A method and system for optimizing process parameters of automobile panel mold

Abstract

The present invention discloses a method and system for optimizing process parameters of an automobile cover mold, which relates to the field of automobile mold technology, including: using historical production data sets to construct a mold wear degree prediction model and a sharp edge feature clarity prediction model, and screening out a group of process parameter combinations as preliminary candidates; using a multi-objective genetic algorithm to optimize the preliminary candidate process parameter combinations, and outputting the optimized process parameter combinations; constructing a digital twin model of the automobile cover mold, inputting the optimized process parameter combination into the digital twin model, further fine-tuning the process parameter combination, and outputting the final optimized process parameter combination; the present invention significantly improves the mold life and product quality, reduces the test cost, accelerates the process optimization process, and improves the overall process performance by constructing a mold wear degree prediction model and a sharp edge feature clarity prediction model, multi-objective genetic algorithm optimization and digital twin technology.

Description

Technical Field

[0001] The invention relates to the technical field of automobile moulds, and in particular to a method and system for optimizing process parameters of an automobile covering part mould. Background Art

[0002] With the rapid development of the automobile manufacturing industry, the manufacturing technology of automobile cover parts molds is also constantly improving. The traditional mold manufacturing process relies on experienced engineers to make manual adjustments, which is not only time-consuming and labor-intensive, but also difficult to ensure the consistency and stability of product quality. Although the existing technology has improved the efficiency and accuracy of mold manufacturing to a certain extent, there are still some shortcomings; first, in the traditional method, the degree of mold wear and the clarity of sharp edge features are often estimated by manual experience. This method is highly subjective and difficult to achieve precise control; second, the existing optimization methods can usually only optimize for a single goal, and cannot simultaneously consider the balance between multiple goals such as minimizing the degree of mold wear and maximizing the clarity of sharp edge features; in addition, the traditional simulation method lacks comprehensive consideration of various complex factors in the actual production process, resulting in a large difference between the optimization results and the actual production effect. Summary of the invention

[0003] In view of the above existing problems, the present invention is proposed.

[0004] Therefore, the present invention provides a method and system for optimizing process parameters of automobile cover molds to solve the problems in the prior art of inaccurate optimization of process parameters of automobile cover molds and difficulty in balancing minimization of mold wear and maximization of sharp edge feature clarity.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] In a first aspect, an embodiment of the present invention provides a method for optimizing process parameters of an automobile panel mold, which includes using a historical production data set to construct a mold wear degree prediction model and a sharp edge feature clarity prediction model, predicting the mold wear degree and sharp edge feature clarity under different process parameter combinations, and selecting a group of process parameter combinations as preliminary candidates;

[0007] Use a multi-objective genetic algorithm to optimize the preliminary candidate process parameter combination and output the optimized process parameter combination;

[0008] Build a digital twin model of the automobile cover mold, input the optimized process parameter combination into the digital twin model, further fine-tune the process parameter combination, and output the final optimized process parameter combination.

[0009] As a preferred solution of the method for optimizing process parameters of automobile cover molds of the present invention, the historical production data set includes stamping pressure, stamping speed, temperature, lubricant usage, forming times and forming cycles.

[0010] As a preferred solution of the process parameter optimization method of automobile panel mold of the present invention, the mold wear degree prediction model and sharp edge feature clarity prediction model are constructed by using historical production data sets, including the following steps:

[0011] Use the Python Pandas library to read historical production data sets, use the dropna() function to delete rows with missing values, and use the Z-score method to identify and delete outliers;

[0012] The processed historical production data set is used to build a mold wear degree prediction model and a sharp edge feature clarity prediction model;

[0013] The mold wear degree prediction model is expressed as,

[0014] ;

[0015] in, Indicates the predicted degree of die wear, Indicates the number of forming times, Indicates the stamping pressure, Indicates the punching speed, Indicates the forming cycle, Indicates temperature, represents the average value of stamping pressure, L represents the amount of lubricant used, Indicates the standard deviation of punching pressure;

[0016] The sharp edge feature clarity prediction model is expressed as,

[0017] ;

[0018] in, represents the predicted sharp edge feature clarity, i represents the index of the forming times, Indicates the amount of lubricant used after forming n times.

[0019] As a preferred solution of the process parameter optimization method for automobile panel mold of the present invention, the method predicts the mold wear degree and sharp edge feature clarity under different process parameter combinations and selects a group of process parameter combinations as preliminary candidates, including the following steps:

[0020] Based on the constructed mold wear degree prediction model and sharp edge feature clarity prediction model, each process parameter combination is input into the mold wear degree prediction model and the sharp edge feature clarity prediction model, and the predicted mold wear degree and predicted sharp edge feature clarity of each process parameter combination are output;

[0021] The output results are standardized, and the comprehensive index is calculated based on the criteria of minimizing the degree of die wear and maximizing the sharp edge feature clarity, expressed as:

[0022] ;

[0023] in, Represents a comprehensive indicator, represents the predicted degree of mold wear after standardization, represents the sharp edge feature clarity of the normalized prediction;

[0024] Arrange the comprehensive index of each process parameter combination in descending order, and select a group of process parameter combinations with the smallest comprehensive index as preliminary candidates.

[0025] As a preferred solution of the process parameter optimization method for automobile panel molds of the present invention, wherein: a multi-objective genetic algorithm is used to optimize the preliminary candidate process parameter combination, and the optimized process parameter combination is output, comprising the following steps:

[0026] The objective function is defined as minimizing the die wear and maximizing the sharp edge feature definition;

[0027] A portion of the preliminary candidate process parameter combinations is randomly selected as individuals in the initial population. When the preliminary candidate process parameter combinations are insufficient, the remaining individuals are supplemented by random generation.

[0028] For each individual, the performance under the two objective functions is calculated, and the simulated two-point crossover operation, Gaussian mutation and tournament selection methods are used for optimization. Individuals with higher fitness are selected to enter the next generation.

[0029] After each generation, all individuals are Pareto sorted to find the individuals that are no worse than other individuals in any goal;

[0030] Set the maximum number of iterations and convergence conditions;

[0031] When the convergence condition is met, the algorithm is considered to have converged. When the number of optimizations reaches the set maximum number of iterations, the optimization is stopped.

[0032] The Pareto optimal solution set is selected from all individuals generated in the optimization process, and the individuals on the Pareto frontier are output as the optimized process parameter combination.

[0033] As a preferred solution of the process parameter optimization method of the automobile panel mold of the present invention, wherein: using physics-based simulation software to build a digital twin model of the automobile panel mold includes the following steps:

[0034] Using physics-based simulation software, a three-dimensional model is established according to the actual size and shape of the mold, the geometry and position of the sharp edges are accurately simulated, the corresponding elastic modulus, Poisson's ratio and yield strength are set according to the actual material used, and the boundary conditions matching the actual production environment are set to obtain the digital twin model of the automotive cover mold.

[0035] As a preferred solution of the process parameter optimization method for automobile cover molds of the present invention, the digital twin model of the automobile cover mold is constructed, the optimized process parameter combination is input into the digital twin model, the process parameter combination is further fine-tuned, and the final optimized process parameter combination is output, including the following steps:

[0036] Import the optimized process parameter combination into the digital twin model, start the simulation software for simulation, and output the dynamic changes of the simulated die wear degree and the simulated sharp edge feature clarity during the stamping process;

[0037] Setting die wear thresholds and sharp edge feature clarity thresholds through statistical analysis of historical production data sets;

[0038] When the simulated mold wear degree is less than or equal to the mold wear degree threshold, and the simulated sharp edge feature clarity is greater than or equal to the sharp edge feature clarity threshold, no fine-tuning is performed, and the final optimized process parameter combination is directly output;

[0039] When the simulated die wear degree is greater than the die wear degree threshold, and the simulated sharp edge feature clarity is less than the sharp edge feature clarity threshold, the die wear degree is reduced and the sharp edge feature clarity is improved by fine-tuning the stamping pressure, stamping speed, temperature, lubricant usage, forming cycle and forming times;

[0040] When the simulated die wear degree is greater than the die wear degree threshold, and the simulated sharp edge feature clarity is greater than or equal to the sharp edge feature clarity threshold, the die wear degree is reduced by reducing the stamping pressure and increasing the amount of lubricant used, while ensuring that the sharp edge feature clarity is not less than the sharp edge feature clarity threshold;

[0041] When the simulated die wear degree is less than or equal to the die wear degree threshold, and the simulated sharp edge feature clarity is less than the sharp edge feature clarity threshold, the sharp edge feature clarity is improved by increasing the stamping pressure and stamping speed, while ensuring that the die wear degree does not exceed the die wear degree threshold;

[0042] After fine-tuning, the digital twin simulation is performed again until the simulated mold wear degree is less than or equal to the mold wear degree threshold, and the simulated sharp edge feature clarity is greater than or equal to the sharp edge feature clarity threshold, and the final optimized process parameter combination is output.

[0043] In a second aspect, the present invention provides a process parameter optimization system for automobile panel molds, including a process parameter combination screening module, which is responsible for building a mold wear degree prediction model and a sharp edge feature clarity prediction model using a historical production data set, predicting the mold wear degree and sharp edge feature clarity under different process parameter combinations, and screening out a group of process parameter combinations as preliminary candidates;

[0044] The process parameter optimization module is responsible for optimizing the preliminary candidate process parameter combinations using a multi-objective genetic algorithm and outputting the optimized process parameter combinations;

[0045] The process parameter simulation and adjustment module is responsible for building a digital twin model of the automobile cover mold, inputting the optimized process parameter combination into the digital twin model, further fine-tuning the process parameter combination, and outputting the final optimized process parameter combination.

[0046] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the method for optimizing the process parameters of the automobile cover mold as described in the first aspect of the present invention is implemented.

[0047] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the method for optimizing process parameters of a mold for an automobile cover as described in the first aspect of the present invention is implemented.

[0048] The beneficial effects of the present invention are as follows: by constructing a mold wear degree prediction model and a sharp edge feature clarity prediction model, and using historical production data sets for data preprocessing, not only the model prediction accuracy is improved, but also the optimal process parameter combination can be quickly identified, greatly reducing unnecessary experimental costs; using a multi-objective genetic algorithm to optimize the preliminary candidate process parameter combination, effectively finding the balance point between minimizing the mold wear degree and maximizing the sharp edge feature clarity, and further improving the overall performance of the process parameter combination; by defining the objective function, initializing the population and performing genetic operations, as well as maintaining population diversity, it is ensured that the algorithm efficiently advances toward the established goal, and the possibility of finding a satisfactory solution is increased; by constructing a digital twin model, the optimized process parameter combination is input into the model for virtual verification and adjustment, ensuring that the expected mold performance and product quality can be achieved in actual production. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0050] Figure 1 This is a flow chart of the method for optimizing process parameters of automobile panel mold in Example 1.

[0051] Figure 2 This is a fine-tuning decision diagram for the process parameter combination in Example 1. DETAILED DESCRIPTION

[0052] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0053] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0054] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0055] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a method for optimizing process parameters of a mold for an automobile cover, comprising the following steps:

[0056] S1. Use historical production data sets to build mold wear degree prediction models and sharp edge feature clarity prediction models to predict mold wear degree and sharp edge feature clarity under different process parameter combinations, and screen out a group of process parameter combinations as preliminary candidates.

[0057] S1.1. Historical production data sets include punching pressure, punching speed, temperature, lubricant usage, forming times, and forming cycles.

[0058] S1.2. Use the Python Pandas library to read the historical production data set, use the dropna() function to delete rows with missing values, and use the Z-score method to identify and delete outliers;

[0059] The processed historical production data set is used to build a mold wear degree prediction model and a sharp edge feature clarity prediction model;

[0060] The mold wear degree prediction model is expressed as,

[0061] ;

[0062] in, Indicates the predicted degree of die wear, Indicates the number of forming operations, which refers to the number of forming operations that the mold undergoes during the production process. It is an important factor affecting mold wear. As the number of forming operations increases, mold wear will gradually increase. Indicates stamping pressure, which refers to the force applied to the material during the stamping process. The greater the stamping pressure, the greater the pressure on the mold, which will increase the wear rate of the mold. Indicates the stamping speed, which refers to the speed at which the mold moves during the stamping process. The speed of the stamping will affect the contact time between the mold and the material, thereby affecting the wear of the mold. Indicates the forming cycle, which refers to the time required to complete a forming operation. A longer forming cycle means that the mold is in contact with the material for a longer time, which may cause more wear. Indicates temperature, which refers to the temperature of the mold when it is working. Too high temperature will accelerate the softening of the material, thus affecting the degree of wear of the mold. It indicates the average value of stamping pressure, which refers to the average level of stamping pressure in a certain period of time and is used to standardize stamping pressure variables. L indicates the amount of lubricant used. Lubricant can reduce the friction between the mold and the material, thereby slowing down the wear of the mold. Indicates the standard deviation of stamping pressure, which refers to the degree of stamping pressure fluctuation and is used to reflect the stability of stamping pressure. It represents the relationship between stamping pressure and die wear. The effect of stamping pressure on die wear is calculated by sigmoid function, and this effect is accumulated by the forming times n. It indicates the influence of stamping pressure, stamping speed, forming cycle and temperature on the degree of die wear. It shows the effect of the interaction between temperature and lubricant usage on the degree of die wear;

[0063] It should be noted that the design of the die wear prediction model is based on the understanding of various factors affecting die wear and their interactions. The model comprehensively considers multiple variables such as stamping pressure, stamping speed, forming cycle, temperature, lubricant usage, and forming times, and quantifies the impact of these factors on die wear through mathematical expressions.

[0064] The sharp edge feature clarity prediction model is expressed as,

[0065] ;

[0066] in, represents the predicted sharp edge feature clarity, i represents the index of the forming times, Indicates the amount of lubricant used after forming n times, It represents the interaction between punching pressure, punching speed and temperature, and takes into account the influence of lubricant usage. It means that the interaction intensity among stamping pressure, stamping speed and temperature is calculated by using the square root function to measure the influencing factors of sharp edge feature clarity.

[0067] It should be noted that the design of the sharp edge feature definition prediction model is based on the understanding of various factors that affect the sharp edge feature definition and their interactions. The model comprehensively considers multiple variables such as stamping pressure, stamping speed, temperature, lubricant usage, and forming times, and quantifies the impact of these factors on the sharp edge feature definition through mathematical expressions.

[0068] S1.3, based on the constructed mold wear degree prediction model and sharp edge feature clarity prediction model, each process parameter combination is input into the mold wear degree prediction model and sharp edge feature clarity prediction model, and the predicted mold wear degree and predicted sharp edge feature clarity of each process parameter combination are output;

[0069] The output results are standardized, and the comprehensive index is calculated based on the criteria of minimizing the degree of die wear and maximizing the sharp edge feature clarity, expressed as:

[0070] ;

[0071] in, It is a comprehensive index used to compare the advantages and disadvantages of different process parameter combinations. The smaller the value, the lower the degree of mold wear and the higher the sharp edge feature clarity, so the process parameter combination is better. represents the predicted degree of mold wear after standardization, represents the sharp edge feature clarity of the normalized prediction;

[0072] Arrange the comprehensive index of each process parameter combination in descending order, and select a group of process parameter combinations with the smallest comprehensive index as preliminary candidates.

[0073] It should be noted that the mold wear degree prediction model and the sharp edge feature clarity prediction model are constructed using historical production data sets to predict the mold wear degree and sharp edge feature clarity under different process parameter combinations, and a group of process parameter combinations are screened out as preliminary candidates, which achieves accurate prediction of the mold wear degree and sharp edge feature clarity. Its function and use is to quickly identify the optimal process parameter combination, and the beneficial effect is to improve the mold life and product quality, and reduce unnecessary testing costs.

[0074] S2. Use a multi-objective genetic algorithm to optimize the preliminary candidate process parameter combination and output the optimized process parameter combination.

[0075] The objective function is defined as minimizing the die wear and maximizing the sharp edge feature definition;

[0076] A portion of the preliminary candidate process parameter combinations is randomly selected as individuals in the initial population. When the preliminary candidate process parameter combinations are insufficient, the remaining individuals are supplemented by random generation.

[0077] For each individual, the performance under the two objective functions is calculated. A simulated two-point crossover operation is used to randomly select two points in each individual and exchange the gene fragments between the two points. Gaussian mutation is used to add a small variation to each gene in the individual according to the Gaussian distribution. The tournament selection method is used for optimization. Two individuals are randomly selected from the population each time, and the individual with higher fitness is selected to enter the next generation.

[0078] After each generation, all individuals are Pareto sorted to find individuals that are no worse than other individuals in any goal. For the Pareto sorted individuals, the crowding distance between them is calculated to maintain population diversity.

[0079] Set the maximum number of iterations and convergence conditions;

[0080] When the convergence condition is met, the algorithm is considered to have converged. When the number of optimizations reaches the set maximum number of iterations, the optimization is stopped.

[0081] The Pareto optimal solution set is selected from all individuals generated in the optimization process, and the individuals on the Pareto frontier are output as the optimized process parameter combination.

[0082] It should be noted that a multi-objective genetic algorithm is used to optimize the preliminary candidate process parameter combination, and the optimized process parameter combination is output, thereby achieving further optimization of the preliminary candidate parameter combination. Its function and purpose is to find the balance point between minimizing the degree of mold wear and maximizing the clarity of sharp edge features. The beneficial effect is to further improve the overall performance of the process parameter combination.

[0083] S3. Build a digital twin model of the automobile cover mold, input the optimized process parameter combination into the digital twin model, further fine-tune the process parameter combination, and output the final optimized process parameter combination.

[0084] S3.1. Use physics-based simulation software to build a three-dimensional model according to the actual size and shape of the mold, accurately simulate the geometric shape and position of the sharp edge part, set the corresponding material properties such as elastic modulus, Poisson's ratio and yield strength according to the actual material used, set boundary conditions that match the actual production environment (such as the position and constraints of fixed support points), and obtain the digital twin model of the automobile cover mold.

[0085] S3.2. Import the optimized process parameter combination into the digital twin model, start the simulation software for simulation, and output the dynamic changes of the simulated mold wear degree and the simulated sharp edge feature clarity during the stamping process;

[0086] Setting die wear thresholds and sharp edge feature clarity thresholds through statistical analysis of historical production data sets;

[0087] When the simulated mold wear degree is less than or equal to the mold wear degree threshold, and the simulated sharp edge feature clarity is greater than or equal to the sharp edge feature clarity threshold, no fine-tuning is performed, and the final optimized process parameter combination is directly output;

[0088] When the simulated die wear degree is greater than the die wear degree threshold, and the simulated sharp edge feature clarity is less than the sharp edge feature clarity threshold, the die wear degree is reduced and the sharp edge feature clarity is improved by fine-tuning the stamping pressure, stamping speed, temperature, lubricant usage, forming cycle and forming times;

[0089] When the simulated die wear degree is greater than the die wear degree threshold, and the simulated sharp edge feature clarity is greater than or equal to the sharp edge feature clarity threshold, the die wear degree is reduced by reducing the stamping pressure and increasing the amount of lubricant used, while ensuring that the sharp edge feature clarity is not less than the sharp edge feature clarity threshold;

[0090] When the simulated die wear degree is less than or equal to the die wear degree threshold, and the simulated sharp edge feature clarity is less than the sharp edge feature clarity threshold, the sharp edge feature clarity is improved by increasing the stamping pressure and stamping speed, while ensuring that the die wear degree does not exceed the die wear degree threshold;

[0091] After fine-tuning, the digital twin simulation is performed again until the simulated mold wear degree is less than or equal to the mold wear degree threshold, and the simulated sharp edge feature clarity is greater than or equal to the sharp edge feature clarity threshold, and the final optimized process parameter combination is output.

[0092] It should be noted that by building a digital twin model of the automobile cover mold, inputting the optimized process parameter combination into the digital twin model, further fine-tuning the process parameter combination, and outputting the final optimized process parameter combination, virtual verification and adjustment are achieved through the digital twin model. The function and purpose is to verify and further optimize the process parameter combination. The beneficial effect is to ensure that the expected mold performance and product quality can be achieved in actual production.

[0093] This embodiment also provides a process parameter optimization system for automobile panel molds, including a process parameter combination screening module, which is responsible for building a mold wear degree prediction model and a sharp edge feature clarity prediction model using a historical production data set, predicting the mold wear degree and sharp edge feature clarity under different process parameter combinations, and screening out a group of process parameter combinations as preliminary candidates;

[0094] The process parameter optimization module is responsible for optimizing the preliminary candidate process parameter combinations using a multi-objective genetic algorithm and outputting the optimized process parameter combinations;

[0095] The process parameter simulation and adjustment module is responsible for building a digital twin model of the automobile cover mold, inputting the optimized process parameter combination into the digital twin model, further fine-tuning the process parameter combination, and outputting the final optimized process parameter combination.

[0096] This embodiment also provides a computer device, which is suitable for the case of a method for optimizing process parameters of automobile cover molds, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the method for optimizing process parameters of automobile cover molds as proposed in the above embodiment.

[0097] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0098] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for optimizing the process parameters of automobile cover molds proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0099] In summary, the present invention constructs a mold wear degree prediction model and a sharp edge feature clarity prediction model, and uses historical production data sets for data preprocessing, which not only improves the model prediction accuracy, but also can quickly identify the optimal process parameter combination, greatly reducing unnecessary experimental costs; uses a multi-objective genetic algorithm to optimize the preliminary candidate process parameter combination, and effectively finds the balance point between minimizing the mold wear degree and maximizing the sharp edge feature clarity, further improving the overall performance of the process parameter combination; by defining the objective function, initializing the population and performing genetic operations, as well as maintaining population diversity, it ensures that the algorithm efficiently advances toward the established goal, increases the possibility of finding a satisfactory solution, and by constructing a digital twin model, the optimized process parameter combination is input into the model for virtual verification and adjustment, ensuring that the expected mold performance and product quality can be achieved in actual production.

[0100] Example 2

[0101] Referring to Table 1, which is the second embodiment of the present invention, in order to further verify the advancement of the present invention, experimental simulation data of the automobile panel mold process parameter optimization method are provided.

[0102] In order to verify the effectiveness of the present invention, the following examples were studied. First, a historical production data set of automobile cover molds produced by XYZ Company in the past three years was collected. The data set includes but is not limited to key information such as mold number, mold material, mold size, mold shape, mold surface treatment, wear position, wear degree, wear rate, wear mode, sharp edge position, sharp edge angle, sharp edge width, sharp edge height, sharp edge shape, sharp edge clarity, stamping pressure, stamping speed, temperature, lubricant use, forming times and forming cycles.

[0103] In the data preprocessing stage, the Python Pandas library is used to read the historical production data set, and the dropna() function is used to delete rows with missing values, and the Z-score method is used to identify and delete outliers. Next, the mold wear degree prediction model is constructed using the processed historical production data set. and sharp edge feature clarity prediction model .

[0104] Then, based on these two models, each process parameter combination is input into the model, and the predicted die wear degree and predicted sharp edge feature clarity of each process parameter combination are output. The output results are standardized, and the comprehensive index is calculated based on the criteria of minimizing die wear degree and maximizing sharp edge feature clarity.

[0105] After the preliminary candidate process parameter combinations are determined, they are optimized using a multi-objective genetic algorithm, with the objective function defined as minimizing die wear and maximizing sharp edge feature clarity. The algorithm uses two-point crossover operation, Gaussian mutation, and tournament selection methods. The maximum number of iterations is set to 100, and the convergence condition is that there is no significant improvement for 20 consecutive generations. The Pareto optimal solution set is selected from all individuals generated during the optimization process.

[0106] Finally, a digital twin model of the automotive panel mold is constructed, and a three-dimensional model is established based on the actual size and shape of the mold to accurately simulate the geometric shape and position of the sharp edge. The optimized process parameter combination is imported into the digital twin model for simulation, and the dynamic changes of the simulated mold wear degree and the simulated sharp edge feature clarity during the stamping process are output.

[0107] The details are shown in Table 1:

[0108] Table 1 Experimental record table

[0109]

[0110] By analyzing the data in Table 1, it can be seen that the process parameter combination P2 performs best in comprehensive indicators, with the lowest predicted die wear (0.025) and the highest predicted sharp edge feature clarity (0.88). Compared with other combinations, P2 has a slightly lower stamping pressure, moderate stamping speed, suitable temperature, lower lubricant usage, and longer forming cycle. These parameters work together to make the die wear significantly lower than other combinations, while the sharp edge feature clarity is higher.

[0111] Specifically, by comparing with P1, the stamping pressure of P2 was reduced by 20MPa, the stamping speed was reduced by 2mm / s, the temperature was reduced by 5°C, and the amount of lubricant used was reduced by 3ml. These changes all helped to reduce the degree of die wear, and at the same time, by moderately increasing the forming cycle, the sharp edge feature clarity was improved. Compared with P3 and P4, although the stamping pressure was similar, the optimization of P2 in temperature, lubricant usage and forming cycle was more conducive to improving the sharp edge feature clarity.

[0112] In addition, the stamping pressure and temperature of P5 are higher, which leads to higher die wear and lower sharp edge feature clarity. P6 slightly adjusts some parameters based on P2, but the overall index decreases slightly.

[0113] In summary, the model and method proposed in the present invention can effectively optimize the combination of process parameters, minimize the degree of mold wear and maximize the clarity of sharp edge features, significantly improve the mold life and product quality, reduce unnecessary testing costs, and reflect the innovation and practicality of the invention content.

[0114] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for optimizing process parameters of automobile panel molds, characterized in that: include, The mold wear degree prediction model and sharp edge feature clarity prediction model are constructed using the historical production data set to predict the mold wear degree and sharp edge feature clarity under different process parameter combinations, and a group of process parameter combinations are selected as preliminary candidates; Use a multi-objective genetic algorithm to optimize the preliminary candidate process parameter combination and output the optimized process parameter combination; Build a digital twin model of the automotive panel mold, input the optimized process parameter combination into the digital twin model, further fine-tune the process parameter combination, and output the final optimized process parameter combination; The historical production data set includes punching pressure, punching speed, temperature, lubricant usage, forming times and forming cycles; The method of using the historical production data set to construct a mold wear degree prediction model and a sharp edge feature clarity prediction model includes the following steps: Use the Python Pandas library to read historical production data sets, use the dropna() function to delete rows with missing values, and use the Z-score method to identify and delete outliers; The processed historical production data set is used to build a mold wear degree prediction model and a sharp edge feature clarity prediction model; The mold wear degree prediction model is expressed as, ； in, Indicates the predicted degree of die wear, Indicates the number of forming times, Indicates the stamping pressure, Indicates the punching speed, Indicates the forming cycle, Indicates temperature, represents the average value of stamping pressure, L represents the amount of lubricant used, Indicates the standard deviation of punching pressure; The sharp edge feature clarity prediction model is expressed as, ； in, represents the predicted sharp edge feature clarity, i represents the index of the forming times, Indicates the amount of lubricant used after forming n times.

2. The method for optimizing process parameters of automobile panel mold according to claim 1, characterized in that: The method of predicting the degree of mold wear and sharp edge feature clarity under different process parameter combinations and selecting a set of process parameter combinations as preliminary candidates comprises the following steps: Based on the constructed mold wear degree prediction model and sharp edge feature clarity prediction model, each process parameter combination is input into the mold wear degree prediction model and the sharp edge feature clarity prediction model, and the predicted mold wear degree and predicted sharp edge feature clarity of each process parameter combination are output; The output results are standardized, and the comprehensive index is calculated based on the criteria of minimizing the degree of die wear and maximizing the sharp edge feature clarity, expressed as: ； in, Represents a comprehensive indicator, represents the predicted degree of mold wear after standardization, represents the sharp edge feature clarity of the normalized prediction; Arrange the comprehensive index of each process parameter combination in descending order, and select a group of process parameter combinations with the smallest comprehensive index as preliminary candidates.

3. The method for optimizing process parameters of automobile panel mold according to claim 2, characterized in that: The multi-objective genetic algorithm is used to optimize the preliminary candidate process parameter combination and output the optimized process parameter combination, including the following steps: The objective function is defined as minimizing the die wear and maximizing the sharp edge feature definition; A portion of the preliminary candidate process parameter combinations is randomly selected as individuals in the initial population. When the preliminary candidate process parameter combinations are insufficient, the remaining individuals are supplemented by random generation. For each individual, the performance under the two objective functions is calculated, and the simulated two-point crossover operation, Gaussian mutation and tournament selection methods are used for optimization. Individuals with higher fitness are selected to enter the next generation. After each generation, all individuals are Pareto sorted to find the individuals that are no worse than other individuals in any goal; Set the maximum number of iterations and convergence conditions; When the convergence condition is met, the algorithm is considered to have converged. When the number of optimizations reaches the set maximum number of iterations, the optimization is stopped. The Pareto optimal solution set is selected from all individuals generated in the optimization process, and the individuals on the Pareto frontier are output as the optimized process parameter combination.

4. The method for optimizing process parameters of automobile panel mold according to claim 3, characterized in that: Using physics-based simulation software to build a digital twin model of an automotive panel mold includes the following steps: Using physics-based simulation software, a three-dimensional model is established according to the actual size and shape of the mold, the geometry and position of the sharp edges are accurately simulated, the corresponding elastic modulus, Poisson's ratio and yield strength are set according to the actual material used, and the boundary conditions matching the actual production environment are set to obtain the digital twin model of the automotive cover mold.

5. The method for optimizing process parameters of automobile panel mold according to claim 4, characterized in that: Constructing a digital twin model of the automotive panel mold, inputting the optimized process parameter combination into the digital twin model, further fine-tuning the process parameter combination, and outputting the final optimized process parameter combination, including the following steps: Import the optimized process parameter combination into the digital twin model, start the simulation software for simulation, and output the dynamic changes of the simulated die wear degree and the simulated sharp edge feature clarity during the stamping process; Setting die wear thresholds and sharp edge feature clarity thresholds through statistical analysis of historical production data sets; When the simulated mold wear degree is less than or equal to the mold wear degree threshold, and the simulated sharp edge feature clarity is greater than or equal to the sharp edge feature clarity threshold, no fine-tuning is performed, and the final optimized process parameter combination is directly output; When the simulated die wear degree is greater than the die wear degree threshold, and the simulated sharp edge feature clarity is less than the sharp edge feature clarity threshold, the die wear degree is reduced and the sharp edge feature clarity is improved by fine-tuning the stamping pressure, stamping speed, temperature, lubricant usage, forming cycle and forming times; When the simulated die wear degree is greater than the die wear degree threshold, and the simulated sharp edge feature clarity is greater than or equal to the sharp edge feature clarity threshold, the die wear degree is reduced by reducing the stamping pressure and increasing the amount of lubricant used, while ensuring that the sharp edge feature clarity is not less than the sharp edge feature clarity threshold; When the simulated die wear degree is less than or equal to the die wear degree threshold, and the simulated sharp edge feature clarity is less than the sharp edge feature clarity threshold, the sharp edge feature clarity is improved by increasing the stamping pressure and stamping speed, while ensuring that the die wear degree does not exceed the die wear degree threshold; After fine-tuning, the digital twin simulation is performed again until the simulated mold wear degree is less than or equal to the mold wear degree threshold, and the simulated sharp edge feature clarity is greater than or equal to the sharp edge feature clarity threshold, and the final optimized process parameter combination is output.

6. A system for optimizing process parameters of automobile panel molds, based on the method for optimizing process parameters of automobile panel molds according to any one of claims 1 to 5, characterized in that: include, The process parameter combination screening module is responsible for building a mold wear degree prediction model and a sharp edge feature clarity prediction model using historical production data sets, predicting the mold wear degree and sharp edge feature clarity under different process parameter combinations, and screening out a group of process parameter combinations as preliminary candidates; The process parameter optimization module is responsible for optimizing the preliminary candidate process parameter combinations using a multi-objective genetic algorithm and outputting the optimized process parameter combinations; The process parameter simulation and adjustment module is responsible for building a digital twin model of the automotive cover mold, inputting the optimized process parameter combination into the digital twin model, further fine-tuning the process parameter combination, and outputting the final optimized process parameter combination.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for optimizing the process parameters of a mold for an automobile cover part according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for optimizing process parameters of a mold for an automobile cover part according to any one of claims 1 to 5 are implemented.

Images