Process parameter determination method and device, electronic equipment and storage medium
By conducting bench performance simulation tests and building predictive models for die-cast parts, the problem of not being able to quickly determine the optimal process parameters during the die-casting process was solved, thereby improving the performance and quality of die-cast parts and reducing production costs and energy consumption.
Patent Information
- Application Number
- CN202411148155.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-20
- Publication Date
- 2026-03-03
AI Technical Summary
The inability to quickly determine the optimal process parameters during die casting makes quality assurance difficult.
By conducting bench performance simulation tests on die-cast parts, a target bench performance prediction model is constructed. This model is then used to predict the performance of parameters in the process parameter space in order to determine the optimal process parameters.
It improves the performance and quality of die-cast parts, reduces production costs and energy consumption, reduces scrap rates, and promotes sustainable development.
Smart Images
Figure CN121598728A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of machine learning technology, and in particular to a method, apparatus, electronic device, and storage medium for determining process parameters. Background Technology
[0002] Given a fixed die-casting machine and materials, the process is the prerequisite for ensuring the quality of large-scale die casting. However, there are hundreds of process parameters, making it the preferred method to ensure quality through quality monitoring and adjustment of these parameters. But with so many process parameters in the die-casting process, it is difficult to quickly determine the optimal parameters. Summary of the Invention
[0003] This disclosure provides a method, apparatus, electronic device, computer-readable storage medium, and computer program product for determining process parameters, to at least solve the problem in related technologies of the inability to quickly determine the optimal process parameters from a large number of process parameters. The technical solution of this disclosure is as follows:
[0004] According to a first aspect of the present disclosure, a method for determining process parameters is provided, comprising: performing bench performance simulation tests on a first die casting to obtain bench performance simulation data of the first die casting; obtaining a target bench performance prediction model based on the die casting process parameters of the first die casting and the bench performance simulation data of the first die casting; and inputting process parameters in the process parameter space into the target bench performance prediction model to determine the optimal process parameters corresponding to the die casting.
[0005] In one embodiment of this disclosure, the step of performing bench performance simulation testing on the first die casting to obtain bench performance simulation data of the first die casting includes: inputting a 3D model of the first die casting into a target simulation test model to obtain bench performance simulation data of the first die casting.
[0006] In one embodiment of this disclosure, the training process of the target simulation test model includes: performing bench performance testing on a second die casting to obtain bench performance test data of the second die casting; acquiring scanning data of the second die casting, the scanning data including at least dimensional data and internal defect data of the second die casting, and generating a 3D model of the second die casting based on the scanning data; constructing a simulation test model; inputting the 3D model of the second die casting into the simulation test model to simulate the second die casting and obtain bench performance simulation data of the second die casting; correcting the simulation test model according to the bench performance simulation data and bench performance test data of the second die casting and continuing the simulation until the correction termination condition is met to obtain the target simulation test model.
[0007] In one embodiment of this disclosure, the step of inputting the 3D model of the second die casting into the simulation test model to simulate the second die casting and obtain bench performance simulation data of the second die casting includes: setting bench test boundary conditions for the 3D model of the second die casting, inputting the 3D model and the bench test boundary conditions into the simulation test model, performing bench performance simulation test on the 3D model of the second die casting, and obtaining bench performance simulation data of the second die casting.
[0008] In one embodiment of this disclosure, the step of correcting the simulation test model based on the bench performance simulation data and bench performance test data of the second die casting further includes: determining whether to optimize the simulation test model based on the bench performance simulation data and bench performance test data of the second die casting; and correcting the simulation test model based on the deviation information between the bench performance simulation data and bench performance test data of the second die casting when it is determined that the simulation test model needs to be optimized.
[0009] In one embodiment of this disclosure, the method further includes: determining the number of die-cast parts whose deviation information is within a set range; and stopping the correction of the simulation test model when the number of die-cast parts reaches the set number, thereby obtaining the target simulation test model.
[0010] In one embodiment of this disclosure, the method further includes: adjusting the boundary conditions of the bench test in response to determining that the simulation test model needs to be optimized.
[0011] In one embodiment of this disclosure, before inputting the 3D model of the first die casting into the target simulation test model to obtain the bench performance simulation data of the first die casting, the method further includes: acquiring scanning data of the first die casting, wherein the scanning data includes at least the dimensional data and internal defect data of the first die casting; and generating a 3D model of the first die casting based on the scanning data of the first die casting.
[0012] In one embodiment of this disclosure, obtaining a target bench performance prediction model based on the die-casting process parameters of the first die-casting part and the bench performance simulation data of the first die-casting part includes: constructing a bench performance prediction model; inputting the die-casting process parameters of the first die-casting part into the bench performance prediction model to obtain bench performance prediction data of the first die-casting part; and adjusting the bench performance prediction model based on the bench performance prediction data and the bench performance simulation data to obtain the target bench performance prediction model.
[0013] In one embodiment of this disclosure, the step of inputting process parameters from the process parameter space into the target bench performance prediction model to determine the optimal process parameters corresponding to the die casting includes: meshing the process parameter space to obtain multiple meshes; inputting each mesh into the target bench performance prediction model to output bench performance prediction data corresponding to each mesh; and determining the optimal process parameters from the process parameter space based on the bench performance prediction data of the meshes.
[0014] In one embodiment of this disclosure, determining the optimal process parameters from the process parameter space based on the bench performance prediction data of the grid includes: comparing the bench performance prediction data of each grid to obtain the optimal bench performance prediction data; determining the target grid corresponding to the optimal bench performance prediction data; and determining the process parameters within the target grid as the optimal process parameters.
[0015] In one embodiment of this disclosure, after finding the optimal process parameters corresponding to the die casting from the process parameter space, the method further includes: configuring the parameters of the die casting equipment based on the optimal process parameters, and performing the die casting process based on the optimal process parameters to obtain the target die casting.
[0016] According to a second aspect of the present disclosure, a process parameter determination apparatus is provided, comprising: a simulation module for performing bench performance simulation tests on a first die casting to obtain bench performance simulation data of the first die casting; a first determination module for obtaining a target bench performance prediction model based on the die casting process parameters of the first die casting and the bench performance simulation data of the first die casting; and a second determination module for inputting process parameters in a process parameter space into the target bench performance prediction model to determine the optimal process parameters corresponding to the die casting.
[0017] In one embodiment of this disclosure, the simulation module is further configured to: input the 3D model of the first die casting into the target simulation test model to obtain bench performance simulation data of the first die casting.
[0018] In one embodiment of this disclosure, the simulation module is further configured to: perform bench performance testing on the second die casting to obtain bench performance test data of the second die casting; acquire scanning data of the second die casting, the scanning data including at least dimensional data and internal defect data of the second die casting, and generate a 3D model of the second die casting based on the scanning data; construct a simulation test model; input the 3D model of the second die casting into the simulation test model to simulate the second die casting and obtain bench performance simulation data of the second die casting; and correct the simulation test model according to the bench performance simulation data and bench performance test data of the second die casting and continue simulation until the correction termination condition is met to obtain the target simulation test model.
[0019] In one embodiment of this disclosure, the simulation module is further configured to: set bench test boundary conditions for the 3D model of the second die casting, input the 3D model and the bench test boundary conditions into the simulation test model, perform bench performance simulation test on the 3D model of the second die casting, and obtain bench performance simulation data of the second die casting.
[0020] In one embodiment of this disclosure, the simulation module is further configured to: determine whether to optimize the simulation test model based on the bench performance simulation data and the bench performance test data of the second die casting; and, in response to the determination that the simulation test model needs to be optimized, correct the simulation test model based on the deviation information between the bench performance simulation data and the bench performance test data of the second die casting.
[0021] In one embodiment of this disclosure, the simulation module is further configured to: determine the number of die-cast parts whose deviation information is within a set range; and, in response to the number of die-cast parts reaching the set number, determine that the correction termination condition is met and then stop correcting the simulation test model to obtain the target simulation test model.
[0022] In one embodiment of this disclosure, the simulation module is further configured to: adjust the boundary conditions of the bench test in response to a determination that the simulation test model needs to be optimized.
[0023] In one embodiment of this disclosure, the simulation module is further configured to: acquire scanning data of the first die casting, the scanning data including at least dimensional data and internal defect data of the first die casting; and generate a 3D model of the first die casting based on the scanning data of the first die casting.
[0024] In one embodiment of this disclosure, the first determining module is further configured to: construct a bench performance prediction model; input the die-casting process parameters of the first die-casting part into the bench performance prediction model to obtain bench performance prediction data of the first die-casting part; and adjust the bench performance prediction model based on the bench performance prediction data and the bench performance simulation data to obtain the target bench performance prediction model.
[0025] In one embodiment of this disclosure, the second determining module is further configured to: grid the process parameter space to obtain multiple grids; input each grid into the target bench performance prediction model to output bench performance prediction data corresponding to each grid; and determine the optimal process parameters from the process parameter space based on the bench performance prediction data of the grids.
[0026] In one embodiment of this disclosure, the second determining module is further configured to: compare the bench performance prediction data of each grid to obtain the optimal bench performance prediction data; determine the target grid corresponding to the optimal bench performance prediction data; and determine the process parameters within the target grid as the optimal process parameters.
[0027] In one embodiment of this disclosure, the second determining module is further configured to: configure the parameters of the die-casting equipment based on the optimal process parameters, and perform the die-casting process based on the optimal process parameters to obtain the target die-casting part.
[0028] According to a third aspect of the present disclosure, an electronic device is provided, including a processor; a memory for storing processor-executable instructions; wherein the processor is configured to implement the steps of the method described in the first aspect of the present disclosure.
[0029] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided that stores computer program instructions thereon, which, when executed by a processor, implement the steps of the method described in the first aspect of the present disclosure.
[0030] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program, characterized in that, when executed by a processor of an electronic device, the computer program implements the steps of the method as described in the first aspect of the present disclosure.
[0031] The technical solutions provided by the embodiments of this disclosure offer at least the following beneficial effects: By conducting bench performance simulation tests on a first die-casting part, bench performance simulation data of the first die-casting part is obtained. Based on the bench performance simulation data of the first die-casting part and the die-casting process parameters of the first die-casting part, a target bench performance prediction model is determined. Furthermore, the target bench performance prediction model can be used to predict the performance of process parameters in the process parameter space to determine the optimal process parameters corresponding to the die-casting part. This allows for the acquisition of optimal process parameters that can improve the performance and quality of the die-casting part. The optimal process parameters can then be used to manufacture the die-casting part, thereby improving the overall performance and reliability of the die-casting part. Obtaining the optimal process parameters can reduce the production cost and energy consumption of the die-casting part, reduce the scrap rate, and promote sustainable development.
[0032] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description
[0033] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.
[0034] Figure 1 This is a flowchart illustrating a method for determining process parameters according to an exemplary embodiment.
[0035] Figure 2 This is a flowchart illustrating a method for determining process parameters according to another exemplary embodiment.
[0036] Figure 3 This is a flowchart illustrating the training process of a target simulation test model in a method for determining process parameters according to an exemplary embodiment.
[0037] Figure 4 This is a flowchart illustrating a method for determining process parameters according to another exemplary embodiment.
[0038] Figure 5 This is a flowchart illustrating a method for determining process parameters according to another exemplary embodiment.
[0039] Figure 6 This is a flowchart illustrating the determination of optimal process parameters according to an exemplary embodiment.
[0040] Figure 7 This is a block diagram illustrating a process parameter determination apparatus according to an exemplary embodiment.
[0041] Figure 8 This is a block diagram illustrating an electronic device according to an exemplary embodiment. Detailed Implementation
[0042] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.
[0043] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.
[0044] The acquisition, storage, use, and processing of data in this disclosed technical solution all comply with the relevant laws and regulations.
[0045] The method and apparatus for determining process parameters according to embodiments of the present disclosure are described below with reference to the accompanying drawings.
[0046] Figure 1 This is a flowchart illustrating a method for determining process parameters according to an exemplary embodiment, such as... Figure 1 As shown, the method for determining process parameters according to an embodiment of this disclosure includes the following steps:
[0047] S101, Perform bench performance simulation test on the first die casting to obtain bench performance simulation data of the first die casting.
[0048] It should be noted that the execution subject of the process parameter determination method in this embodiment is an electronic device, such as a mobile phone, laptop, desktop computer, vehicle terminal, smart home appliance, wearable device, etc. Wearable devices may include wrist-worn devices (such as smartwatches and smart bracelets), head-worn devices, foot-worn devices, etc. The process parameter determination method in this embodiment can be executed by the process parameter determination device, which can be configured in any electronic device to execute the process parameter determination method.
[0049] In some implementations, the first die-casting can be simulated based on a pre-trained target simulation test model to obtain bench performance simulation data of the first die-casting. Alternatively, simulation test software, simulation test tools, etc., can also be used to simulate the first die-casting.
[0050] In some implementations, sample bench performance test data of multiple sample die-cast parts and sample scanning data of the sample die-cast parts can be obtained in advance, and then a simulation test model can be used to simulate the sample scanning data to obtain bench performance simulation data.
[0051] Furthermore, the simulation test model is corrected and trained again based on the sample bench performance test data and bench performance simulation data to obtain the target simulation test model.
[0052] Optionally, a target simulation test model can be used to simulate the three-dimensional (3D) model of the first die casting to obtain bench performance simulation data of the first die casting. That is, by inputting the 3D model of the first die casting into the target simulation test model, the target simulation test model performs bench performance simulation tests based on the 3D model of the first die casting to obtain bench performance simulation data of the first die casting. Here, the first die casting refers to the die casting used to train the bench performance prediction model.
[0053] Optionally, a 3D model can be constructed based on the dimensional data and defect data of the first die casting.
[0054] Optionally, the bench performance simulation data includes, but is not limited to: tensile strength, compressive strength, yield strength, toughness, compressive strength, etc.
[0055] S102, Based on the die-casting process parameters of the first die-casting part and the bench performance simulation data of the first die-casting part, a target bench performance prediction model is obtained.
[0056] In some implementations, a bench performance prediction model can be pre-built, and the die-casting process parameters of the first die-casting part can be obtained. By inputting the die-casting process parameters into the bench performance prediction model, the model can predict the bench performance of the die-casting process parameters and output the bench performance prediction data. Optionally, the bench performance prediction data includes, but is not limited to: tensile strength, compressive strength, yield strength, toughness, compressive strength, etc.
[0057] Optionally, a test bench performance prediction model can be constructed based on a neural network model. For example, the target of the model prediction can be predetermined as test bench performance data such as yield strength and tensile strength. Then, the network structure of the model can be defined as an input layer, a feature extraction layer, a performance prediction layer, and an output layer. Based on the network structure and the prediction target, a test bench performance prediction model can be constructed.
[0058] Furthermore, based on the bench performance simulation data and bench performance prediction data of the first die-cast part, it is determined whether the bench performance prediction model needs to be adjusted. Optionally, by obtaining the error value between the bench performance simulation data and the bench performance prediction data, if the error value is greater than the error threshold, it is determined that the bench performance prediction model needs to be adjusted.
[0059] Optionally, a loss function can be determined based on bench performance simulation data and bench performance prediction data, and the parameters of the bench performance prediction model can be adjusted using the loss function. The adjusted bench performance prediction model can then be used to continue predicting the bench performance of the die casting process parameters until it is determined that no further adjustment to the bench performance prediction model is needed, thus obtaining the target bench performance prediction model.
[0060] In other words, the bench performance prediction model can extract features from the die casting process parameters, predict the bench performance prediction data of the first die casting based on the features of the die casting process parameters, determine the loss function based on the bench performance simulation data and the bench performance prediction data, and adjust the bench performance prediction model based on the loss function until the training ends and the target bench performance prediction model is obtained.
[0061] S103, input the process parameters in the process parameter space into the target bench performance prediction model to determine the optimal process parameters corresponding to the die casting.
[0062] In some implementations, the process parameter space can be pre-gridized to obtain gridded process parameters, meaning that each grid contains a set of process parameters. By inputting the grid into the target bench performance prediction model, the target bench performance prediction model predicts the bench performance of the process parameters in each grid and outputs the bench performance prediction data.
[0063] Furthermore, by comparing the magnitudes of the predicted test performance data, the optimal test performance prediction data can be determined. For example, the data with the largest predicted test performance data can be taken as the optimal test performance prediction data. Then, the grid corresponding to the optimal test performance prediction data is determined, and the optimal process parameters for the die casting are determined from this grid.
[0064] The method for determining process parameters provided in this disclosure involves conducting bench performance simulation tests on a first die-casting part to obtain bench performance simulation data. Based on this data and the die-casting process parameters, a target bench performance prediction model is determined. Furthermore, the target bench performance prediction model can be used to predict the performance of process parameters in the process parameter space to determine the optimal process parameters corresponding to the die-casting part. This allows for the acquisition of optimal process parameters that improve the performance and quality of the die-casting part, enabling its manufacture and thus enhancing its overall performance and reliability. Obtaining the optimal process parameters reduces production costs and energy consumption, decreases scrap rates, and promotes sustainable development.
[0065] Figure 2 This is a flowchart illustrating a method for determining process parameters according to an exemplary embodiment, such as... Figure 2 As shown, the method for determining process parameters according to an embodiment of this disclosure includes the following steps:
[0066] S201. Based on the bench performance test data and scanning data of the second die casting, determine the target simulation test model. The scanning data includes at least the dimensional data and internal defect data of the second die casting.
[0067] In some implementations, a simulation test model can be constructed and trained based on the bench performance test data and scanning data of the second die-cast part until the training termination condition is met, thus obtaining the target simulation test model. The second die-cast part is used to train the simulation test model, while the first die-cast part in the above embodiment is used to train the bench performance prediction model. It should be noted that both the first and second die-cast parts are sample die-cast parts and may or may not be identical.
[0068] Understandably, the simulation test model outputs bench performance test data related to mechanics. This can be achieved by collecting mechanical data and using simulation tools to establish a mathematical model describing the mechanics, which can then serve as the simulation test model. This model can be a theoretical model based on physics or an empirical model based on experimental data.
[0069] Optionally, the mapping relationship between the 3D model of the second die casting and the mechanical data can be determined based on the mechanical data related to the bench performance data, and then a simulation test model can be established based on the mapping relationship.
[0070] Optionally, bench performance testing can be performed on the second die casting to obtain bench performance test data, and X-ray scanning can be performed on the second die casting to obtain scan data. The scan data includes at least the dimensional data and internal defect data of the second die casting. For example, X-ray scanning of the second die casting can be performed using an X-ray machine to obtain the scan data.
[0071] Optionally, the second die casting can be simulated based on the simulation test model and scanning data to obtain bench performance simulation data of the second die casting, and the simulation test model can be trained based on the bench performance simulation data and bench performance test data.
[0072] Optionally, the training termination condition can be that the number of training sessions reaches a set value, or that the deviation between the bench performance simulation data and the bench performance test data is less than a set threshold.
[0073] S202, input the 3D model of the first die casting into the target simulation test model to obtain the bench performance simulation data of the first die casting.
[0074] In some implementations, a 3D model of the first die casting can be constructed and input into a target simulation test model. The target simulation test model can then simulate the bench performance of the first die casting and output the bench performance simulation data of the first die casting.
[0075] Optionally, a 3D model of the first die casting can be generated by acquiring scanning data of the first die casting, the scanning data including at least the dimensional data and internal defect data of the first die casting.
[0076] In some implementations, the scanning data of the first die casting can be obtained by performing X-ray scanning on the first die casting. For example, the scanning data of the second die casting can be obtained by X-ray scanning of the first die casting using an X-ray machine. Furthermore, based on the scanning data of the first die casting, a 3D reconstruction of the first die casting can be performed to obtain a 3D model of the first die casting.
[0077] S203, Construct a bench performance prediction model.
[0078] Optionally, a test bench performance prediction model can be constructed based on a neural network model. For example, the target of the model prediction can be predetermined as test bench performance data such as yield strength and tensile strength. Then, the network structure of the model can be defined as an input layer, a feature extraction layer, a performance prediction layer, and an output layer. Based on the network structure and the prediction target, a test bench performance prediction model can be constructed.
[0079] S204. Input the die-casting process parameters of the first die-casting part into the bench performance prediction model to obtain the bench performance prediction data of the first die-casting part.
[0080] In some implementations, the die-casting process parameters of the first die-casting part are input into the bench performance prediction model. The feature extraction layer of the bench performance prediction model extracts features from the die-casting process parameters to obtain the feature data of the die-casting process parameters.
[0081] Furthermore, the performance prediction layer of the bench performance prediction model predicts bench performance data such as yield strength and tensile strength of the first die casting based on feature data, and uses these data as bench performance prediction data.
[0082] S205. Based on the test bench performance prediction data and test bench performance simulation data, the test bench performance prediction model is adjusted to obtain the target test bench performance prediction model.
[0083] Optionally, a loss function can be determined based on bench performance simulation data and bench performance prediction data, and the bench performance prediction model can be adjusted based on the loss function until the loss function is less than a set threshold to obtain the target bench performance prediction model.
[0084] S206. Input the process parameters in the process parameter space into the target bench performance prediction model to determine the optimal process parameters corresponding to the die casting.
[0085] For details regarding step S206, please refer to the above embodiments, which will not be repeated here.
[0086] The method for determining process parameters provided in this disclosure, based on bench performance test data and scanning data of a second die casting, trains a target simulation test model. This target simulation test model is then used to perform bench performance simulation tests on a first die casting to obtain bench performance simulation data for the first die casting. Based on this bench performance simulation data and the die casting process parameters of the first die casting, a constructed bench performance prediction model is trained to obtain a target bench performance prediction model. Furthermore, the target bench performance prediction model can be used to predict the performance of process parameters in the process parameter space to determine the optimal process parameters corresponding to the die casting. This allows for the acquisition of optimal process parameters that improve the performance and quality of the die casting, enabling the manufacturing of the die casting using these optimal process parameters and improving the overall performance and reliability of the die casting. Obtaining the optimal process parameters can reduce the production cost and energy consumption of the die casting, decrease the scrap rate, and promote sustainable development.
[0087] Based on the above embodiments, the present disclosure embodiments can explain and illustrate the training process of the target simulation test model, such as... Figure 3As shown, the training process of the target simulation test model in this embodiment includes the following steps:
[0088] S301, Perform bench performance testing on the second die casting to obtain bench performance test data for the second die casting.
[0089] As is understandable, bench performance testing is a method of testing equipment, components, or complete machines in a laboratory environment using a specially designed test bench. This method simulates actual usage conditions to perform performance tests on the test object under various operating conditions in order to evaluate its performance, durability, and reliability.
[0090] In other words, bench performance tests can be conducted on the second die casting based on the test bench, and the various performance parameters and data during the test process can be recorded as bench performance test data for the second die casting.
[0091] Optionally, bench performance test data include, but are not limited to: tensile strength, compressive strength, yield strength, toughness, compressive strength, etc.
[0092] S302, acquire scan data of the second die casting, the scan data includes at least the dimensional data and internal defect data of the second die casting, and generate a 3D model of the second die casting based on the scan data.
[0093] Optionally, the second die casting can be scanned by X-ray to obtain scan data of the second die casting. The scan data includes at least the dimensional data and internal defect data of the second die casting. For example, the scan data of the second die casting can be obtained by X-ray scanning of the second die casting using an X-ray machine.
[0094] Furthermore, the scanning data of the second die casting is used to perform three-dimensional reconstruction to obtain a 3D model of the second die casting.
[0095] S303, Construct a simulation test model.
[0096] In some implementations, mechanical data related to bench performance can be collected, and simulation tools can be used to establish a mathematical model describing the mechanics as a simulation test model. This model can be a theoretical model based on physics or an empirical model based on experimental data.
[0097] Optionally, the mapping relationship between the 3D model of the second die casting and the mechanical data can be determined based on the mechanical data related to the bench performance data, and then a simulation test model can be established based on the mapping relationship.
[0098] S304. Input the 3D model of the second die casting into the simulation test model to simulate the second die casting and obtain the bench performance simulation data of the second die casting.
[0099] In some implementations, the 3D model of the second die-casting is input into a simulation test model, which then simulates the 3D model of the second die-casting and outputs bench performance simulation data of the second die-casting. This bench performance simulation data includes, but is not limited to, tensile strength, compressive strength, yield strength, toughness, and compressive strength.
[0100] Optionally, the 3D model of the second die casting can be simulated and tested according to the bench test boundary conditions. By setting the bench test boundary conditions for the 3D model of the second die casting and inputting the 3D model and the bench test boundary conditions into the simulation test model, bench performance simulation test is performed on the 3D model of the second die casting to obtain bench performance simulation data of the second die casting.
[0101] It is understandable that the boundary conditions of a bench test refer to the conditions set at the interface between the experimental object and its external environment during the experiment. These conditions may include physical constraints (such as fixing method, loading method), environmental conditions (such as temperature, humidity, pressure, vibration, etc.), and experimental parameters (such as input voltage, current, rotational speed, load, etc.).
[0102] In this embodiment of the disclosure, the magnitude of the force applied to the second die-casting during the experiment can be set as the boundary condition for the bench test.
[0103] S305. Based on the bench performance simulation data and bench performance test data of the second die casting, the simulation test model is corrected and the simulation continues until the correction termination condition is met, thus obtaining the target simulation test model.
[0104] In some implementations, the need to optimize the simulation test model can be determined based on the bench performance simulation data and bench performance test data of the second die-cast part. Alternatively, the need to optimize the simulation test model can be determined by judging whether there is a discrepancy between the bench performance simulation data and the bench performance test data.
[0105] In some implementations, when there is a discrepancy between the bench performance simulation data and the bench performance test data, that is, in response to the determination that the simulation test model needs to be optimized, the simulation test model is corrected based on the discrepancy information between the bench performance simulation data and the bench performance test data of the second die casting.
[0106] In some implementations, it can be determined whether to continue modifying the simulation test model by identifying a correction termination condition and judging whether the deviation information meets the correction termination condition. Optionally, by determining the number of die-cast parts with deviation information within a set range and judging whether the number of die-cast parts has reached the set number, in response to the determination that the correction termination condition is met when the number of die-cast parts reaches the set number, the modification of the simulation test model is stopped, and the target simulation test model is obtained.
[0107] Optionally, the simulation test model can be optimized by adjusting the boundary conditions of the bench test. That is, the boundary conditions of the bench test are adjusted in response to the determination that optimization of the simulation test model is needed. For example, if the original boundary condition of the bench test was a tensile force of 500N applied to the die-casting, and optimization of the simulation test model is determined, the boundary condition of the bench test is adjusted to a tensile force of 300N applied to the die-casting.
[0108] The method for determining process parameters provided in the embodiments of this disclosure trains a simulation test model based on bench performance test data and scanning data of the second die casting. Based on the bench performance simulation data and bench performance test data of the second die casting, it can be determined whether the simulation test model needs to be corrected. If correction is determined, the bench experimental boundary conditions can be adjusted to correct the simulation test model, thereby obtaining a target simulation test model. This makes the simulation data output by the target simulation test model more meaningful.
[0109] Figure 4 This is a flowchart illustrating a method for determining process parameters according to an exemplary embodiment, such as... Figure 4 As shown, the method for determining process parameters according to an embodiment of this disclosure includes the following steps:
[0110] S401, acquire scan data of the first die casting, the scan data including at least the dimensional data and internal defect data of the first die casting.
[0111] In some implementations, the scanning data of the first die-casting part can be obtained by performing X-ray scanning on the first die-casting part. For example, the scanning data of the second die-casting part can be obtained by X-ray scanning the first die-casting part using an X-ray machine.
[0112] S402, Based on the scan data of the first die casting, generate a 3D model of the first die casting.
[0113] Optionally, a 3D model of the first die casting can be obtained by performing 3D reconstruction based on the scanning data of the first die casting. The scanning data includes at least the dimensional data and internal defect data of the first die casting. In other words, through 3D reconstruction, a 3D model with the same dimensions and defects as the first die casting can be obtained.
[0114] S403, input the 3D model of the first die casting into the target simulation test model to obtain the bench performance simulation data of the first die casting.
[0115] In some implementations, the 3D model of the first die casting is input into the target simulation test model, which then performs bench performance simulation tests on the 3D model of the first die casting and outputs bench performance simulation data of the first die casting.
[0116] Optionally, the bench performance simulation data of the first die casting includes, but is not limited to: tensile strength, compressive strength, yield strength, toughness, compressive strength, etc.
[0117] S404. Based on the die-casting process parameters of the first die-casting part and the bench performance simulation data of the first die-casting part, a target bench performance prediction model is obtained.
[0118] S405: Input the process parameters in the process parameter space into the target bench performance prediction model to determine the optimal process parameters corresponding to the die casting.
[0119] For details regarding steps S404-S405, please refer to the above embodiments; they will not be repeated here.
[0120] The method for determining process parameters provided in this disclosure involves acquiring scanned data of a first die-casting part and obtaining a 3D model of the first die-casting part based on the scanned data. The 3D model can then undergo bench performance simulation testing to obtain bench performance simulation data of the first die-casting part. Based on the bench performance simulation data and the die-casting process parameters of the first die-casting part, a target bench performance prediction model is determined. Furthermore, the target bench performance prediction model can be used to predict the performance of process parameters in the process parameter space to determine the optimal process parameters corresponding to the die-casting part. This allows for the acquisition of optimal process parameters that improve the performance and quality of the die-casting part, enabling its manufacturing and thus enhancing the overall performance and reliability of the die-casting part. Obtaining the optimal process parameters reduces production costs and energy consumption, decreases scrap rates, and promotes sustainable development.
[0121] Figure 5 This is a flowchart illustrating a method for determining process parameters according to an exemplary embodiment, such as... Figure 5As shown, the method for determining process parameters according to an embodiment of this disclosure includes the following steps:
[0122] S501, a bench performance simulation test is performed on the first die casting to obtain the bench performance simulation data of the first die casting.
[0123] S502, based on the die-casting process parameters of the first die-casting part and the bench performance simulation data of the first die-casting part, a target bench performance prediction model is obtained.
[0124] For details regarding steps S501-S502, please refer to the above embodiments, which will not be repeated here.
[0125] S503 meshes the process parameter space to obtain multiple meshes.
[0126] In some implementations, the process parameter space may contain multiple parameter variables, and these variables may have complex interactions. Optionally, based on the complexity of the interactions between process parameters, an appropriate meshing method can be selected to divide the process parameter space into multiple mesh cells. For example, the process parameter space can be meshed using methods such as uniform meshing or non-uniform meshing.
[0127] S504 inputs each grid into the target test bench performance prediction model to output the test bench performance prediction data corresponding to each grid.
[0128] In some implementations, a pre-trained target bench performance prediction model is obtained, which is used to predict the bench performance of process parameters. That is, each gridded cell can be input into the target bench performance prediction model, and the bench performance of each cell can be predicted using the grid performance data of the target bench performance prediction model, thus obtaining the bench performance prediction data corresponding to each cell.
[0129] S505 determines the optimal process parameters from the process parameter space based on the grid's bench performance prediction data.
[0130] Optionally, the optimal test performance prediction data can be obtained by comparing the test performance prediction data of each grid, and the target grid corresponding to the optimal test performance prediction data can be determined. Then, the process parameters within the target grid can be determined as the optimal process parameters.
[0131] Optionally, reference test bench performance prediction data can be preset, and it can be determined whether the test bench performance prediction data of the grid is the same as the reference test bench performance prediction data. The same reference test bench performance prediction data is taken as the optimal test bench performance prediction data, and then the process parameters in the target grid corresponding to the optimal test bench performance prediction data can be determined as the best process parameters.
[0132] In some implementations, after determining the optimal process parameters, the die-casting equipment can be configured based on the optimal process parameters, and the die-casting process can be carried out based on the optimal process parameters to obtain the target die-casting part, thereby improving the quality of the die-casting part.
[0133] The method for determining process parameters provided in this disclosure involves meshing the process parameter space to obtain multiple meshes containing the process parameters. A target bench performance prediction model is then used to predict the bench performance of the process parameters within the meshes, obtaining bench performance prediction data. Further, optimal bench performance prediction data is determined from this data, and the optimal process parameters corresponding to the die-casting part are determined from the target mesh corresponding to the optimal bench performance prediction data. This yields the best process parameters that improve the performance and quality of the die-casting part, allowing it to be manufactured using these optimal parameters to enhance the overall performance and reliability of the die-casting part. Obtaining the optimal process parameters reduces the production cost and energy consumption of the die-casting part, decreases the scrap rate, and promotes sustainable development.
[0134] Figure 6 The flowchart shown illustrates the process for determining optimal process parameters. By performing defect detection on the second die-casting, scan data of the second die-casting can be obtained, including dimensional data and internal defect data. Then, 3D reconstruction is performed based on the scan data to obtain a 3D model of the second die-casting. Simulation tests are then conducted on the 3D model using a constructed simulation test model to obtain bench performance simulation data for the second die-casting. Furthermore, based on the bench performance simulation data and bench performance test data of the second die-casting, the simulation test model is optimized and corrected to obtain the target simulation test model.
[0135] Simulation tests were conducted on the scanned data of the first die-casting part based on the target simulation test model to obtain the bench performance simulation data of the first die-casting part. Then, based on the die-casting process parameters of the first die-casting part, the bench performance prediction model was trained to obtain the target bench performance prediction model. Furthermore, the target bench performance prediction model was used to determine the optimal process parameters from the process parameters and spatial parameters.
[0136] Figure 7 This is a block diagram illustrating a process parameter determination apparatus according to an exemplary embodiment. (Refer to...) Figure 7 The process parameter determination apparatus 700 of this disclosure embodiment includes:
[0137] The simulation module 701 is used to perform bench performance simulation tests on the first die casting to obtain bench performance simulation data of the first die casting.
[0138] The first determining module 702 is used to obtain a target bench performance prediction model based on the die casting process parameters of the first die casting and the bench performance simulation data of the first die casting.
[0139] The second determining module 703 is used to input the process parameters in the process parameter space into the target bench performance prediction model to determine the optimal process parameters corresponding to the die casting.
[0140] In one embodiment of this disclosure, the simulation module 701 is further configured to: input the 3D model of the first die casting into the target simulation test model to obtain bench performance simulation data of the first die casting.
[0141] In one embodiment of this disclosure, the simulation module 701 is further configured to: perform bench performance testing on the second die casting to obtain bench performance test data of the second die casting; acquire scanning data of the second die casting, the scanning data including at least dimensional data and internal defect data of the second die casting, and generate a 3D model of the second die casting based on the scanning data; construct a simulation test model; input the 3D model of the second die casting into the simulation test model to simulate the second die casting and obtain bench performance simulation data of the second die casting; and correct the simulation test model according to the bench performance simulation data and bench performance test data of the second die casting and continue simulation until the correction termination condition is met to obtain the target simulation test model.
[0142] In one embodiment of this disclosure, the simulation module 701 is further configured to: set bench test boundary conditions for the 3D model of the second die casting, input the 3D model and the bench test boundary conditions into the simulation test model, perform bench performance simulation test on the 3D model of the second die casting, and obtain bench performance simulation data of the second die casting.
[0143] In one embodiment of this disclosure, the simulation module 701 is further configured to: determine whether to optimize the simulation test model based on the bench performance simulation data of the second die casting and the bench performance test data; and, in response to the determination that the simulation test model needs to be optimized, correct the simulation test model based on the deviation information between the bench performance simulation data of the second die casting and the bench performance test data.
[0144] In one embodiment of this disclosure, the simulation module 701 is further configured to: determine the number of die-cast parts whose deviation information is within a set range; and, in response to the number of die-cast parts reaching the set number, determine that the correction termination condition is met and then stop correcting the simulation test model to obtain the target simulation test model.
[0145] In one embodiment of this disclosure, the simulation module 701 is further configured to: adjust the boundary conditions of the bench test in response to a determination that the simulation test model needs to be optimized.
[0146] In one embodiment of this disclosure, the simulation module 701 is further configured to: acquire scanning data of the first die casting, the scanning data including at least dimensional data and internal defect data of the first die casting; and generate a 3D model of the first die casting based on the scanning data of the first die casting.
[0147] In one embodiment of this disclosure, the first determining module 702 is further configured to: construct a bench performance prediction model; input the die-casting process parameters of the first die-casting part into the bench performance prediction model to obtain bench performance prediction data of the first die-casting part; and adjust the bench performance prediction model based on the bench performance prediction data and the bench performance simulation data to obtain the target bench performance prediction model.
[0148] In one embodiment of this disclosure, the second determining module 703 is further configured to: grid the process parameter space to obtain multiple grids; input each grid into the target bench performance prediction model to output bench performance prediction data corresponding to each grid; and determine the optimal process parameters from the process parameter space based on the bench performance prediction data of the grids.
[0149] In one embodiment of this disclosure, the second determining module 703 is further configured to: compare the bench performance prediction data of each grid to obtain the optimal bench performance prediction data; determine the target grid corresponding to the optimal bench performance prediction data; and determine the process parameters within the target grid as the optimal process parameters.
[0150] In one embodiment of this disclosure, the second determining module 703 is further configured to: configure the parameters of the die-casting equipment based on the optimal process parameters, and perform the die-casting process based on the optimal process parameters to obtain the target die-casting part.
[0151] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.
[0152] The apparatus for determining process parameters provided in the embodiments of this disclosure obtains bench performance simulation data of the first die casting by performing bench performance simulation tests on the first die casting. Based on the bench performance simulation data and the die casting process parameters of the first die casting, a target bench performance prediction model is determined. Furthermore, the target bench performance prediction model can be used to predict the performance of process parameters in the process parameter space to determine the optimal process parameters corresponding to the die casting. This allows for the acquisition of optimal process parameters that improve the performance and quality of the die casting, enabling the manufacturing of the die casting using these optimal process parameters to enhance its overall performance and reliability. Obtaining the optimal process parameters reduces the production cost and energy consumption of the die casting, decreases the scrap rate, and promotes sustainable development.
[0153] Figure 8 This is a block diagram illustrating an electronic device according to an exemplary embodiment.
[0154] like Figure 8 As shown, the above-mentioned electronic device 800 includes:
[0155] The system includes a memory 801 and a processor 802, and a bus 803 connecting different components (including the memory 801 and the processor 802). The memory 801 stores a computer program, which, when executed by the processor 802, implements the method for determining process parameters as described in the embodiments of this disclosure.
[0156] Bus 803 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.
[0157] Electronic device 800 typically includes a variety of electronic device readable media. These media can be any available media that can be accessed by electronic device 800, including volatile and non-volatile media, removable and non-removable media.
[0158] Memory 801 may also include computer system readable media in the form of volatile memory, such as random access memory (RAM) 804 and / or cache memory 805. Electronic device 800 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 806 may be used to read and write non-removable, non-volatile magnetic media (… Figure 8 Not shown; usually referred to as a "hard drive"). Although Figure 8Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 803 via one or more data media interfaces. Memory 801 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this disclosure.
[0159] A program / utility 808 having a set (at least one) of program modules 807 may be stored, for example, in memory 801. Such program modules 807 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 807 typically perform the functions and / or methods described in the embodiments of this disclosure.
[0160] Electronic device 800 can also communicate with one or more external devices 809 (e.g., keyboard, pointing device, display 891, etc.), and with one or more devices that enable a user to interact with the electronic device 800, and / or with any device that enables the electronic device 800 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed through input / output (I / O) interface 892. Furthermore, electronic device 800 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 893. Figure 8 As shown, network adapter 893 communicates with other modules of electronic device 800 via bus 803. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.
[0161] The processor 802 executes various functional applications and data processing by running programs stored in the memory 801.
[0162] It should be noted that the implementation process and technical principles of the electronic device in this embodiment are explained in the foregoing description of the method for determining process parameters in the embodiments of this disclosure, and will not be repeated here.
[0163] To implement the above embodiments, this disclosure also proposes a computer-readable storage medium storing computer program instructions thereon, which, when executed by a processor, implement the steps of the method for determining process parameters provided in this disclosure.
[0164] Alternatively, the computer-readable storage medium may be ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.
[0165] To implement the above embodiments, this disclosure also provides a computer program product, including a computer program, characterized in that, when the computer program is executed by a processor of an electronic device, it implements the method for determining process parameters as described above.
[0166] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.
[0167] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.
Claims
1. A method for determining process parameters, characterized in that, include: A bench performance simulation test was performed on the first die casting to obtain bench performance simulation data of the first die casting. Based on the die-casting process parameters of the first die-casting part and the bench performance simulation data of the first die-casting part, a target bench performance prediction model is obtained. The process parameters in the process parameter space are input into the target bench performance prediction model to determine the optimal process parameters corresponding to the die casting.
2. The method according to claim 1, characterized in that, The bench performance simulation test of the first die casting to obtain bench performance simulation data of the first die casting includes: The 3D model of the first die casting is input into the target simulation test model to obtain the bench performance simulation data of the first die casting.
3. The method according to claim 2, characterized in that, The training process of the target simulation test model includes: A bench performance test was performed on the second die casting to obtain the bench performance test data of the second die casting. The scanning data of the second die casting is obtained, the scanning data including at least the dimensional data and internal defect data of the second die casting, and a 3D model of the second die casting is generated based on the scanning data; Construct a simulation test model; The 3D model of the second die casting is input into the simulation test model to simulate the second die casting and obtain the bench performance simulation data of the second die casting. Based on the bench performance simulation data and bench performance test data of the second die casting, the simulation test model is corrected and the simulation continues until the correction termination condition is met, thus obtaining the target simulation test model.
4. The method according to claim 3, characterized in that, The step of inputting the 3D model of the second die-casting part into the simulation test model to simulate the second die-casting part and obtain bench performance simulation data of the second die-casting part includes: Set bench test boundary conditions for the 3D model of the second die casting, and input the 3D model and the bench test boundary conditions into the simulation test model to perform bench performance simulation test on the 3D model of the second die casting to obtain bench performance simulation data of the second die casting.
5. The method according to claim 3, characterized in that, The step of correcting the simulation test model based on the bench performance simulation data and bench performance test data of the second die casting also includes: Based on the bench performance simulation data and bench performance test data of the second die casting, determine whether to optimize the simulation test model; When it is determined that the simulation test model needs to be optimized, the simulation test model is corrected based on the deviation information between the bench performance simulation data of the second die casting and the bench performance test data.
6. The method according to claim 3, characterized in that, The method further includes: Determine the number of die-cast parts whose deviation information falls within a set range; When the number of die-cast parts reaches a set number, if the correction termination condition is met, the correction of the simulation test model is stopped, and the target simulation test model is obtained.
7. The method according to claim 3, characterized in that, The method further includes: When it is determined that the simulation test model needs to be optimized, the boundary conditions of the bench test are adjusted.
8. The method according to any one of claims 2-7, characterized in that, Before inputting the 3D model of the first die-casting part into the target simulation test model to obtain the bench performance simulation data of the first die-casting part, the method further includes: Obtain scanning data of the first die casting, wherein the scanning data includes at least the dimensional data and internal defect data of the first die casting; A 3D model of the first die casting is generated based on the scanning data of the first die casting.
9. The method according to any one of claims 1-7, characterized in that, The target bench performance prediction model is obtained based on the die-casting process parameters of the first die-casting part and the bench performance simulation data of the first die-casting part, including: Construct a bench performance prediction model; The die-casting process parameters of the first die-casting part are input into the bench performance prediction model to obtain the bench performance prediction data of the first die-casting part. Based on the test bench performance prediction data and the test bench performance simulation data, the test bench performance prediction model is adjusted to obtain the target test bench performance prediction model.
10. The method according to any one of claims 1-7, characterized in that, The step of inputting process parameters from the process parameter space into the target bench performance prediction model to determine the optimal process parameters corresponding to the die casting includes: The process parameter space is meshed to obtain multiple meshes; Each grid is input into the target test bench performance prediction model to output the test bench performance prediction data corresponding to each grid. The optimal process parameters are determined from the process parameter space based on the bench performance prediction data of the grid.
11. The method according to claim 10, characterized in that, The step of determining the optimal process parameters from the process parameter space based on the bench performance prediction data of the grid includes: The test bench performance prediction data for each grid are compared to obtain the optimal test bench performance prediction data. Determine the target grid corresponding to the optimal test bench performance prediction data; The process parameters within the target grid are determined as the optimal process parameters.
12. The method according to any one of claims 1-7, characterized in that, After finding the optimal process parameters corresponding to the die casting from the process parameter space, the method further includes: The die-casting equipment is configured with the optimal process parameters, and the die-casting process is carried out based on the optimal process parameters to obtain the target die-cast part.
13. A device for determining process parameters, characterized in that, include: The simulation module is used to perform bench performance simulation tests on the first die casting to obtain bench performance simulation data of the first die casting. The first determining module is used to obtain a target bench performance prediction model based on the die casting process parameters of the first die casting and the bench performance simulation data of the first die casting. The second determining module is used to input the process parameters in the process parameter space into the target bench performance prediction model to determine the optimal process parameters corresponding to the die casting.
14. An electronic device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured as follows: The steps for implementing the method according to any one of claims 1-12.
15. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, When executed by a processor, the program instructions implement the steps of the method described in any one of claims 1-12.