A training and prediction method and device for a PCB electroplating parameter prediction model

Abstract

The application discloses a kind of PCB electroplating parameter prediction model training, prediction method and device, method includes: data set is divided into data set and test set;Model training is carried out to training set, and the model that training is completed is saved;Predictive value output is carried out to training set and data set, and the predictive value obtained is compared with actual value, to obtain the evaluation index value of training set and test set;According to the evaluation index value of training set and test set that set threshold value is filtered out in line with threshold value, constructs second random number generator seed database;Data set is divided into training set and test set using second random number generator seed, to generate second training and test set database and carry out model training, and the model that training is completed is saved, to obtain second prediction model database;PCB electroplating parameter is predicted using the prediction model in second prediction model database, to obtain predictive value list.The application makes that prediction result is more reliable, and the quality of production is improved.

Description

Technical Field

[0001] This invention relates to the field of PCB manufacturing technology, and more specifically to a training and prediction method and apparatus for a PCB electroplating parameter prediction model. Background Technology

[0002] The accuracy of PCB electroplating parameters, including current density, electroplating time, and the settings of these parameters, directly determines product quality, yield, production efficiency, and production costs. Electroplating time is set based on the upper and lower limits of the VCP line current density, and the current density is estimated based on the required copper thickness for PCB electroplating. Currently, the industry focuses on identifying factors influencing current density, primarily PCB product characteristics such as board thickness, hole diameter, and copper thickness requirements. Mathematical models are then established for prediction and optimization, mainly decision tree models and multiple linear regression models. During model training, a seed from a random number generator is specified to divide the training and test sets. The model is then trained and predictions are made based on the generated model. Models trained using the specified seed may exhibit inconsistent yield predictions, such as higher yield predictions on the training set but lower yield predictions on the test set.

[0003] The above training methods have the following shortcomings: the training model may overfit or underfit, and the prediction model may be unstable, resulting in the PCB copper thickness being too thick or too thin according to the predicted electroplating parameters, which in turn increases production costs and reduces production efficiency and quality yield. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of the prior art and provide a training and prediction method and apparatus for a PCB electroplating parameter prediction model.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] In a first aspect, the present invention provides a method for training and predicting a PCB electroplating parameter prediction model, comprising:

[0007] Obtain the original production data of the PCB;

[0008] The original PCB production data is preprocessed to obtain a dataset;

[0009] Construct a seed database for the first random number generator and set the range of the first random number generator seed;

[0010] Based on the range of the first random number generator seed, the dataset is divided into a training set and a test set to generate the first training and test set database.

[0011] The model is trained on the training set in the first training and test set database, and the trained model is saved to obtain the first prediction model database.

[0012] Each prediction model in the first prediction model database is used to generate prediction values ​​for the training set and the test set. The predicted values ​​are then compared with the actual values ​​to obtain the evaluation index values ​​for the training set and the test set.

[0013] Based on the error control requirements for electroplating parameters, threshold values ​​for evaluation indicators in the training and testing sets are set.

[0014] The evaluation index values ​​of the training set and test set that meet the threshold are selected, and the second random number generator seed database is constructed using the first random number generator seed corresponding to the training set and test set that meet the threshold requirements.

[0015] The dataset is divided into training and test sets using a second random number generator seed to generate a second training and test set database;

[0016] The model is trained on the training set in the second training and test set database, and the trained model is saved to obtain the second prediction model database.

[0017] The PCB electroplating parameters are predicted using the prediction models in the second prediction model database to obtain a list of predicted values.

[0018] Furthermore, the formulas for calculating the evaluation metrics of the training set and the test set are as follows:

[0019] Where RMES is the evaluation index value, y i Indicates the actual value. This represents the predicted value, where n is the number of samples.

[0020] Furthermore, the number of predicted values ​​in the predicted value list is greater than or equal to 1.

[0021] Further, after predicting the PCB electroplating parameters using the prediction models in the second prediction model database to obtain a list of predicted values, the process includes:

[0022] All predicted values ​​in the predicted value list are weighted to obtain the final predicted value.

[0023] Furthermore, the calculation formula for the weighted processing is as follows:

[0024] Where predict1 is the specific predicted value in the list of predicted values, n is the number of predicted values, and predict2 is the final predicted value.

[0025] Furthermore, after weighting all predicted values ​​in the predicted value list to obtain the final predicted value, the process includes:

[0026] The corresponding parameters in the PCB electroplating parameters are automatically updated using the final predicted values.

[0027] Furthermore, the original production data of the PCB includes current density, actual value of surface copper plating, requirements for hole copper plating, surface copper plating requirements, board thickness, minimum hole diameter, and aspect ratio.

[0028] Secondly, the present invention also provides a training and prediction device for a PCB electroplating parameter prediction model, including an acquisition unit, a preprocessing unit, a first construction unit, a first partitioning unit, a first model training unit, a comparison unit, a setting unit, a second construction unit, a second partitioning unit, a second model training unit, and a prediction unit.

[0029] The acquisition unit is used to acquire the original production data of the PCB;

[0030] The preprocessing unit is used to preprocess the original production data of the PCB to obtain a dataset;

[0031] The first construction unit is used to construct a first random number generator seed database and set the range of the first random number generator seed;

[0032] The first partitioning unit is used to divide the dataset into a dataset and a test set according to the range of the first random number generator seed, so as to generate a first training and test set database.

[0033] The first model training unit is used to train the model on the training set in the first training and test set database, and save the trained model to obtain the first prediction model database.

[0034] The comparison unit is used to output predicted values ​​for the training set and the dataset using each predicted model in the first prediction model database, and compare the obtained predicted values ​​with the actual values ​​to obtain the evaluation index values ​​for the training set and the test set.

[0035] The setting unit is used to set the threshold values ​​of the evaluation index values ​​of the training set and the test set according to the error control requirements of the electroplating parameters.

[0036] The second construction unit is used to select the evaluation index values ​​of the training set and test set that meet the threshold, and to construct the second random number generator seed database using the first random number generator seed corresponding to the training set and test set that meet the threshold requirements.

[0037] The second partitioning unit is used to divide the dataset into a training set and a test set using a second random number generator seed, so as to generate a second training and test set database;

[0038] The second model training unit is used to train the model on the training set in the second training and test set database, and save the trained model to obtain the second prediction model database.

[0039] The prediction unit is used to predict PCB electroplating parameters using prediction models in the second prediction model database to obtain a list of predicted values.

[0040] Thirdly, the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the training and prediction method of the PCB electroplating parameter prediction model as described above.

[0041] Fourthly, the present invention also provides a computer-readable storage medium storing a computer program, the computer program including program instructions, which, when executed by a processor, cause the processor to perform the training and prediction method for the PCB electroplating parameter prediction model as described above.

[0042] The beneficial effects of this invention compared to existing technologies are as follows: By dividing the dataset and training the model multiple times, and doing so on the basis of each subsequent division, this invention can find a model that performs well on different datasets, thereby avoiding the problems of overfitting (the model performs well on the training set but poorly on the test set) or underfitting (the model performs poorly on both the training and test sets). At the same time, through multiple trials and screenings, a more stable model can be found, making the prediction results more reliable and improving the quality of production.

[0043] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other objectives, features and advantages of the present invention more obvious and understandable, preferred embodiments are described in detail below. Attached Figure Description

[0044] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1A flowchart illustrating a training and prediction method for a PCB electroplating parameter prediction model, provided for a specific embodiment of the present invention;

[0046] Figure 2 A schematic block diagram of a training and prediction device for a PCB electroplating parameter prediction model provided in a specific embodiment of the present invention;

[0047] Figure 3 This is a schematic block diagram of a computer device provided for a specific embodiment of the present invention. Detailed Implementation

[0048] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0049] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0050] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0051] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0052] like Figure 1 As shown, this embodiment of the invention provides a training and prediction method for a PCB electroplating parameter prediction model. This method is applicable to automated production management systems (such as MES systems) and includes the following steps: S1-S11.

[0053] S1. Obtain the original production data of the PCB.

[0054] Automated production management systems (such as MES systems) can monitor various parameters and statuses on the production line in real time. Integration with these systems allows for the automated collection of production data; therefore, raw PCB production data can be exported from the automated production management system.

[0055] In this embodiment, the original production data of the PCB includes current density, actual value of surface copper plating, hole copper plating requirements, surface copper plating requirements, board thickness, minimum hole diameter, and aspect ratio.

[0056] S2. Preprocess the original PCB production data to obtain a dataset.

[0057] The preprocessing here mainly includes: removing duplicate records, records with missing fields, and records with outliers.

[0058] The purpose of removing duplicate records is to prevent the same record from appearing multiple times in the dataset, which can cause statistical bias and model overfitting. Specifically, methods in data framework tools (such as Pandas) (e.g., `drop_duplicates()`) are used to detect whether identical records exist in the dataset. Once duplicate records are detected, you can choose to keep the first or last record and delete the other duplicates, depending on the situation.

[0059] The purpose of handling missing fields is to ensure that each record is complete and contains all required fields, preventing errors or reduced accuracy in the model when processing missing data. Specifically, you can check each field in the dataset for missing values ​​(NaN or null values) using the `isna()` or `isnull()` methods. If a record's critical field is missing, you can choose to delete the entire record. For non-critical fields, you can fill in the missing values ​​with the mean, median, or other appropriate values.

[0060] The purpose of outlier logging is to remove significant deviations from the norm in a dataset to prevent them from negatively impacting model training and prediction results. Specifically, statistical methods (such as Z-scores and interquartile ranges) or algorithms (such as clustering and isolation forests) are used to detect outliers. Detected outlier records can be directly deleted, or they can be replaced with more reasonable data, such as the mean or median.

[0061] S3. Construct the first random number generator seed database and set the range of the first random number generator seed.

[0062] A random number generator seed is used to initialize the random number generator to ensure that the generated random number sequence is identical each time the same seed value is used. The seed database is a structure that stores all predefined seed values. This database can be a simple list, an array, or even a database table, depending on the specific requirements and implementation details. The seed range refers to the possible range of values ​​that the seed value can take, such as from 0 to 100. Setting this range allows the use of multiple seed values ​​in experiments, ensuring the stability and comprehensiveness of different data partitions and model training results.

[0063] S4. Based on the range of the first random number generator seed, divide the dataset into a training set and a test set to generate the first training and test set database.

[0064] By setting a range of seed values, the dataset can be divided multiple times for cross-validation or to evaluate model stability. Different seed values ​​will generate different combinations of training and test sets. The original dataset is divided into training and test sets. The training set is used for model training, and the test set is used to evaluate model performance. The dataset is randomly divided according to a certain ratio (e.g., 80% training set, 20% test set). Multiple different training and test sets are combined to form the first training and test set database.

[0065] S5. Train the model on the training set in the first training and test set database, and save the trained model to obtain the first prediction model database.

[0066] Select a suitable dataset and task-specific machine learning algorithm to train the model on each training set within the first training and test set database. Machine learning algorithms such as LightGBM, XGBoost, Random Forest, Neural Networks, and Multiple Linear Regression are used. The trained models are then stored in the first prediction model database for subsequent prediction and evaluation. This database can be a simple dictionary, a file system storage, or a more complex database system.

[0067] S6. Use each prediction model in the first prediction model database to output predicted values ​​for the training set and the test set, and compare the obtained predicted values ​​with the actual values ​​to obtain the evaluation index values ​​for the training set and the test set.

[0068] Each prediction model in the first prediction model database makes predictions on both the training and test sets, and the corresponding RMSE metric is calculated, which can effectively evaluate the model's performance. The RMSE of the training set (train_rmse) and the RMSE of the test set (test_rmse) measure the model's performance on the training data and unseen data, respectively. These evaluation metrics can help us further understand the model's generalization ability and select and optimize the most suitable model.

[0069] For each training set, make predictions using the corresponding model and calculate the RMSE for the training set. For each test set, make predictions using the corresponding model and calculate the RMSE for the test set.

[0070] The formulas for calculating the evaluation metrics of the training and test sets are as follows:

[0071] Where RMES is the evaluation index value, y iIndicates the actual value. This represents the predicted value, where n is the number of samples.

[0072] S7. Based on the error control requirements for electroplating parameters, set the threshold values ​​for the evaluation indicators of the training set and the test set.

[0073] Different electroplating parameters have different error requirements. Therefore, the threshold can be set according to the specific electroplating parameter that needs to be controlled and the corresponding error requirement. For example, if the electroplating thickness control error requirement is 0-3μm, based on the normal distribution rule, the upper limit of the threshold for train_rmse and test_rmse is set to t2<=0.8, and the lower limit is t1=t2-0.2. The 0.8 is set based on the fact that the electroplated copper thickness output in 1ASF*h electroplating time is <=1μm.

[0074] S8. Select the evaluation index values ​​of the training set and test set that meet the threshold, and use the first random number generator seed corresponding to the training set and test set that meet the threshold to construct the second random number generator seed database.

[0075] Based on the values ​​of train_rmse and test_rmse, random number generator seeds that meet the given interval are selected and stored in a new random number generator seed database seed2 (second random number generator seed database). This is a process of selecting the best model.

[0076] By selecting models whose train_rmse and test_rmse values ​​are both within the given interval [t1, t2] and storing the corresponding random number generator seeds in a new seed database seed2, the seeds corresponding to the better-performing models can be effectively selected, thus preventing overfitting or underfitting problems.

[0077] S9. Use the second random number generator seed to divide the dataset into training and test sets to generate a second training and test set database.

[0078] S10. Train the model on the training set in the second training and test set database, and save the trained model to obtain the second prediction model database.

[0079] For steps S9 and S10, in order to further optimize model performance, the selected seeds are divided into datasets and corresponding training and test sets are generated. Then, the model is trained on these datasets to generate a new prediction model database model2 (second prediction model database).

[0080] By using a selected random number generator seed to split the dataset, a new training and test set database, data2, is generated. An ensemble learning algorithm is then applied to train models on these datasets, ultimately producing a prediction model database, model2. This approach combines the advantages of ensemble learning, helping to improve the model's generalization ability and thus achieving more stable and higher predictive performance.

[0081] S11. Use the prediction models in the second prediction model database to predict the PCB electroplating parameters to obtain a list of predicted values.

[0082] Based on the requirements, the prediction models in the second prediction model database are used to predict specific PCB electroplating parameters to obtain a list of predicted values. For example, the model in model2 is used to predict the current density of the PCB part number to be produced, generating a list of predicted values, predict1.

[0083] Note that the number of predicted values ​​in the predicted value list is greater than or equal to 1.

[0084] In one embodiment, step S11 is followed by the following step: S12.

[0085] S12. Weight all predicted values ​​in the predicted value list to obtain the final predicted value.

[0086] The formula for weighted processing is:

[0087] Where predict1 is the specific predicted value in the list of predicted values, n is the number of predicted values, and predict2 is the final predicted value.

[0088] By weighting all predicted values, a more accurate and stable final predicted value, predict2, can be output. This weighting method considers the different performance characteristics of each model, fully utilizing their strengths and improving the accuracy of the final prediction. The final prediction result, predict2, can be saved to a file or database for subsequent analysis and use.

[0089] In one embodiment, step S12 is followed by the following step: S13.

[0090] S13. Use the final predicted value to automatically update the corresponding parameters in the PCB electroplating parameters.

[0091] To achieve automatic parameter updates, the final predicted values ​​are automatically submitted and updated through the MES system, thereby realizing production automation.

[0092] This invention involves multiple partitioning of the dataset and training of the model, with each partition building upon the previous one. This allows for the identification of models that perform well across different datasets, thus avoiding overfitting (the model performs well on the training set but poorly on the test set) or underfitting (the model performs poorly on both the training and test sets). Furthermore, through multiple trials and selections, a more stable model can be found, resulting in more reliable predictions and improved production quality.

[0093] This invention also provides a training and prediction apparatus for a PCB electroplating parameter prediction model. This apparatus is used to execute the steps in any of the aforementioned embodiments of the PCB electroplating parameter prediction model training and prediction method. Specifically, please refer to... Figure 2 , Figure 2 A schematic block diagram of a training and prediction device 1 for a PCB electroplating parameter prediction model provided in an embodiment of this application is shown. The training and prediction device 1 for the PCB electroplating parameter prediction model specifically includes an acquisition unit 10, a preprocessing unit 20, a first construction unit 30, a first division unit 40, a first model training unit 50, a comparison unit 60, a setting unit 70, a second construction unit 80, a second division unit 90, a second model training unit 100, and a prediction unit 110.

[0094] The system comprises the following components: Acquisition Unit 10, for acquiring original PCB production data; Preprocessing Unit 20, for preprocessing the original PCB production data to obtain a dataset; First Construction Unit 30, for constructing a first random number generator seed database and setting the range of the first random number generator seeds; First Partition Unit 40, for dividing the dataset into training and testing sets according to the set range of the first random number generator seeds to generate a first training and testing set database; First Model Training Unit 50, for training models on the training sets within the first training and testing set database and saving the trained models to obtain a first prediction model database; Comparison Unit 60, for using each prediction model in the first prediction model database to output predicted values ​​for the training and datasets, and comparing the obtained predicted values ​​with the actual values ​​to obtain evaluation index values ​​for the training and testing sets; and Setting Unit 70, for setting threshold values ​​for the evaluation index values ​​of the training and testing sets according to the electroplating parameter control error requirements. The second construction unit 80 is used to select evaluation index values ​​for training and test sets that meet the threshold requirements, and to construct a second random number generator seed database using the first random number generator seeds corresponding to the training and test sets that meet the threshold requirements. The second partitioning unit 90 is used to partition the dataset into training and test sets using the second random number generator seeds to generate a second training and test set database. The second model training unit 100 is used to train a model on the training set in the second training and test set database and save the trained model to obtain a second prediction model database. The prediction unit 110 is used to predict PCB electroplating parameters using the prediction models in the second prediction model database to obtain a list of predicted values.

[0095] In one embodiment, the training and prediction device 1 for the PCB electroplating parameter prediction model further includes a weighted processing unit.

[0096] The weighted processing unit is used to weight all the predicted values ​​in the predicted value list to obtain the final predicted value.

[0097] In one embodiment, the training and prediction device 1 for the PCB electroplating parameter prediction model further includes an update unit.

[0098] The update unit is used to automatically update the corresponding parameters in the PCB electroplating parameters using the final predicted values.

[0099] It should be noted that those skilled in the art can clearly understand that the training of the above-mentioned PCB electroplating parameter prediction model, the specific implementation process of the prediction device 1 and each unit can be referred to the corresponding description in the foregoing method embodiments. For the sake of convenience and brevity, it will not be repeated here.

[0100] The training and prediction device for the aforementioned PCB electroplating parameter prediction model can be implemented as a computer program, which can be used in, for example... Figure 3 It runs on the computer device shown.

[0101] Please see Figure 3 , Figure 3 This is a schematic block diagram of a computer device provided in an embodiment of this application. The computer device 700 can be a server, wherein the server can be a standalone server or a server cluster composed of multiple servers.

[0102] like Figure 3 As shown, the computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the training and prediction method steps of the PCB electroplating parameter prediction model as described above.

[0103] The computer device 700 can be a terminal or a server. The computer device 700 includes a processor 720, a memory, and a network interface 750 connected via a system bus 710, wherein the memory may include a non-volatile storage medium 730 and internal memory 740.

[0104] The non-volatile storage medium 730 can store an operating system 731 and a computer program 732. When the computer program 732 is executed, it enables the processor 720 to perform training and prediction methods for the PCB electroplating parameter prediction model.

[0105] The processor 720 provides computing and control capabilities to support the operation of the entire computer device 700.

[0106] The internal memory 740 provides an environment for the operation of the computer program 732 in the non-volatile storage medium 730. When the computer program 732 is executed by the processor 720, the processor 720 can execute the training and prediction methods of the PCB electroplating parameter prediction model.

[0107] This network interface 750 is used for network communication, such as sending assigned tasks. Those skilled in the art will understand that... Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device 700 to which the present application is applied. The specific computer device 700 may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements. The processor 720 is used to run program code stored in memory to implement the training and prediction method steps of the PCB electroplating parameter prediction model.

[0108] Those skilled in the art will understand that Figure 3 The embodiments of the computer device shown do not constitute a limitation on the specific configuration of the computer device. In other embodiments, the computer device may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. For example, in some embodiments, the computer device may include only memory and a processor. In such embodiments, the structure and function of the memory and processor are different from those shown. Figure 3 The embodiments shown are consistent and will not be repeated here.

[0109] It should be understood that, in the embodiments of this application, the processor 720 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0110] In another embodiment of the present invention, a computer-readable storage medium is provided. This computer-readable storage medium may be a non-volatile computer-readable storage medium. The computer-readable storage medium stores a computer program, wherein when executed by a processor, the computer program implements the training and prediction method for the PCB electroplating parameter prediction model disclosed in this embodiment of the present invention.

[0111] Those skilled in the art will readily understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this invention.

[0112] In the embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Units with the same function may be grouped into one unit. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, or may be electrical, mechanical, or other forms of connection.

[0113] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of the present invention, depending on actual needs.

[0114] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0115] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), magnetic disks, or optical disks.

[0116] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A training and prediction method for a PCB electroplating parameter prediction model, characterized in that, include: Obtain the original production data of the PCB, which includes current density, actual value of surface copper plating, hole copper plating requirements, surface copper plating requirements, board thickness, minimum hole diameter, and aspect ratio. The original PCB production data is preprocessed to obtain a dataset; Construct a seed database for the first random number generator and set the range of the first random number generator seed; Based on the range of the first random number generator seed, the dataset is divided into a training set and a test set to generate the first training and test set database; The model is trained on the training set in the first training and test set database, and the trained model is saved to obtain the first prediction model database. Each prediction model in the first prediction model database is used to generate prediction values ​​for the training set and the test set. The predicted values ​​are then compared with the actual values ​​to obtain the evaluation index values ​​for the training set and the test set. Based on the error control requirements for electroplating parameters, threshold values ​​for evaluation indicators in the training and testing sets are set. The evaluation index values ​​of the training set and test set that meet the threshold are selected, and the second random number generator seed database is constructed using the first random number generator seed corresponding to the training set and test set that meet the threshold requirements. The dataset is divided into training and test sets using a second random number generator seed to generate a second training and test set database; The model is trained on the training set in the second training and test set database, and the trained model is saved to obtain the second prediction model database. The PCB electroplating parameters are predicted using the prediction models in the second prediction model database to obtain a list of predicted values.

2. The training and prediction method for a PCB electroplating parameter prediction model according to claim 1, characterized in that, The formulas for calculating the evaluation metrics of the training and test sets are as follows: ,in, To evaluate the indicator values, Indicates the actual value. Indicates the predicted value. This represents the number of samples.

3. The training and prediction method for a PCB electroplating parameter prediction model according to claim 1, characterized in that, The predicted value list contains at least one predicted value.

4. The training and prediction method for a PCB electroplating parameter prediction model according to claim 3, characterized in that, After using the prediction models in the second prediction model database to predict the PCB electroplating parameters and obtain a list of predicted values, the process includes: All predicted values ​​in the predicted value list are weighted to obtain the final predicted value.

5. The training and prediction method for a PCB electroplating parameter prediction model according to claim 4, characterized in that, The calculation formula for the weighted processing is as follows: ,in, For the specific predicted values ​​in the predicted value list, The number of predicted values. This is the final predicted value.

6. The training and prediction method for a PCB electroplating parameter prediction model according to claim 4, characterized in that, The process of weighting all predicted values ​​in the predicted value list to obtain the final predicted value includes: The corresponding parameters in the PCB electroplating parameters are automatically updated using the final predicted values.

7. A training and prediction device for a PCB electroplating parameter prediction model, wherein, during operation, the training and prediction method for the PCB electroplating parameter prediction model according to any one of claims 1-6 is executed, characterized in that, It includes an acquisition unit, a preprocessing unit, a first construction unit, a first partitioning unit, a first model training unit, a comparison unit, a setting unit, a second construction unit, a second partitioning unit, a second model training unit, and a prediction unit; The acquisition unit is used to acquire the original production data of the PCB, which includes current density, actual value of surface copper plating, hole copper plating requirements, surface copper plating requirements, board thickness, minimum hole diameter, and aspect ratio. The preprocessing unit is used to preprocess the original production data of the PCB to obtain a dataset; The first construction unit is used to construct a first random number generator seed database and set the range of the first random number generator seed; The first partitioning unit is used to divide the dataset into a training set and a test set according to the range of the first random number generator seed, so as to generate a first training and test set database. The first model training unit is used to train the model on the training set in the first training and test set database, and save the trained model to obtain the first prediction model database. The comparison unit is used to output predicted values ​​for the training set and the dataset using each predicted model in the first prediction model database, and compare the obtained predicted values ​​with the actual values ​​to obtain the evaluation index values ​​for the training set and the test set. The setting unit is used to set the threshold values ​​of the evaluation index values ​​of the training set and the test set according to the error control requirements of the electroplating parameters. The second construction unit is used to select the evaluation index values ​​of the training set and test set that meet the threshold, and to construct the second random number generator seed database using the first random number generator seed corresponding to the training set and test set that meet the threshold requirements. The second partitioning unit is used to divide the dataset into a training set and a test set using a second random number generator seed, so as to generate a second training and test set database; The second model training unit is used to train the model on the training set in the second training and test set database, and save the trained model to obtain the second prediction model database. The prediction unit is used to predict PCB electroplating parameters using prediction models in the second prediction model database to obtain a list of predicted values.

8. A computer device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the training and prediction method of the PCB electroplating parameter prediction model as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which includes program instructions. When the program instructions are executed by a processor, the processor performs the training and prediction method for the PCB electroplating parameter prediction model as described in any one of claims 1 to 6.

Images