A precision mold design optimization method and system based on data mining

Abstract

The application discloses a precision mold design optimization method and system based on data mining, and the method comprises the following steps: obtaining historical mold data in a mold case database, analyzing unstructured data in the historical mold data, and extracting key historical data; obtaining target material data, target process parameters and target structure data from current mold data, and obtaining first verification data; filtering out historical molds corresponding to the target material data and material characteristic data from the key historical data, and optimizing the target process parameters and the target structure data according to process parameters and structure design data in the historical molds to obtain an optimized mold; performing simulation test on the optimized mold to obtain second verification data, determining an optimization target according to errors between the first verification data and the second verification data and a preset demand, and performing secondary optimization on the current mold or the optimized mold based on the optimization target to obtain a final optimized precision mold.

Description

Technical Field

[0001] This invention relates to the field of mold design and manufacturing technology, and in particular to a precision mold design optimization method and system based on data mining. Background Technology

[0002] Currently, mold design relies heavily on individual engineers' experience, requiring multiple trials and errors to adjust design parameters, resulting in low efficiency and high costs. Furthermore, the design process involves disparate and heterogeneous information from various sources, such as process parameters, material properties, and simulation data, which lacks unified integration. However, existing methods using data mining can assist in optimizing precision mold design, thereby reducing the complexity of optimization and improving efficiency.

[0003] However, existing mold design optimization methods can only focus on assisting the design and optimization of existing or historical molds. For molds with entirely new structures or performance requirements, they tend to rely on data from historical molds for optimization. This can lead to molds with entirely new structures or performance requirements failing to meet design goals and requirements, and failing to achieve accurate and precise auxiliary design of molds. At the same time, molds that fail to meet the standards after optimization using existing methods also increase the complexity of designing and optimizing entirely new molds, and reduce the efficiency of design optimization. Summary of the Invention

[0004] This invention provides a precision mold design optimization method and system based on data mining, in order to solve the technical problem that existing technologies tend to rely on data from historical molds for optimization, resulting in molds with entirely new structures or performance requirements failing to meet design goals and requirements.

[0005] To address the aforementioned technical problems, embodiments of the present invention provide a precision mold design optimization method based on data mining, comprising:

[0006] Historical mold data is obtained from the mold case database, and the unstructured data in the historical mold data is parsed to extract key historical data. Each historical mold corresponds to one key historical data, which includes: material characteristic data, process parameters, structural design data, and verification data.

[0007] Acquire the current mold data, parse the current mold data to obtain target material data, target process parameters and target structure data, and perform simulation test on the current mold to obtain the first verification data;

[0008] Historical molds corresponding to target material data and material characteristic data are selected from key historical data. Based on the process parameters and structural design data in the historical molds, the target process parameters and target structural data are optimized to obtain optimized molds.

[0009] The optimized mold is simulated and tested to obtain second verification data. Based on the errors between the first and second verification data and the preset requirements, the optimization target is determined. Based on the optimization target, the current mold or the optimized mold is optimized a second time to obtain the final optimized precision mold.

[0010] As a preferred embodiment, the step of acquiring historical mold data from the mold case database and parsing the unstructured data in the historical mold data to extract key historical data specifically includes:

[0011] Retrieve historical molds and their corresponding historical mold data from the mold case database;

[0012] The historical mold data corresponding to each historical mold is organized and the unstructured data in the historical mold data is integrated.

[0013] Deep semantic analysis is performed on the unstructured data in the historical mold data to extract material feature data, process parameters, structural design data and verification data from each historical mold.

[0014] As a preferred embodiment, the step of acquiring the current mold data, parsing the current mold data to obtain target material data, target process parameters, and target structure data, and performing simulation tests on the current mold data to obtain first verification data specifically includes:

[0015] Acquire the current mold data, organize the current mold data, and integrate the unstructured data in the current mold data;

[0016] Deep semantic parsing is performed on the unstructured data in the current mold data to extract the target material data, target process parameters, and target structure data in the current mold;

[0017] The current mold is simulated and tested under preset simulation test conditions, and the test data of the current mold is collected during the simulation test as the first verification data of the current mold.

[0018] As a preferred embodiment, the step of selecting historical molds corresponding to target material data and material characteristic data from key historical data, and optimizing the target process parameters and target structural data based on the process parameters and structural design data in the historical molds to obtain an optimized mold, specifically includes:

[0019] Based on the target material data, the material feature data in the key historical data are compared to screen out the historical molds that correspond to the target material data and the material feature data.

[0020] Based on the process parameters and structural design data in the historical molds, generate mold constraint conditions;

[0021] Based on the first verification data, determine the optimization weight of the target mold;

[0022] Based on the mold constraints and optimization weights, an optimization parameter combination is generated using a preset LSTM prediction optimization model.

[0023] The target process parameters and target structural data are optimized according to the optimized parameter combination, and an optimized mold is generated based on the optimized target process parameters and target structural data.

[0024] As a preferred embodiment, the method for constructing the preset LSTM prediction optimization model includes:

[0025] Construct the structure of the initial LSTM model;

[0026] The historical mold data in the mold case database is preprocessed to obtain training data;

[0027] Design an optimization algorithm and construct a loss function based on the verification data in the historical mold data;

[0028] Based on the optimization algorithm, combined with the loss function, and using the training data, the initial LSTM model is iteratively trained.

[0029] After reaching the preset number of iterations, the preset LSTM prediction optimization model is obtained.

[0030] As a preferred embodiment, the process of performing simulation tests on the optimized mold to obtain second verification data, determining the optimization target based on the errors between the first and second verification data and the preset requirements, and performing secondary optimization on the current mold or the optimized mold based on the optimization target to obtain the final optimized precision mold, specifically includes:

[0031] The optimized mold is simulated and tested under preset simulation test conditions, and the test data of the optimized mold is collected during the simulation test as the second verification data; wherein, both the first verification data and the second verification data include the mold trial defect record and the mold life index;

[0032] Determine the first error between the first verification data and the second verification data;

[0033] When the first error between the first verification data and the second verification data is less than a preset range, a first optimization target is generated based on the difference between the trial mold defect records and mold life indicators in the first verification data and the preset requirements, through a preset mold optimization model.

[0034] Based on the difference between the trial mold defect records and mold life indicators in the second verification data and the preset requirements, a second optimization target is generated through a preset mold optimization model;

[0035] The first optimization objective and the second optimization objective are fused to obtain the final optimization objective, and the optimized mold is further optimized based on the final optimization objective to obtain the final optimized precision mold.

[0036] As a preferred option, it also includes:

[0037] When the first error between the first verification data and the second verification data is not less than a preset range, calculate the second error between the trial mold defect record and mold life index in the first verification data and the preset requirement, and calculate the third error between the trial mold defect record and mold life index in the second verification data and the preset requirement.

[0038] When the second error is less than the third error, based on the difference between the trial mold defect record and mold life index in the first verification data and the preset requirements, a first optimization target is generated through a preset mold optimization model, and the target mold is optimized a second time based on the first optimization target to obtain the final optimized precision mold.

[0039] When the third error is less than the second error, based on the difference between the trial mold defect record and mold life index in the second verification data and the preset requirements, a second optimization target is generated through the preset mold optimization model, and the optimized mold is further optimized based on the second optimization target to obtain the final optimized precision mold.

[0040] Accordingly, the present invention also provides a precision mold design optimization system based on data mining, comprising:

[0041] The history module is used to acquire historical mold data from the mold case database and parse the unstructured data in the historical mold data to extract key historical data. Each historical mold corresponds to one key historical data, which includes: material characteristic data, process parameters, structural design data, and verification data.

[0042] The parsing module is used to acquire the current mold data, parse the current mold data to obtain target material data, target process parameters and target structure data, and perform simulation tests on the current mold to obtain the first verification data;

[0043] The optimization module is used to filter out historical molds corresponding to target material data and material characteristic data from key historical data, and optimize the target process parameters and target structural data based on the process parameters and structural design data in the historical molds, thereby obtaining an optimized mold.

[0044] The secondary module is used to perform simulation tests on the optimized mold to obtain second verification data, and to determine the optimization target based on the errors between the first verification data and the second verification data and the preset requirements, and to perform secondary optimization on the current mold or the optimized mold based on the optimization target to obtain the final optimized precision mold.

[0045] Accordingly, the present invention also provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the data mining-based precision mold design optimization method as described above.

[0046] Accordingly, the present invention also provides a computer-readable storage medium comprising a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the data mining-based precision mold design optimization method as described above.

[0047] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0048] The technical solution of this invention extracts key historical data by acquiring historical mold data from a mold case database, and then filters out historical molds corresponding to target material data and material characteristic data by acquiring current mold data. Based on these historical molds, optimization is performed to obtain an optimized mold. The optimized mold is then subjected to simulation testing to obtain second verification data, which is used to determine the error between the optimized mold data and the preset requirements. Finally, the optimization target is determined. This avoids optimizing a completely new current mold solely based on the data from the optimized mold. It also allows for optimization by combining historical mold data when designing a non-new current mold, thereby performing secondary optimization of the current mold or the optimized mold based on the optimization target to obtain a final optimized precision mold. This reduces the complexity of optimizing a completely new mold design and improves design optimization efficiency. Attached Figure Description

[0049] Figure 1 : A flowchart of a precision mold design optimization method based on data mining provided in an embodiment of the present invention;

[0050] Figure 2: A structural diagram of a precision mold design optimization system based on data mining provided in an embodiment of the present invention. Detailed Implementation

[0051] 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 embodiments of the present invention, and not all embodiments. 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. Example 1

[0052] Please refer to Figure 1 The present invention provides a precision mold design optimization method based on data mining, comprising the following steps S101-S104:

[0053] Step S101: Obtain historical mold data from the mold case database, and parse the unstructured data in the historical mold data to extract key historical data; wherein, each historical mold corresponds to one key historical data, and the key historical data includes: material characteristic data, process parameters, structural design data and verification data.

[0054] As a preferred embodiment, the step of acquiring historical mold data from the mold case database and parsing the unstructured data in the historical mold data to extract key historical data specifically includes:

[0055] Retrieve historical molds and their corresponding historical mold data from the mold case database;

[0056] The historical mold data corresponding to each historical mold is organized and the unstructured data in the historical mold data is integrated.

[0057] Deep semantic analysis is performed on the unstructured data in the historical mold data to extract material feature data, process parameters, structural design data and verification data from each historical mold.

[0058] In this embodiment, the key historical data extracted from the historical mold includes, but is not limited to, material characteristic data, process parameters, structural design data, and verification data. Among them, the material characteristic data includes material mechanical properties and forming performance parameters. Material mechanical properties include shear strength (τ), yield strength (σs), tensile strength (σb), elastic modulus, Poisson's ratio, material heat treatment curve, and hardness change, etc. Forming performance parameters include minimum bending radius, elongation of plastic material, springback angle (Δα), neutral layer coefficient, and plastic shrinkage rate, etc. Process parameters include stamping and injection molding parameters. Stamping parameters include blanking clearance (single-sided clearance ratio %t, classified by material such as 7-10%t for low-carbon steel), drawing coefficient (m value, such as 0.5-0.6 for the first drawing of flangeless cylindrical parts), and flanging coefficient (K value, such as 0.68-0.72 for the ultimate flanging coefficient of low-carbon steel). Injection molding parameters include flash value (a key parameter for controlling flash defects, such as 0.03-0.05mm for ABS flash), mold temperature and melt temperature (affecting the molding shrinkage rate of crystalline plastics), holding time and cooling rate (which need to match the phase transformation characteristics of the material). Structural design data includes mold cavity dimensions, parting line position, gating system layout, ejector mechanism stroke, stamping part dimensional tolerances, and mold part fitting clearances. Verification data includes: trial mold defect records (such as shrinkage area and weld line position) and mold life indicators (preferably, stamping mold life ≥ 500,000 cycles, injection mold life ≥ 1 million cycles).

[0059] In this embodiment, the mold case database covers different types of molds (such as injection molds, stamping molds, etc.), and each case includes detailed design drawings, process documents, material specifications, performance test reports, and other information. In addition to data provided by the internal design department, data from the actual manufacturing process, such as processing parameters and quality inspection results, are also collected from the production workshop. At the same time, external data sources such as material performance data provided by suppliers and user feedback are integrated to enrich the data dimensions.

[0060] In this embodiment, unstructured data in historical mold data, such as design drawings (CAD files) and technical documents (PDF, Word, etc.), is converted into structured data tables using data transformation technology. For example, geometric dimensions, tolerances, material specifications, and other information from design drawings can be extracted using the API of CAD software and stored in the corresponding fields of a relational database. Key parameters and descriptions are extracted from technical documents using text mining technology and stored in a structured format. Furthermore, data from different data sources are merged to resolve issues such as inconsistent data formats and data redundancy, integrating unstructured data from historical mold data.

[0061] In this embodiment, Natural Language Processing (NLP) and knowledge graph technologies are used to perform deep semantic analysis on textual information in unstructured data. Preferably, for descriptive text in mold design documents, NLP methods such as part-of-speech tagging, named entity recognition, and semantic role labeling are used to understand key concepts and relationships in the text, such as material type, process steps, and design requirements. Based on the semantic analysis results, a feature extraction algorithm is designed to accurately extract the material feature data, process parameters, structural design data, and verification data of the mold. Specifically, for material feature data, key features such as the strength, toughness, and thermal stability of the material are extracted by analyzing the parameter ranges and performance indicators in the material specification. For process parameters, specific values ​​and control ranges such as processing temperature, pressure, and time are extracted from the process documents.

[0062] Step S102: Obtain the current mold data, parse the current mold data to obtain target material data, target process parameters and target structure data, and perform simulation testing on the current mold to obtain the first verification data.

[0063] As a preferred embodiment, the step of acquiring the current mold data, parsing the current mold data to obtain target material data, target process parameters, and target structure data, and performing simulation tests on the current mold data to obtain first verification data specifically includes:

[0064] Acquire the current mold data, organize the current mold data, and integrate the unstructured data in the current mold data;

[0065] Deep semantic parsing is performed on the unstructured data in the current mold data to extract the target material data, target process parameters, and target structure data in the current mold;

[0066] The current mold is simulated and tested under preset simulation test conditions, and the test data of the current mold is collected during the simulation test as the first verification data of the current mold.

[0067] In this embodiment, relevant data of the current mold is collected, including design drawings, process documents, material specifications, etc. For unstructured data in the current mold data, such as CAD design drawings (.dwg, .igs, etc.) and technical documents (.pdf, .doc, etc.), data conversion technology is used to convert them into structured data formats. That is, the geometric dimensions, tolerances, material annotations, and other information in the design drawings are extracted through the API of the CAD software and stored in the corresponding fields of the relational database. Text mining technology is used to extract key parameters and descriptions from the technical documents and store them in a structured manner. Then, natural language processing (NLP) and knowledge graph technology are used to perform deep semantic analysis on the text information in the unstructured data to extract the target material data, target process parameters, and target structural data of the current mold.

[0068] In this embodiment, simulation test conditions and parameters are set according to the mold design requirements and application scenario. For example, for injection molds, simulation test conditions may include injection pressure, temperature, and holding time; for stamping molds, they may include stamping speed, material thickness, and mold clearance. The current mold is then subjected to simulation testing. During the simulation, the actual working state of the mold is simulated, and performance data such as stress distribution, deformation, and filling conditions are collected as the first verification data for the current mold. Simultaneously, the verification data generated during the simulation test is collected and stored, forming a complete dataset together with other mold data, providing a basis for subsequent analysis and optimization.

[0069] Step S103: Select historical molds corresponding to the target material data and material characteristic data from the key historical data, and optimize the target process parameters and target structural data based on the process parameters and structural design data in the historical molds to obtain optimized molds.

[0070] As a preferred embodiment, the step of selecting historical molds corresponding to target material data and material characteristic data from key historical data, and optimizing the target process parameters and target structural data based on the process parameters and structural design data in the historical molds to obtain an optimized mold, specifically includes:

[0071] Based on the target material data, the material feature data in the key historical data are compared to screen out the historical molds that correspond to the target material data and the material feature data.

[0072] Based on the process parameters and structural design data in the historical molds, generate mold constraint conditions;

[0073] Based on the first verification data, determine the optimization weight of the target mold;

[0074] Based on the mold constraints and optimization weights, an optimization parameter combination is generated using a preset LSTM prediction optimization model.

[0075] The target process parameters and target structural data are optimized according to the optimized parameter combination, and an optimized mold is generated based on the optimized target process parameters and target structural data.

[0076] In this embodiment, the target material data of the current mold is compared with the material characteristic data in key historical data. This comparison involves parameters such as material composition, mechanical properties, and thermal properties. Specifically, by comparing key indicators such as yield strength, thermal conductivity, and coefficient of linear expansion, the historical molds most similar to the target material data are identified. Based on the comparison results, historical molds that match the target material data are selected. Since historical molds share similar material properties with the current mold, their design and process parameters can be directly adopted for optimization. Furthermore, the design and process parameters of these historical molds have reference and optimization value for the current mold.

[0077] In this embodiment, process parameters (such as injection temperature, holding pressure, cooling time, etc.) and structural design data (such as mold geometry, size, assembly relationship, etc.) are extracted from the selected historical molds. Combined with the current mold design requirements and the data extracted from the historical molds, mold constraints are generated. The constraints include the range of process parameters, restrictions on structural design, etc., which are used to guide the optimization design of the current mold.

[0078] In this embodiment, the first verification data of the current mold (such as stress distribution, deformation, and filling conditions in simulation tests) is used to evaluate the mold's performance on different performance indicators. Based on the performance evaluation results, the optimization weights of the target mold are determined. These optimization weights reflect the relative importance of different performance indicators in the mold optimization process.

[0079] In this embodiment, a predictive optimization model based on a Long Short-Term Memory (LSTM) network is established. The mold constraints and optimization weights are used as inputs to train the LSTM model. Through model prediction, various combinations of optimization parameters are generated. These combinations include different process parameter settings and structural design adjustment schemes. Finally, based on these combinations, optimized target process parameters and target structural data are obtained, thereby generating an optimized mold.

[0080] As a preferred embodiment, the method for constructing the preset LSTM prediction optimization model includes:

[0081] Construct the structure of the initial LSTM model;

[0082] The historical mold data in the mold case database is preprocessed to obtain training data;

[0083] Design an optimization algorithm and construct a loss function based on the verification data in the historical mold data;

[0084] Based on the optimization algorithm, combined with the loss function, and using the training data, the initial LSTM model is iteratively trained.

[0085] After reaching the preset number of iterations, the preset LSTM prediction optimization model is obtained.

[0086] In this embodiment, based on the characteristics of the mold design optimization problem, the input and output dimensions of the LSTM model are determined. The input may include material characteristic data, process parameters, structural design data, etc., of the mold, while the output is the target mold performance index, i.e., the optimized parameter combination. An appropriate number of hidden layers and neurons per layer are selected, along with a suitable activation function. The model's weight parameters are initialized using either random initialization or empirically based pre-trained model parameters. Furthermore, historical mold data in the mold case database is cleaned to remove outliers, missing values, and duplicate data, ensuring the accuracy and completeness of the data.

[0087] In this embodiment, based on the characteristics and training requirements of the LSTM model, a suitable optimization algorithm, such as Adam or RMSprop, is selected. This algorithm can effectively adjust the model's weight parameters and minimize the loss function. Then, based on the optimization goal of the mold design, a loss function is designed. The mean squared error (MSE) loss function can be used to measure the difference between the model's predicted value and the actual value, or a composite loss function can be constructed by combining multiple performance indicators to comprehensively consider the various aspects of the mold's performance.

[0088] In this embodiment, training hyperparameters such as learning rate, batch size, and number of iterations are determined. The learning rate determines the step size for updating model parameters, the batch size affects the amount of data used for each parameter update, and the number of iterations determines the total training time. The initial LSTM model is iteratively trained using training data. In each iteration, training data is input into the model in batches, and the predicted values ​​and loss function values ​​are calculated through forward propagation. Then, an optimization algorithm is used for backpropagation to update the model's weight parameters, gradually reducing the loss function value. Finally, after reaching the preset number of iterations, a preset optimized LSTM prediction model is obtained.

[0089] Step S104: Perform simulation testing on the optimized mold to obtain second verification data, and determine the optimization target based on the errors between the first verification data and the second verification data and the preset requirements, and perform secondary optimization on the current mold or the optimized mold based on the optimization target to obtain the final optimized precision mold.

[0090] As a preferred embodiment, the process of performing simulation tests on the optimized mold to obtain second verification data, determining the optimization target based on the errors between the first and second verification data and the preset requirements, and performing secondary optimization on the current mold or the optimized mold based on the optimization target to obtain the final optimized precision mold, specifically includes:

[0091] The optimized mold is simulated and tested under preset simulation test conditions, and the test data of the optimized mold is collected during the simulation test as the second verification data; wherein, both the first verification data and the second verification data include the mold trial defect record and the mold life index;

[0092] Determine the first error between the first verification data and the second verification data;

[0093] When the first error between the first verification data and the second verification data is less than a preset range, a first optimization target is generated based on the difference between the trial mold defect records and mold life indicators in the first verification data and the preset requirements, through a preset mold optimization model.

[0094] Based on the difference between the trial mold defect records and mold life indicators in the second verification data and the preset requirements, a second optimization target is generated through a preset mold optimization model;

[0095] The first optimization objective and the second optimization objective are fused to obtain the final optimization objective, and the optimized mold is further optimized based on the final optimization objective to obtain the final optimized precision mold.

[0096] In this embodiment, the preset simulation test conditions can be set independently according to actual conditions and needs. The optimized mold is simulated and tested, and test data is collected during the simulation test as second verification data. Then, a first error between the first and second verification data can be calculated. By determining whether the first error exceeds a preset range, the differences in trial mold defect records and mold life indicators between the current mold and the optimized mold are determined. Finally, the final optimization target for the secondary optimization of the optimized mold is determined, thereby obtaining the final optimized precision mold.

[0097] In this embodiment, based on the differences between the trial mold defect records and mold life indicators in the first verification data and the preset requirements, a first optimization objective is generated using a preset mold optimization model. The first optimization objective primarily addresses the problems and deficiencies of the mold before optimization, proposing improvement directions and goals. Based on the differences between the trial mold defect records and mold life indicators in the second verification data and the preset requirements, a second optimization objective is generated using the preset mold optimization model. The second optimization objective primarily addresses the performance of the optimized mold, further proposing optimization directions and goals.

[0098] In this embodiment, the first and second optimization objectives are fused, taking into account the optimization directions and requirements of both, to obtain the final optimization objective. The fusion method can employ techniques such as weighted averaging and multi-objective optimization to ensure that the final optimization objective considers both the improvement of the problem before optimization and the performance enhancement after optimization.

[0099] In this embodiment, the final optimization objective is applied to the mold optimization. Secondary optimization is performed by adjusting the mold's process parameters and structural design. For example, process parameters such as injection temperature and holding pressure are adjusted, or the mold's geometry, dimensions, and other structural designs are modified to meet the requirements of the final optimization objective. After secondary optimization, the final optimized precision mold design scheme is obtained.

[0100] Understandably, when the first error between the first verification data and the second verification data is less than the preset range, it indicates that the difference between the trial mold defect records and mold life indicators between the current mold and the optimized mold is very small, meaning that the performance gap between the two is also small. This results in a small difference between the process parameters and structural design data between the current mold and the optimized mold. Therefore, during secondary optimization, the first optimization target corresponding to the first verification data and the second optimization target corresponding to the second verification data can be fused together. This ensures that the optimization target comes from both the current mold and the optimized mold, avoiding inaccurate optimization due to data from only one dimension. The final optimization target is then obtained, and the optimized mold is further optimized based on the final optimization target to obtain the final optimized precision mold.

[0101] As a preferred option, it also includes:

[0102] When the first error between the first verification data and the second verification data is not less than a preset range, calculate the second error between the trial mold defect record and mold life index in the first verification data and the preset requirement, and calculate the third error between the trial mold defect record and mold life index in the second verification data and the preset requirement.

[0103] When the second error is less than the third error, based on the difference between the trial mold defect record and mold life index in the first verification data and the preset requirements, a first optimization target is generated through a preset mold optimization model, and the target mold is optimized a second time based on the first optimization target to obtain the final optimized precision mold.

[0104] When the third error is less than the second error, based on the difference between the trial mold defect record and mold life index in the second verification data and the preset requirements, a second optimization target is generated through the preset mold optimization model, and the optimized mold is further optimized based on the second optimization target to obtain the final optimized precision mold.

[0105] In this embodiment, when the first error between the first verification data and the second verification data is not less than a preset range, the second error between the trial mold defect records and mold life indicators in the first verification data and the preset requirements, and the third error between the trial mold defect records and mold life indicators in the second verification data and the preset requirements are calculated respectively. Error calculation can employ methods such as mean squared error (MSE) and mean absolute error (MAE), with the specific choice determined according to actual needs.

[0106] In this embodiment, the magnitudes of the second error and the third error are compared to determine which set of verification data is closer to the preset requirement. When the second error is smaller than the third error, based on the difference between the trial mold defect records and mold life indicators in the first verification data and the preset requirement, a first optimization target is generated through a preset mold optimization model. The target mold is then further optimized based on the first optimization target to obtain the final optimized precision mold.

[0107] Furthermore, when the third error is less than the second error, based on the difference between the trial mold defect records and mold life indicators in the second verification data and the preset requirements, a second optimization target is generated through a preset mold optimization model. The optimized mold is then further optimized based on the second optimization target to obtain the final optimized precision mold.

[0108] Understandably, if the first error between the first and second verification data exceeds the preset range, it indicates a significant difference in the trial mold defect records and mold life indicators between the current mold and the optimized mold. This means that the process parameters and structural design data of the current mold underwent substantial modifications during the first optimization process. Therefore, it is necessary to further determine the differences between the current mold and the optimized mold and the preset requirements, and then select the item with the smaller error as the target for secondary optimization. The errors between the trial mold defect records and mold life indicators in the first verification data and the preset requirements are calculated. Finally, through the preset mold optimization model, the corresponding optimization targets are generated to achieve secondary optimization of the target mold or the optimized mold. This avoids optimization deviations caused by newly designed molds differing from historical mold data in the database. Furthermore, by using the error between the design and the preset requirements to determine the final optimization target, it ensures that the secondary optimization is directly guided by the preset requirement target results, ensuring that the final optimized precision mold meets the preset requirements and guaranteeing the accuracy and efficiency of precision mold design optimization.

[0109] Implementing the above embodiments has the following effects:

[0110] The technical solution of this invention extracts key historical data by acquiring historical mold data from a mold case database, and then filters out historical molds corresponding to target material data and material characteristic data by acquiring current mold data. Based on these historical molds, optimization is performed to obtain an optimized mold. The optimized mold is then subjected to simulation testing to obtain second verification data, which is used to determine the error between the optimized mold data and the preset requirements. Finally, the optimization target is determined. This avoids optimizing a completely new current mold solely based on the data from the optimized mold. It also allows for optimization by combining historical mold data when designing a non-new current mold, thereby performing secondary optimization of the current mold or the optimized mold based on the optimization target to obtain a final optimized precision mold. This reduces the complexity of optimizing a completely new mold design and improves design optimization efficiency. Example 2

[0111] Please see Figure 2 This invention provides a precision mold design optimization system based on data mining, comprising:

[0112] The history module 201 is used to acquire historical mold data from the mold case database and parse the unstructured data in the historical mold data to extract key historical data. Each historical mold corresponds to one key historical data, which includes: material characteristic data, process parameters, structural design data, and verification data.

[0113] The parsing module 202 is used to acquire the current mold data, parse the current mold data to obtain target material data, target process parameters and target structure data, and perform simulation tests on the current mold to obtain the first verification data;

[0114] The optimization module 203 is used to filter out historical molds corresponding to target material data and material characteristic data from key historical data, and optimize the target process parameters and target structural data based on the process parameters and structural design data in the historical molds, thereby obtaining an optimized mold;

[0115] The secondary module 204 is used to perform simulation tests on the optimized mold to obtain second verification data, and determine the optimization target based on the errors between the first verification data and the second verification data and the preset requirements, and perform secondary optimization on the current mold or the optimized mold based on the optimization target to obtain the final optimized precision mold.

[0116] As a preferred embodiment, the step of acquiring historical mold data from the mold case database and parsing the unstructured data in the historical mold data to extract key historical data specifically includes:

[0117] Retrieve historical molds and their corresponding historical mold data from the mold case database;

[0118] The historical mold data corresponding to each historical mold is organized and the unstructured data in the historical mold data is integrated.

[0119] Deep semantic analysis is performed on the unstructured data in the historical mold data to extract material feature data, process parameters, structural design data and verification data from each historical mold.

[0120] As a preferred embodiment, the step of acquiring the current mold data, parsing the current mold data to obtain target material data, target process parameters, and target structure data, and performing simulation tests on the current mold data to obtain first verification data specifically includes:

[0121] Acquire the current mold data, organize the current mold data, and integrate the unstructured data in the current mold data;

[0122] Deep semantic parsing is performed on the unstructured data in the current mold data to extract the target material data, target process parameters, and target structure data in the current mold;

[0123] The current mold is simulated and tested under preset simulation test conditions, and the test data of the current mold is collected during the simulation test as the first verification data of the current mold.

[0124] As a preferred embodiment, the step of selecting historical molds corresponding to target material data and material characteristic data from key historical data, and optimizing the target process parameters and target structural data based on the process parameters and structural design data in the historical molds to obtain an optimized mold, specifically includes:

[0125] Based on the target material data, the material feature data in the key historical data are compared to screen out the historical molds that correspond to the target material data and the material feature data.

[0126] Based on the process parameters and structural design data in the historical molds, generate mold constraint conditions;

[0127] Based on the first verification data, determine the optimization weight of the target mold;

[0128] Based on the mold constraints and optimization weights, an optimization parameter combination is generated using a preset LSTM prediction optimization model.

[0129] The target process parameters and target structural data are optimized according to the optimized parameter combination, and an optimized mold is generated based on the optimized target process parameters and target structural data.

[0130] As a preferred embodiment, the method for constructing the preset LSTM prediction optimization model includes:

[0131] Construct the structure of the initial LSTM model;

[0132] The historical mold data in the mold case database is preprocessed to obtain training data;

[0133] Design an optimization algorithm and construct a loss function based on the verification data in the historical mold data;

[0134] Based on the optimization algorithm, combined with the loss function, and using the training data, the initial LSTM model is iteratively trained.

[0135] After reaching the preset number of iterations, the preset LSTM prediction optimization model is obtained.

[0136] As a preferred embodiment, the process of performing simulation tests on the optimized mold to obtain second verification data, determining the optimization target based on the errors between the first and second verification data and the preset requirements, and performing secondary optimization on the current mold or the optimized mold based on the optimization target to obtain the final optimized precision mold, specifically includes:

[0137] The optimized mold is simulated and tested under preset simulation test conditions, and the test data of the optimized mold is collected during the simulation test as the second verification data; wherein, both the first verification data and the second verification data include the mold trial defect record and the mold life index;

[0138] Determine the first error between the first verification data and the second verification data;

[0139] When the first error between the first verification data and the second verification data is less than a preset range, a first optimization target is generated based on the difference between the trial mold defect records and mold life indicators in the first verification data and the preset requirements, through a preset mold optimization model.

[0140] Based on the difference between the trial mold defect records and mold life indicators in the second verification data and the preset requirements, a second optimization target is generated through a preset mold optimization model;

[0141] The first optimization objective and the second optimization objective are fused to obtain the final optimization objective, and the optimized mold is further optimized based on the final optimization objective to obtain the final optimized precision mold.

[0142] As a preferred option, it also includes:

[0143] When the first error between the first verification data and the second verification data is not less than a preset range, calculate the second error between the trial mold defect record and mold life index in the first verification data and the preset requirement, and calculate the third error between the trial mold defect record and mold life index in the second verification data and the preset requirement.

[0144] When the second error is less than the third error, based on the difference between the trial mold defect record and mold life index in the first verification data and the preset requirements, a first optimization target is generated through a preset mold optimization model, and the target mold is optimized a second time based on the first optimization target to obtain the final optimized precision mold.

[0145] When the third error is less than the second error, based on the difference between the trial mold defect record and mold life index in the second verification data and the preset requirements, a second optimization target is generated through the preset mold optimization model, and the optimized mold is further optimized based on the second optimization target to obtain the final optimized precision mold.

[0146] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the device described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0147] Implementing the above embodiments has the following effects:

[0148] The technical solution of this invention extracts key historical data by acquiring historical mold data from a mold case database, and then filters out historical molds corresponding to target material data and material characteristic data by acquiring current mold data. Based on these historical molds, optimization is performed to obtain an optimized mold. The optimized mold is then subjected to simulation testing to obtain second verification data, which is used to determine the error between the optimized mold data and the preset requirements. Finally, the optimization target is determined. This avoids optimizing a completely new current mold solely based on the data from the optimized mold. It also allows for optimization by combining historical mold data when designing a non-new current mold, thereby performing secondary optimization of the current mold or the optimized mold based on the optimization target to obtain a final optimized precision mold. This reduces the complexity of optimizing a completely new mold design and improves design optimization efficiency. Example 3

[0149] Accordingly, the present invention also provides a terminal device, comprising: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the precision mold design optimization method based on data mining as described in any of the above embodiments.

[0150] The terminal device in this embodiment includes a processor, a memory, and a computer program and computer instructions stored in the memory and executable on the processor. When the processor executes the computer program, it implements the various steps described in Embodiment 1 above, for example... Figure 1 The steps S101 to S104 are shown. Alternatively, when the processor executes the computer program, it implements the functions of each module / unit in the above-described device embodiment, such as optimization module 203.

[0151] For example, the computer program can be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the terminal device. For example, optimization module 203 is used to filter historical molds corresponding to target material data and material characteristic data from key historical data, and optimize the target process parameters and target structural data based on the process parameters and structural design data in the historical molds, thereby obtaining an optimized mold.

[0152] The terminal device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the schematic diagram is merely an example of a terminal device and does not constitute a limitation on the terminal device. It may include more or fewer components than illustrated, or combine certain components, or different components. For example, the terminal device may also include input / output devices, network access devices, buses, etc.

[0153] The processor can be a Central Processing Unit (CPU), or 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. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the terminal device, connecting all parts of the terminal device via various interfaces and lines.

[0154] The memory can be used to store the computer programs and / or modules. The processor implements various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and by calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, applications required for at least one function, etc.; the data storage area may store data created based on the use of the mobile terminal, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital card (SD card), flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0155] Wherein, if the modules / units integrated in the terminal device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by a processor, it can implement the steps of the various method embodiments described above. Wherein, the computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content contained in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals. Example 4

[0156] Accordingly, the present invention also provides a computer-readable storage medium comprising a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the data mining-based precision mold design optimization method as described in any of the above embodiments.

[0157] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.

Claims

1. A precision mold design optimization method based on data mining, characterized in that, include: Historical mold data is obtained from the mold case database, and the unstructured data in the historical mold data is parsed to extract key historical data. Each historical mold corresponds to one key historical data, which includes: material characteristic data, process parameters, and structural design data. Acquire the current mold data and parse the current mold data to obtain target material data, target process parameters and target structure data. Perform simulation test on the current mold based on the parsed data to obtain the first verification data. Historical molds whose material characteristic data corresponds to the target material data of the current mold are selected from key historical data. Based on the process parameters and structural design data in the historical molds, the target process parameters and target structural data are optimized to obtain an optimized mold. The optimized mold is simulated and tested to obtain second verification data. Based on the errors between the first and second verification data and the preset requirements, the optimization target is determined. The current mold or the optimized mold is then optimized a second time based on the optimization target to obtain the final optimized precision mold.

2. The precision mold design optimization method based on data mining as described in claim 1, characterized in that, The process of acquiring historical mold data from the mold case database and parsing the unstructured data in the historical mold data to extract key historical data specifically includes: Retrieve historical molds and their corresponding historical mold data from the mold case database; The historical mold data corresponding to each historical mold is organized and the unstructured data in the historical mold data is integrated. Deep semantic analysis is performed on the unstructured data in the historical mold data to extract material feature data, process parameters, structural design data and verification data from each historical mold.

3. The precision mold design optimization method based on data mining as described in claim 2, characterized in that, The process of acquiring current mold data, parsing the current mold data to obtain target material data, target process parameters, and target structure data, and performing simulation tests on the current mold data to obtain first verification data specifically includes: Acquire the current mold data, organize the current mold data, and integrate the unstructured data in the current mold data; Deep semantic parsing is performed on the unstructured data in the current mold data to extract the target material data, target process parameters, and target structure data in the current mold; The current mold is simulated and tested under preset simulation test conditions, and the test data of the current mold is collected during the simulation test as the first verification data of the current mold.

4. The precision mold design optimization method based on data mining as described in claim 3, characterized in that, The process of selecting historical molds corresponding to target material data and material characteristic data from key historical data, and optimizing the target process parameters and target structural data based on the process parameters and structural design data in these historical molds to obtain optimized molds, specifically includes: Based on the target material data, the material feature data in the key historical data are compared to screen out the historical molds that correspond to the target material data and the material feature data. Based on the process parameters and structural design data in the historical molds, generate mold constraint conditions; Based on the first verification data, determine the optimization weight of the target mold; Based on the mold constraints and optimization weights, an optimization parameter combination is generated using a preset LSTM prediction optimization model. The target process parameters and target structural data are optimized according to the optimized parameter combination, and an optimized mold is generated based on the optimized target process parameters and target structural data.

5. The precision mold design optimization method based on data mining as described in claim 4, characterized in that, The method for constructing the preset LSTM prediction optimization model includes: Construct the structure of the initial LSTM model; The historical mold data in the mold case database is preprocessed to obtain training data; Design an optimization algorithm and construct a loss function based on the verification data in the historical mold data; Based on the optimization algorithm, combined with the loss function, and using the training data, the initial LSTM model is iteratively trained. After reaching the preset number of iterations, the preset LSTM prediction optimization model is obtained.

6. The precision mold design optimization method based on data mining as described in claim 1, characterized in that, The process involves performing simulation tests on the optimized mold to obtain second verification data, determining an optimization target based on the errors between the first and second verification data and preset requirements, and then performing secondary optimization on the current mold or the optimized mold based on the optimization target to obtain the final optimized precision mold. Specifically, this includes: The optimized mold is simulated and tested under preset simulation test conditions, and the test data of the optimized mold is collected during the simulation test as the second verification data; wherein, both the first verification data and the second verification data include the mold trial defect record and the mold life index; Determine the first error between the first verification data and the second verification data; When the first error between the first verification data and the second verification data is less than a preset range, a first optimization target is generated based on the difference between the trial mold defect records and mold life indicators in the first verification data and the preset requirements, through a preset mold optimization model. Based on the difference between the trial mold defect records and mold life indicators in the second verification data and the preset requirements, a second optimization target is generated through a preset mold optimization model; The first optimization objective and the second optimization objective are fused to obtain the final optimization objective, and the optimized mold is further optimized based on the final optimization objective to obtain the final optimized precision mold.

7. The precision mold design optimization method based on data mining as described in claim 6, characterized in that, Also includes: When the first error between the first verification data and the second verification data is not less than a preset range, calculate the second error between the trial mold defect record and mold life index in the first verification data and the preset requirement, and calculate the third error between the trial mold defect record and mold life index in the second verification data and the preset requirement. When the second error is less than the third error, based on the difference between the trial mold defect record and mold life index in the first verification data and the preset requirements, a first optimization target is generated through a preset mold optimization model, and the target mold is optimized a second time based on the first optimization target to obtain the final optimized precision mold. When the third error is less than the second error, based on the difference between the trial mold defect record and mold life index in the second verification data and the preset requirements, a second optimization target is generated through the preset mold optimization model, and the optimized mold is further optimized based on the second optimization target to obtain the final optimized precision mold.

8. A precision mold design optimization system based on data mining, characterized in that, include: The history module is used to acquire historical mold data from the mold case database and parse the unstructured data in the historical mold data to extract key historical data. Each historical mold corresponds to one key historical data, which includes: material characteristic data, process parameters, structural design data, and verification data. The parsing module is used to acquire the current mold data, parse the current mold data to obtain target material data, target process parameters and target structure data, and perform simulation tests on the current mold to obtain the first verification data; The optimization module is used to filter out historical molds corresponding to target material data and material characteristic data from key historical data, and optimize the target process parameters and target structural data based on the process parameters and structural design data in the historical molds, thereby obtaining an optimized mold. The secondary module is used to perform simulation tests on the optimized mold to obtain second verification data, and to determine the optimization target based on the errors between the first verification data and the second verification data and the preset requirements, and to perform secondary optimization on the current mold or the optimized mold based on the optimization target to obtain the final optimized precision mold.

9. A terminal device, characterized in that, The system includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the data mining-based precision mold design optimization method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device on which the computer-readable storage medium is located to perform the data mining-based precision mold design optimization method as described in any one of claims 1 to 7.

Images