Metal plate stamping process parameter optimization method and equipment based on machine learning and medium

Abstract

The invention provides a machine learning-based sheet metal stamping process parameter optimization method, equipment and a medium. The method comprises the following steps of obtaining equipment parameter data, process condition data and quality parameter data in a historical sheet metal stamping process; training a machine learning model through the equipment parameter data, the process condition data and the quality parameter data in the historical sheet metal stamping process to obtain a sheet metal stamping quality prediction model; acquiring actual process condition data of the current process period; by taking quality optimization as a target, solving optimal equipment parameter data in combination with the actual process condition data and the sheet metal stamping quality prediction model; and in the current process period, the metal plate stamping equipment is controlled according to the optimal equipment parameter data. According to the method, proper metal plate stamping process parameters can be conveniently determined, so that the consistency of product quality is effectively ensured.

Description

Technical Field

[0001] This invention relates to the field of sheet metal stamping control technology, specifically to a method, equipment, and medium for optimizing sheet metal stamping process parameters based on machine learning. Background Technology

[0002] Sheet metal stamping is a key process in modern industrial production such as automobile manufacturing and home appliance manufacturing. The setting of process parameters such as stamping pressure and stamping speed directly affects the quality of the product. At present, the industry mainly relies on the experience of process engineers for parameter setting and debugging. This method is highly subjective, has a long debugging cycle, is highly dependent on personnel experience, and makes it difficult to guarantee the consistency of product quality. Summary of the Invention

[0003] To address the aforementioned technical problems, this invention provides a method, equipment, and medium for optimizing sheet metal stamping process parameters based on machine learning. This method can conveniently determine suitable sheet metal stamping process parameters, thereby effectively ensuring the consistency of product quality.

[0004] The technical solution adopted in this invention is as follows: A machine learning-based method for optimizing sheet metal stamping process parameters includes the following steps: acquiring equipment parameter data, process condition data, and quality parameter data from historical sheet metal stamping processes; training a machine learning model using the historical sheet metal stamping process data to obtain a sheet metal stamping quality prediction model; acquiring actual process condition data for the current process cycle; solving for optimal equipment parameter data by combining the actual process condition data and the sheet metal stamping quality prediction model, with the goal of achieving optimal quality; and controlling the sheet metal stamping equipment using the optimal equipment parameter data in the current process cycle.

[0005] Equipment parameter data is a combination of multiple equipment parameters, including stamping pressure, stamping speed, stamping stroke, and die clearance; process condition data is a combination of multiple process conditions, including the material of the target being processed, material hardness, material thickness, ambient temperature and humidity, and the total usage time of the sheet metal stamping equipment; quality parameter data is a combination of multiple quality parameters, including springback, maximum thinning rate, surface roughness, and contour error.

[0006] The objective function, with the goal of achieving optimal quality, is as follows:

[0007] in, Q This refers to the overall deviation error in sheet metal stamping quality. y iThe first of the quality parameter data output by the sheet metal stamping quality prediction model is... i Predicted values ​​of each quality parameter t i For the quality parameter data, the first i Target values ​​for each quality parameter ω i For the quality parameter data, the first i The weighting coefficients of each quality parameter N This represents the total number of quality parameters in the quality parameter data.

[0008] The constraints corresponding to the objective function include that each device parameter is within the corresponding preset range and each quality parameter is not greater than the corresponding threshold.

[0009] The objective function is solved by Bayesian optimization algorithm to obtain the combination of equipment parameters that minimizes the overall deviation error of the sheet metal stamping quality, which is then used as the optimal equipment parameter data.

[0010] The machine learning model is a convolutional neural network model.

[0011] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the machine learning-based sheet metal stamping process parameter optimization method.

[0012] A non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the machine learning-based sheet metal stamping process parameter optimization method described above.

[0013] The beneficial effects of this invention are: This invention trains a quality prediction model using historical data of sheet metal stamping processes, and then uses actual process conditions and other data in the current process cycle to solve for the optimal equipment parameter data when the quality is optimal. The invention also uses this optimal equipment parameter data to control the sheet metal stamping equipment in the current process cycle. As a result, suitable sheet metal stamping process parameters can be easily determined, thereby effectively ensuring the consistency of product quality. Attached Figure Description

[0014] Figure 1 This is a flowchart of a machine learning-based method for optimizing sheet metal stamping process parameters according to an embodiment of the present invention. Detailed Implementation

[0015] 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.

[0016] like Figure 1 As shown in the figure, the sheet metal stamping process parameter optimization method based on machine learning in this embodiment of the invention includes the following steps: S1: Obtain equipment parameter data, process condition data, and quality parameter data from historical sheet metal stamping processes.

[0017] In one embodiment of the present invention, the equipment parameter data is a combination of multiple equipment parameters, including stamping pressure, stamping speed, stamping stroke, die clearance, etc. The process condition data is a combination of multiple process conditions, including the material composition, hardness, and thickness of the target material, as well as ambient temperature and humidity, and the total usage time of the sheet metal stamping equipment, etc. The quality parameter data is a combination of multiple quality parameters, including springback, maximum thinning rate, surface roughness, and contour error, etc.

[0018] The aforementioned historical data was obtained through reading, collecting, and testing during the sheet metal stamping process over a historical period. Furthermore, the equipment parameter data and process condition data correspond to the quality parameter data, thereby reflecting the quality of the products obtained by sheet metal stamping under certain equipment parameters and process conditions.

[0019] S2 trains a machine learning model using equipment parameter data, process condition data, and quality parameter data from historical sheet metal stamping processes to obtain a sheet metal stamping quality prediction model.

[0020] Before model training, the aforementioned historical data can be preprocessed, including time synchronization, missing value imputation, and outlier removal. The machine learning model in this embodiment of the invention can be a convolutional neural network model or a gradient boosting decision tree, etc. The training process of the machine learning model is a common technique and will not be detailed here.

[0021] S3: Obtain the actual process condition data for the current process cycle.

[0022] In an embodiment of the present invention, process parameters can be optimized once in each process cycle. Step S1 obtains data from multiple historical process cycles, and the equipment parameters for the current process cycle can be optimized based on the data from multiple historical process cycles.

[0023] In one embodiment of the present invention, the running time between each start-up and shutdown of the sheet metal stamping equipment can be used as a process cycle, or a fixed time, such as one day, can be used as a process cycle.

[0024] S4, with the goal of achieving optimal quality, combines actual process condition data and sheet metal stamping quality prediction models to solve for the optimal equipment parameter data.

[0025] In embodiments of the present invention, an objective function can be constructed, and an optimization algorithm can be used to input actual process condition data and trial equipment parameter data into the sheet metal stamping quality prediction model, outputting predicted quality parameter data. Through continuous trials, the optimal solution of the final equipment parameter data is obtained, so that the objective can meet the constraints of the objective function.

[0026] In one embodiment of the present invention, with the goal of achieving optimal quality, the objective function is constructed as follows:

[0027] in, Q This refers to the overall deviation error in sheet metal stamping quality. y i The first of the quality parameter data output by the sheet metal stamping quality prediction model. i Predicted values ​​of each quality parameter t i For the quality parameter data, the first i Target values ​​for each quality parameter ω i For the quality parameter data, the first i The weighting coefficients of each quality parameter N This represents the total number of quality parameters in the quality parameter data.

[0028] Overall deviation error of sheet metal stamping quality Q This represents the weighted sum of errors between the predicted and target values ​​of the quality parameters. Since the target value is the numerical value corresponding to the expected high quality, the overall deviation error of sheet metal stamping quality is... Q The smaller the value, the closer the quality predicted by the sheet metal stamping quality prediction model is to the target quality, meaning the higher the product quality. Therefore, solving this problem makes... Q The smallest possible equipment parameter data is the optimal equipment parameter data. Weighting coefficients. ω i This indicates the degree of attention paid to each quality parameter. The more emphasis is placed on ensuring the quality of a certain aspect, the greater the weight coefficient of the corresponding quality parameter. Therefore, each weight coefficient can be set according to actual needs.

[0029] In one embodiment of the present invention, the constraints corresponding to the objective function include each equipment parameter being within a corresponding preset range and each quality parameter not exceeding a corresponding threshold. For example, due to limitations in the performance of sheet metal stamping equipment, the stamping speed is between 50 mm / s and 500 mm / s; to ensure that the product does not break as much as possible, the maximum thinning rate should not exceed 25%.

[0030] In one embodiment of the present invention, the objective function can be solved by a Bayesian optimization algorithm to obtain the combination of equipment parameters that minimizes the overall deviation error of sheet metal stamping quality, which is then used as the optimal equipment parameter data.

[0031] S5 controls the sheet metal stamping equipment with optimal equipment parameter data during the current process cycle.

[0032] The sheet metal stamping process parameter optimization method based on machine learning according to embodiments of the present invention trains a quality prediction model using historical data of the sheet metal stamping process, and solves for the optimal equipment parameter data when the quality is optimal using actual process condition data in the current process cycle. The sheet metal stamping equipment is then controlled using the optimal equipment parameter data in the current process cycle. As a result, suitable sheet metal stamping process parameters can be easily determined, thereby effectively ensuring the consistency of product quality.

[0033] Corresponding to the above embodiments, the present invention also proposes a computer device.

[0034] The computer device of this invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it can implement the sheet metal stamping process parameter optimization method based on machine learning according to the above embodiments of this invention.

[0035] According to the computer device of the present invention, when the processor executes the computer program stored in the memory, it trains a quality prediction model using historical data of sheet metal stamping process, and solves for the optimal equipment parameter data when the quality is optimal in the current process cycle using actual process condition data, etc., and controls the sheet metal stamping equipment with the optimal equipment parameter data in the current process cycle. Thus, it is possible to conveniently determine suitable sheet metal stamping process parameters, thereby effectively ensuring the consistency of product quality.

[0036] Corresponding to the above embodiments, the present invention also proposes a non-transitory computer-readable storage medium.

[0037] The non-transitory computer-readable storage medium of this invention stores a computer program thereon, which, when executed by a processor, can implement the machine learning-based sheet metal stamping process parameter optimization method according to the above embodiments of this invention.

[0038] According to the non-transitory computer-readable storage medium of the present invention, when the processor executes the computer program stored thereon, it trains a quality prediction model using historical data of sheet metal stamping process, and solves for the optimal equipment parameter data when the quality is optimal in the current process cycle using actual process condition data, etc., and controls the sheet metal stamping equipment with the optimal equipment parameter data in the current process cycle. Thus, it is possible to conveniently determine suitable sheet metal stamping process parameters, thereby effectively ensuring the consistency of product quality.

[0039] In the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. "A plurality of" means two or more, unless otherwise explicitly specified.

[0040] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0041] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature is in indirect contact with the second feature through an intermediate medium. Furthermore, "above," "over," and "on top" of the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.

[0042] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Furthermore, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0043] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0044] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0045] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0046] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0047] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0048] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for optimizing sheet metal stamping process parameters based on machine learning, characterized in that, Includes the following steps: Obtain equipment parameter data, process condition data, and quality parameter data from historical sheet metal stamping processes; A machine learning model is trained using equipment parameter data, process condition data, and quality parameter data from the historical sheet metal stamping process to obtain a sheet metal stamping quality prediction model. Obtain the actual process condition data for the current process cycle; With the goal of achieving optimal quality, the optimal equipment parameter data is obtained by combining the actual process condition data and the sheet metal stamping quality prediction model. In the current process cycle, the sheet metal stamping equipment is controlled using the aforementioned optimal equipment parameter data.

2. The method for optimizing sheet metal stamping process parameters based on machine learning according to claim 1, characterized in that, The equipment parameter data is a combination of multiple equipment parameters, including stamping pressure, stamping speed, stamping stroke, and die clearance; the process condition data is a combination of multiple process conditions, including the material of the target being processed, material hardness, material thickness, ambient temperature and humidity, and the total usage time of the sheet metal stamping equipment. The quality parameter data is a combination of multiple quality parameters, including springback, maximum thinning rate, surface roughness, and profile error.

3. The method for optimizing sheet metal stamping process parameters based on machine learning according to claim 2, characterized in that, in, With the goal of achieving optimal quality, the objective function is constructed as follows: ； in, Q This refers to the overall deviation error in sheet metal stamping quality. y i The first of the quality parameter data output by the sheet metal stamping quality prediction model is... i Predicted values ​​of each quality parameter t i For the quality parameter data, the first i Target values ​​for each quality parameter ω i For the quality parameter data, the first i The weighting coefficients of each quality parameter N This represents the total number of quality parameters in the quality parameter data.

4. The method for optimizing sheet metal stamping process parameters based on machine learning according to claim 3, characterized in that, The constraints corresponding to the objective function include that each device parameter is within the corresponding preset range and each quality parameter is not greater than the corresponding threshold.

5. The method for optimizing sheet metal stamping process parameters based on machine learning according to claim 4, characterized in that, The objective function is solved by Bayesian optimization algorithm to obtain the combination of equipment parameters that minimizes the overall deviation error of the sheet metal stamping quality, which is then used as the optimal equipment parameter data.

6. The method for optimizing sheet metal stamping process parameters based on machine learning according to claim 1, characterized in that, The machine learning model is a convolutional neural network model.

7. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the machine learning-based method for optimizing sheet metal stamping process parameters according to any one of claims 1-6.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the machine learning-based method for optimizing sheet metal stamping process parameters according to any one of claims 1-6.

Images