012] A printed circuit board simulation production system based on virtual technology includes the following modules: Data collection module: This module is responsible for collecting data required to build a virtual environment, including: equipment type, specifications, and performance parameters, production rate, failure rate, and maintenance records, material characteristics and process parameters, operation logs, and production reports; cleaning, sorting, and standardizing the data; Virtual modeling and simulation module: Establish a virtual model of printed circuit board production, including equipment models, process flow models, and material models, ensuring that the virtual model can accurately reflect various factors in the actual production environment, supporting simulation and optimization; and performing simulation prediction, building a prediction model, and evaluating production efficiency and product quality under different parameter settings; Optimization adjustment and control module: According to the simulation prediction results, adjust and optimize the parameters of production machines, provide suggestions for improving the process flow, and optimize production steps and material usage methods; Performance evaluation and continuous optimization module: Evaluate and verify the performance of the optimized production system, simulate production scenarios under different working conditions, collect actual production data, analyze problems and bottlenecks, and propose suggestions for continuous improvement and optimization.

[0013] Furthermore, a printed circuit board simulation production method based on virtual technology includes the following steps: S1: Collect and prepare data, collect various data of printed circuit board production machines in the real world, including: equipment type, specifications, and performance parameters, production rate, failure rate, and maintenance records, material characteristics and process parameters, operation logs, and production reports; after data collection, clean, sort, and standardize the data; S2: Construct a virtual production model. Based on the processed data above, construct a virtual model for printed circuit board production, including: physical characteristics and performance models of production equipment, process flows and parameter settings, characteristics and formulations of production materials, quality control and inspection mechanisms; S3: Simulate pre-production. Conduct a pre-production model in the virtual model, set different process parameters and production conditions, and evaluate and analyze production quality and production efficiency; S4: Parameter adjustment and optimization. Continuously adjust the parameters of production machines, including: equipment parameters, temperature, pressure, production process, material ratio, to make the production system achieve the best production efficiency, where the best efficiency is provided by the production efficiency prediction model; Furthermore, the steps for the production efficiency prediction model to provide the best production efficiency in step S4 are as follows: S41: Data collection and preparation: Collect historical production data, including different process parameters, equipment parameters, production efficiency values, and other factors affecting production efficiency, and perform data cleaning, transformation, and feature engineering on the data; S42: Feature selection and modeling: Select appropriate characteristic production parameters as input variables of the model, select production efficiency as the target variable, and use machine learning algorithms for modeling; S43: Model training and evaluation: Divide the data set into a training set and a test set, use the training set to train the production efficiency prediction model, use the test set to verify the prediction accuracy of the model, and evaluate the performance indicators of the model; S44: Predict the best production efficiency value: After the model training is completed, input different production parameters, predict the corresponding production efficiency values, and through the production efficiency prediction results output by the model, find the combination of production parameters that makes the production efficiency reach the best state, that is, the parameter settings corresponding to the best production efficiency value.

Claims

1. A printed circuit board simulation production system based on virtual technology, characterized in that: Includes the following modules: Data collection module: This module is responsible for collecting the data needed to build the virtual environment, including: equipment type, specifications and performance parameters, production rate, failure rate and maintenance records, material characteristics and process parameters, operation logs and production reports; cleaning, sorting and standardizing the data; Virtual modeling and simulation module: Establish a virtual model of printed circuit board production, including equipment model, process flow model, and material model, to ensure that the virtual model can accurately reflect various factors in the actual production environment and support simulation and optimization; and perform simulation prediction, build prediction models, and evaluate production efficiency and product quality under different parameter settings; Optimization, adjustment and control module: adjust and optimize the parameters of the production machine according to the simulation prediction results, provide process improvement suggestions, and optimize the production steps and material usage methods; Performance evaluation and continuous optimization module: perform performance evaluation and verification on the optimized production system, simulate production scenarios under different working conditions, collect actual production data, analyze problems and bottlenecks, and put forward suggestions for continuous improvement and optimization.

2. A printed circuit board simulation production method based on virtual technology, characterized in that: The following steps are involved: S1: Collect and prepare data. Collect various data of printed circuit board production machines in the real world, including: equipment type, specifications and performance parameters, production rate, failure rate and maintenance records, material characteristics and process parameters, operation logs and production reports; after data collection, clean, organize and standardize the data; S2: Construct a virtual production model. Based on the above processed data, a virtual model of printed circuit board production is constructed, including: physical characteristics and performance models of production equipment, process flow and parameter settings, production material characteristics and formulas, quality control and detection mechanisms; S3: Simulate pre-production and production report to conduct pre-production model in virtual model, set different process parameters and production conditions, and evaluate and analyze production quality and production efficiency; S4: Parameter adjustment and optimization, by continuously adjusting the parameters of the production machines, including: equipment parameters, temperature, pressure, production process, material ratio, so that the production system can achieve the best production efficiency. The best efficiency is provided by the production efficiency prediction model.

3. A printed circuit board simulation production method based on virtual technology according to claim 2, characterized in that: The steps of providing the production efficiency prediction model with the optimal production efficiency in step S4 are as follows: S41: Data collection and preparation: Collect historical production data, including different process parameters, equipment parameters, production efficiency values ​​and other factors affecting production efficiency, and clean, convert and feature engineer the data; S42: Feature Selection and Modeling: Select appropriate characteristic production parameters as the input variables of the model, select production efficiency as the target variable, and use machine learning algorithms to build models; S43: Model training and evaluation: Divide the data set into a training set and a test set. Use the training set to train the production efficiency prediction model, and use the test set to verify the prediction accuracy of the model and evaluate the performance indicators of the model. S44: Predict the optimal production efficiency value: After the model training is completed, different production parameters are input to predict the corresponding production efficiency values. Through the production efficiency prediction results output by the model, the production parameter combination that makes the production efficiency reach the optimal state is found, that is, the parameter setting corresponding to the optimal production efficiency value.