Mold manufacturing optimization method and system

Abstract

The invention relates to the technical field of information, in particular to a mold manufacturing optimization method and system in the technical field of mold manufacturing, and the method comprises the following steps: selecting high-toughness and high-wear-resistance mold steel according to mold structure design requirements, optimizing heat treatment process parameters through a simulated annealing algorithm, and improving the hardness and toughness of a mold material; real-time data in the mold base machining process are obtained, the size precision and the surface quality of the mold base are controlled by dynamically adjusting machining parameters, and the mold assembly process requirements are met; predicting the hardness, toughness and wear resistance of the mold by adopting a mold performance prediction model according to the mold blank material and the heat treatment and surface treatment process parameters, and judging whether the mold test verification standard is met or not; and if the mold performance prediction result does not meet the requirement, adjusting the material components and preparation process parameters of the mold base, and preparing and processing the mold base again until the mold performance meets the mold test verification standard.

Description

Technical Field

[0001] The present invention relates to the field of information technology, specifically to the field of mold manufacturing technology, and in particular to a mold manufacturing optimization method and system. Background Art

[0002] In the development process of hardware molds and mold bases, the selection and performance of steel have an important impact on the processing efficiency, service life and production cost of the mold. At present, the commonly used mold steel has certain contradictions and deficiencies in terms of hardness, toughness and wear resistance, and it is difficult to meet the requirements of efficient processing and long life at the same time. For example, although steel with high hardness has good wear resistance, it has poor toughness and is prone to microcracks during processing, leading to early failure of the mold; while steel with good toughness is not easy to break, but the hardness and wear resistance are relatively low. In mass production, it is easy to have problems such as reduced dimensional accuracy and increased mold wear, which requires frequent repair or replacement, increasing production costs.

[0003] In addition, the demoulding performance of the mold is also a key factor affecting production efficiency. The roughness, taper and lubricity of the mold surface will affect the smoothness of demoulding. The performance of the commonly used mold steel in these aspects needs to be further optimized to improve the demoulding efficiency and reduce the wear and adhesion of the mold surface. Therefore, it is urgent to develop a new type of mold steel with better comprehensive performance, while ensuring sufficient hardness and wear resistance, taking into account good toughness and demoulding performance, so as to improve the processing efficiency and service life of hardware molds and reduce production costs. This requires systematic research and optimization in terms of material composition, heat treatment process, surface treatment, etc., to develop special steel that meets the development needs of hardware molds and mold bases, and promote technological progress and industrial upgrading in the hardware processing industry. Summary of the invention

[0004] The present invention provides a mold manufacturing optimization method, which comprises the following steps:

[0005] S101. According to the requirements of mold structure design, select mold steel with high toughness and high wear resistance, optimize heat treatment process parameters through simulated annealing algorithm, and improve the hardness and toughness of mold material;

[0006] S102, preparing a mold base by a process combining casting and heat treatment, and controlling the dimensional accuracy and internal defects of the mold base by optimizing casting process parameters and heat treatment temperature to meet the mold base processing allowance requirements;

[0007] S103. According to the surface quality requirements of the mold base, the particle swarm optimization algorithm is used to optimize the surface treatment process, and the matching degree between the mold base and the mold cavity is improved by controlling the surface roughness and lubricity, thereby reducing the mold base processing amount;

[0008] S104, acquiring real-time data during the mold base processing, and dynamically adjusting the processing parameters to control the dimensional accuracy and surface quality of the mold base to meet the mold assembly process requirements;

[0009] S105, using a mold performance prediction model, predicting the hardness, toughness and wear resistance of the mold according to mold base material, heat treatment and surface treatment process parameters, and determining whether the mold trial verification standard is met;

[0010] S106. If the mold performance prediction result does not meet the requirements, the mold base material composition and preparation process parameters are adjusted, and the mold base is re-prepared and processed until the mold performance meets the mold trial verification standard;

[0011] S107. Obtain actual performance data of the mold through mold trial verification, use a mold life prediction model, combine mold repair and maintenance strategies, predict the service life of the mold, and formulate a mold remanufacturing plan;

[0012] S108. According to the complexity of the mold structure and the processing accuracy requirements, a cost estimation model is used to calculate the manufacturing cost of the mold. By optimizing the mold base preparation process and the mold processing process, the mold cost is controlled within the budget.

[0013] The present invention provides a mold manufacturing optimization system, which mainly includes:

[0014] The material selection module is used to select mold steel with high toughness and high wear resistance according to the mold structure design requirements, and optimize the heat treatment process parameters through the simulated annealing algorithm to improve the hardness and toughness of the mold material;

[0015] The process optimization module is used to prepare the mold base by combining casting and heat treatment. By optimizing the casting process parameters and heat treatment temperature, the dimensional accuracy and internal defects of the mold base are controlled to meet the mold base processing allowance requirements;

[0016] The mold base preparation module is used to optimize the surface treatment process based on the mold base surface quality requirements by using the particle swarm optimization algorithm. By controlling the surface roughness and lubricity, the matching degree between the mold base and the mold cavity is improved, and the mold base processing amount is reduced;

[0017] The surface treatment module is used to obtain real-time data during the mold base processing, and dynamically adjust the processing parameters to control the dimensional accuracy and surface quality of the mold base to meet the mold assembly process requirements;

[0018] The processing control module is used to use the mold performance prediction model to predict the hardness, toughness and wear resistance of the mold according to the mold base material, heat treatment and surface treatment process parameters, and determine whether the mold trial verification standard is met;

[0019] The performance prediction module is used to adjust the mold base material composition and preparation process parameters if the mold performance prediction result does not meet the requirements, and re-prepare and process the mold base until the mold performance meets the mold trial verification standard;

[0020] The life prediction module is used to obtain the actual performance data of the mold through mold trial verification, adopt the mold life prediction model, combine the mold repair and maintenance strategy, predict the service life of the mold, and formulate the mold remanufacturing plan;

[0021] The cost control module is used to calculate the manufacturing cost of the mold based on the complexity of the mold structure and the processing accuracy requirements, using the cost estimation model, and to control the mold cost within the budget by optimizing the mold base preparation process and the mold processing process.

[0022] The technical solution provided by the embodiment of the present invention may have the following beneficial effects:

[0023] The present invention discloses a method for optimizing mold manufacturing. The method selects mold steel with high toughness and high wear resistance, and optimizes the heat treatment process in combination with a simulated annealing algorithm to improve the performance of the mold material. A mold base is prepared by a process combining casting and heat treatment, and a particle swarm optimization algorithm is used to optimize the surface treatment process to improve the quality of the mold base. During the processing, data is acquired in real time and parameters are adjusted dynamically to ensure that the mold base meets the assembly requirements. The present invention also introduces a mold performance prediction model and a life prediction model, and combines trial mold verification to achieve precise control of mold performance and life prediction. The manufacturing process is optimized through a cost estimation model to control costs within the budget. This method realizes intelligent optimization of the entire mold manufacturing process, significantly improves mold quality, performance and service life, and effectively controls manufacturing costs. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention is described in detail below in conjunction with specific embodiments.

[0025] A mold manufacturing optimization method in this embodiment may specifically include:

[0026] S101. According to the requirements of mold structure design, select mold steel with high toughness and high wear resistance, optimize heat treatment process parameters through simulated annealing algorithm, and improve the hardness and toughness of mold material.

[0027] The mold structure design requirements are obtained to determine the high toughness and high wear resistance requirements of the mold steel; according to the mold steel performance requirements, the mold steel that meets the high toughness and high wear resistance is selected; a simulated annealing algorithm is used to optimize the heat treatment process parameters of the mold steel to obtain the optimized heat treatment process parameters; according to the optimized heat treatment process parameters, the hardness value and toughness value of the mold material are calculated; it is determined whether the hardness value and toughness value meet the mold structure design requirements; if the hardness value and toughness value do not meet the mold structure design requirements, the parameters of the simulated annealing algorithm are adjusted, and the optimization is re-executed until the hardness value and toughness value that meet the mold structure design requirements are obtained; and the final heat treatment process parameters that meet the mold structure design requirements are determined.

[0028] Specifically, the mold structure design requirements are the basis for manufacturing high-quality molds. High toughness and high wear resistance are the key performance indicators of mold steel, which directly affect the service life and processing accuracy of the mold. It is crucial to select the right mold steel. For example, for cold working molds, Cr12Mo1V1 steel can be selected, which has a good balance of wear resistance and toughness. For hot working molds, H13 steel can be considered, which can still maintain excellent mechanical properties at high temperatures. The simulated annealing algorithm is a heuristic optimization method used to solve complex combinatorial optimization problems. In the optimization of mold steel heat treatment process parameters, parameters such as temperature, holding time, and cooling rate can be used as optimization variables. The algorithm simulates the metal cooling process and continuously adjusts the parameters to find the optimal solution. For example, for H13 steel, the initial annealing temperature can be set to 1020℃, and then the temperature can be gradually reduced, while adjusting the holding time until the best parameter combination is found. After the heat treatment process parameters are optimized, the hardness and toughness values ​​of the material need to be calculated and verified. Hardness can be measured by a Rockwell hardness tester, while toughness can be evaluated by an impact test. Taking H13 steel as an example, after optimized heat treatment process, a hardness of 52HRC and 20J / cm 2impact toughness. These values ​​need to be compared with the requirements of the mold structure design to determine whether they meet the use requirements. If the calculated hardness and toughness values ​​fail to meet the requirements, the parameters of the simulated annealing algorithm need to be adjusted and re-optimized. This may include changing the initial temperature, cooling rate, or neighborhood search range. For example, if the hardness is insufficient, you can consider increasing the quenching temperature or extending the holding time; if the toughness is insufficient, you may need to adjust the tempering temperature or number of times. Through repeated optimization and verification, the hardness and toughness values ​​that meet the requirements of the mold structure design are finally determined, so as to obtain the optimal heat treatment process parameters. This process can not only improve the performance and life of the mold, but also reduce production costs and improve production efficiency. For example, for a complex injection mold, the optimized heat treatment process may increase the mold life by 30%, while reducing the processing allowance by 15%, greatly improving the economy and practicality of the mold. This method of determining heat treatment process parameters based on algorithm optimization can find the optimal solution more quickly and accurately than the traditional empirical method, and is particularly suitable for the process development of new mold steels or complex mold structures. It not only improves the scientificity and accuracy of mold manufacturing, but also provides new ideas and methods for technological innovation in the mold industry.

[0029] S102. Prepare the mold base by combining casting and heat treatment, and control the dimensional accuracy and internal defects of the mold base by optimizing the casting process parameters and the heat treatment temperature to meet the mold base processing allowance requirements.

[0030] Obtain preset mold base dimensional accuracy thresholds and defect thresholds; obtain mold base casting parameters and heat treatment temperature data, and establish a casting parameter and temperature optimization model; iteratively calculate the casting parameters and heat treatment temperature according to the optimization model to obtain an optimal parameter combination; generate a mold base casting and heat treatment process plan according to the optimal parameter combination, and output a process parameter file; control the casting equipment and heat treatment equipment through the process parameter file to execute the mold base preparation process; obtain dimensional data and defect detection data during the mold base preparation process; determine whether the dimensional data and defect detection data meet the preset mold base dimensional accuracy thresholds and defect thresholds; if the dimensional data or defect detection data does not meet the threshold, adjust the optimization model parameters, re-perform iterative calculations, and obtain an adjusted optimal parameter combination; update the mold base casting and heat treatment process plan according to the adjusted optimal parameter combination to complete the mold base preparation process.

[0031] Specifically, the optimization of mold base casting and heat treatment process is the key link to improve the quality of molds. First, the mold base casting parameters and heat treatment temperature data are obtained. These data include casting parameters such as casting temperature, pouring speed, cooling time, and heat treatment parameters such as quenching temperature and tempering temperature. At the same time, the dimensional accuracy threshold is preset, such as the mold base dimensional error does not exceed ±0.05mm. Establishing a casting parameter and temperature optimization model is the core of process optimization. The model can use the response surface method, take the casting parameters and heat treatment temperature as independent variables, and take the mold base dimensional accuracy and performance indicators as dependent variables to construct a quadratic polynomial regression model. For example, the casting temperature can be set in the range of 1450℃-1550℃, and the heat treatment temperature can be set in the range of 850℃-950℃. The test data is obtained through orthogonal experimental design to establish an optimization model. The iterative calculation of the optimization model uses a genetic algorithm. First, an initial population is generated, and each individual represents a set of casting and heat treatment parameters. A new population is generated through operations such as crossover and mutation, and the fitness function is used to evaluate the quality of each individual. The fitness function can be designed as the square sum of the deviations between the dimensional accuracy and the target value. After multiple generations of iterations, the optimal parameter combination is finally obtained. Based on the optimal parameter combination, a process plan is generated, including specific casting temperature, holding time, pouring speed, cooling curve, as well as heat treatment heating rate, holding time, cooling medium, etc. These parameters are output in the form of process parameter files for controlling casting equipment and heat treatment equipment. For example, the casting temperature is set to 1500°C, the pouring speed is 0.5kg / s, the heat treatment quenching temperature is 900°C, and oil cooling is performed after holding for 2 hours. During the preparation of the mold base, a three-coordinate measuring machine is used to obtain dimensional data, and an ultrasonic flaw detector is used to detect internal defects. If the dimensional deviation is detected to exceed

[0032] If the size is less than ±0.05mm or there are internal cracks exceeding 2mm, the optimization model needs to be adjusted. The adjustment method can be to increase the weight of certain parameters in the model or to expand the parameter search range. For example, if it is found that the size is too large, the search lower limit of the casting temperature can be appropriately lowered and the optimization calculation can be re-performed. Through this closed-loop optimization method, the preparation quality of the mold base is continuously improved, and finally a mold blank that meets the requirements is obtained. The advantage of this method is that it can dynamically adjust the process parameters according to the actual production situation, effectively respond to the influence of factors such as changes in raw material batches and fluctuations in equipment status, and ensure the consistency and reliability of the mold blank.

[0033] S103. According to the surface quality requirements of the mold base, the particle swarm optimization algorithm is used to optimize the surface treatment process. By controlling the surface roughness and lubricity, the matching degree between the mold base and the mold cavity is improved, and the mold base processing amount is reduced.

[0034] The surface roughness data and lubricity index of the mold base are obtained, and the roughness data and lubricity index are used to establish a surface quality evaluation model; according to the surface quality evaluation model, the objective function and constraint conditions of the particle swarm optimization algorithm are determined; the particle swarm optimization algorithm is used to search for the optimal surface treatment process parameter combination in a preset parameter space; the optimal surface treatment process parameter combination is input into the surface treatment equipment to perform mold base surface treatment; the surface data of the mold base after treatment is obtained, and the matching index between the mold base surface and the mold cavity surface is calculated; if the matching index does not reach the preset threshold, the weight coefficient of the particle swarm optimization algorithm is adjusted, and the optimization process is re-executed until the matching index reaches the preset threshold; according to the final determined process parameter combination, the mold base surface treatment process plan is output.

[0035] Specifically, mold base surface quality evaluation is a key link, involving multiple parameters and indicators. Surface roughness data can be obtained by precision instrument measurement, such as using an optical profilometer to scan the mold base surface to obtain micron-level surface height distribution data. Lubricity indicators can be evaluated by friction coefficient testing, such as using a reciprocating friction and wear tester to measure the dynamic friction coefficient between the mold base surface and a specific material. These data together constitute the input of the surface quality evaluation model. When establishing a surface quality evaluation model, a multi-objective decision-making method can be used. For example, the surface roughness Ra value, the maximum height Rz value, and the lubricity index can be used as evaluation indicators and assigned different weights. Assuming that the mold use environment has high requirements for lubricity, the weight of the lubricity index can be set to 0.5, and the weights of the Ra value and the Rz value can be set to 0.25 each. Particle swarm optimization algorithm is an intelligent optimization method suitable for solving complex nonlinear optimization problems. In this case, the objective function can be defined as minimizing the comprehensive score of the surface quality evaluation model. The constraints may include the range of values ​​of the surface treatment process parameters, such as the polishing time is limited to 30-120 minutes, the polishing pressure is limited to 0.5-2.0MPa, etc. When searching for the optimal surface treatment process parameter combination in the preset parameter space, the size of the particle swarm can be set to 50 and the maximum number of iterations can be set to 100. Each particle represents a set of possible process parameter combinations, such as polishing time, pressure, speed, etc. Through iterative calculation, the particle swarm will gradually converge to the optimal solution. The optimized process parameter combination may be as follows: polishing time 75 minutes, pressure 1.2MPa, speed 60rpm. These parameters are input into the CNC polishing machine to perform the mold base surface treatment process. After the treatment is completed, the mold base surface data is collected again to calculate the matching index with the mold cavity surface. The matching index can be calculated by the shape error analysis method. For example, a three-coordinate measuring machine is used to scan the processed mold base surface and the mold cavity surface to obtain point cloud data. The average deviation and maximum deviation between the two surfaces are calculated by the least squares fitting algorithm. Assume that the preset matching threshold is that the average deviation does not exceed 0.05mm and the maximum deviation does not exceed 0.1mm. If the calculation results show that the average deviation is 0.07mm and the maximum deviation is 0.15mm, which does not reach the preset threshold, the weight coefficient of the particle swarm optimization algorithm needs to be adjusted. The weight of the surface roughness index can be increased from 0.25 to 0.35, and the weight of the lubricity index can be reduced accordingly to better balance the various performances. After multiple iterations of optimization, the final process parameter combination may be: polishing time 90 minutes, pressure 1.5MPa, speed 70rpm. This set of parameters can further improve the surface roughness while ensuring good lubricity, so that the matching degree between the mold base surface and the mold cavity surface meets the expected requirements. Finally, this set of parameters is output as the core content of the mold base surface treatment process plan to provide reliable technical support for the subsequent mold manufacturing process.

[0036] S104, obtaining real-time data during the mold base processing, and dynamically adjusting the processing parameters to control the dimensional accuracy and surface quality of the mold base to meet the mold assembly process requirements.

[0037] The vibration, temperature and pressure data collected by the sensor network in the processing equipment during the processing are obtained, and the data are processing data; the processing data are input into a pre-established neural network model to identify the processing state characteristics corresponding to the processing data; according to the processing state characteristics, the deviation value between the current processing parameter and the target parameter is calculated; a PID control algorithm is used to generate a processing parameter adjustment instruction according to the deviation value; the processing parameter adjustment instruction is sent to the processing equipment controller to perform parameter optimization operations; the processed mold base size data collected by the online measurement system is obtained, and the size error corresponding to the mold base size data is calculated; a genetic algorithm is used to optimize the weight parameters of the neural network model according to the size error to obtain an optimized neural network model; and the optimized neural network model is applied to the subsequent processing parameter optimization process.

[0038] Specifically, deploying sensor networks in processing equipment is a key step in achieving intelligent manufacturing. Taking mold base processing as an example, accelerometers, thermocouples, and pressure sensors can be installed on the lathe spindle, tool holder, and workpiece fixture. These sensors collect vibration frequency, temperature change, and cutting force data in real time, providing a basis for subsequent analysis. The collected data is input into a pre-trained neural network model, which can use a convolutional neural network structure to extract processing state features through multi-layer convolution and pooling. For example, high-frequency vibration may indicate tool wear, and a sudden temperature rise may mean insufficient cooling. The identified features are compared with preset parameters to calculate the deviation value. The deviation value is used to generate adjustment instructions for the PID control algorithm. Assuming that the spindle vibration frequency is detected to exceed the threshold, the PID controller will generate instructions to reduce the spindle speed or increase the feed rate based on the deviation size and change trend. These instructions are sent to the CNC system of the processing equipment through the field bus to achieve real-time parameter optimization. Online measurement systems, such as laser scanners, can obtain mold base size data immediately after processing. By comparing the actual size with the design size, the error value of each key part is calculated. These error data are not only used for quality control, but also as a basis for optimizing the neural network model. Genetic algorithms are used to optimize the weight parameters of neural networks. First, the existing weights are encoded as "chromosomes", and then new weight combinations are generated through operations such as crossover and mutation. Each set of weights is verified with historical data to calculate the prediction accuracy. The weight combination with high accuracy is retained and further optimized, and finally a neural network model with better performance is obtained. This closed-loop optimization system can continuously improve processing accuracy and efficiency. For example, in a batch of mold base processing, the system detected an abnormal increase in temperature. The neural network model identified that this may cause thermal expansion, and the PID controller immediately reduced the feed speed and increased the coolant flow. At the same time, online measurement found that some dimensions still had slight deviations, and the genetic algorithm adjusted the model weights accordingly, improving the accuracy of the prediction of the impact of thermal expansion. After several batches of self-learning and optimization, the system's processing accuracy under similar working conditions was significantly improved, and the scrap rate was reduced by 15%. This intelligent manufacturing method is not only applicable to mold base processing, but can also be extended to other precision manufacturing fields. Through continuous data collection, analysis and optimization, the manufacturing process becomes more intelligent and efficient, providing strong support for improving product quality and production efficiency.

[0039] S105. Use the mold performance prediction model to predict the hardness, toughness and wear resistance of the mold according to the mold base material, heat treatment and surface treatment process parameters to determine whether the mold trial verification standard is met.

[0040] The mold base material properties, heat treatment process parameters and surface treatment process parameters are obtained, and a pre-established mold performance prediction model is input; the mold performance prediction model is used to calculate the predicted values ​​of mold hardness, toughness and wear resistance according to the mold base material properties, the heat treatment process parameters and the surface treatment process parameters; a preset hardness threshold, toughness standard and wear resistance requirement are obtained; it is determined whether the predicted value of the mold hardness reaches the preset hardness threshold; if so, it is determined whether the predicted value of the mold toughness meets the preset toughness standard; if so, it is further determined whether the predicted value of the mold wear resistance meets the preset wear resistance requirement; based on the judgment results of the hardness, toughness and wear resistance, it is determined whether the mold performance meets the preset mold trial verification standard; if so, a qualified mold performance result is output; if not, an unqualified mold performance result is output.

[0041] Specifically, the mold performance prediction model is a key link in the mold manufacturing process. By inputting the mold base material properties, heat treatment process parameters and surface treatment process parameters, the mold hardness, toughness and wear resistance can be predicted. For example, for a commonly used mold steel material, its chemical composition includes elements such as carbon, chromium, and molybdenum. The heat treatment process may involve parameters such as quenching temperature, holding time and tempering temperature, and the surface treatment may include processes such as nitriding or chrome plating. These parameters jointly affect the final performance of the mold. The mold hardness is an important indicator to measure its deformation resistance. The prediction model may consider factors such as the carbon content and quenching temperature of the material to estimate the hardness value. Assuming that the preset hardness threshold is HRC60, the hardness value predicted by the model is HRC62, which means that the preset threshold is reached. After the hardness meets the standard, the toughness of the mold needs to be further evaluated. Toughness reflects the ability of the mold to resist impact and fracture. The model may analyze factors such as the ratio of alloy elements and the tempering process to predict toughness. If the preset toughness standard is that the impact energy is not less than 20 joules, and the predicted value is 25 joules, it can be determined that the toughness meets the requirements. After the toughness meets the standard, the wear resistance of the mold needs to be examined. Wear resistance determines the service life of the mold. The prediction model may combine factors such as surface treatment process and hardness value to estimate wear resistance. Assume that the preset wear resistance requirement is that the wear rate does not exceed 0.1mm 3 / Nm, the predicted value is 0.08mm 3 / Nm, it can be considered that the wear resistance meets the requirements. Taking into account the prediction results of hardness, toughness and wear resistance, it can be judged whether the mold performance meets the mold trial verification standard. This multi-dimensional evaluation method can fully reflect the performance of the mold and help to find potential problems before actual production. For example, if the hardness and wear resistance of a mold meet the standards, but the toughness is slightly lower than the requirements, it may be necessary to adjust the heat treatment process to improve the toughness while weighing the impact on other properties. Through this prediction and evaluation mechanism, the probability of mold trial failure can be effectively reduced and the success rate of mold manufacturing can be improved. At the same time, this method also provides direction for process optimization. If the prediction results do not meet the requirements, the material selection or process parameters can be adjusted in a targeted manner. This can not only save time and material costs, but also improve the overall quality and service life of the mold, providing reliable protection for downstream product manufacturing.

[0042] S106. If the mold performance prediction result does not meet the requirements, the mold base material composition and preparation process parameters are adjusted, and the mold base is re-prepared and processed until the mold performance meets the mold trial verification standard.

[0043] Obtain a mold performance prediction value; determine whether the mold performance prediction value is lower than a preset threshold; if the mold performance prediction value is lower than the preset threshold, extract mold base material composition information and process parameter information from a preset database; generate a mold base material composition adjustment item list and a process parameter adjustment item list according to the correlation between the mold base material composition information and the process parameter information; optimize the mold base material composition according to the mold base material composition adjustment item list to obtain an optimized mold base material composition; optimize the mold base preparation process parameters according to the process parameter adjustment item list to obtain an optimized mold base preparation process parameters; prepare a new mold base using the optimized mold base material composition and the optimized mold base preparation process parameters; obtain performance test data of the new mold base; compare the performance test data with a preset mold performance standard to obtain a judgment result on whether the mold performance meets the standard.

[0044] Specifically, mold performance prediction is a key link in the precision manufacturing industry. After obtaining the predicted value of mold performance, it needs to be compared with the preset threshold. Assuming that the predicted hardness value of a mold is 45HRC, and the preset threshold is 50HRC, the predicted value is lower than the threshold and needs to be optimized. In order to optimize the mold performance, the mold base material composition and process parameters are first extracted from the database. For example, the mold base material may be H13 hot working die steel, whose main components include carbon, chromium, molybdenum and vanadium. The process parameters may include quenching temperature, tempering temperature and holding time. According to the correlation between the composition ratio and the process parameters, a list of adjustment items can be generated. For example, increasing the carbon content can increase the hardness, but may reduce the toughness; increasing the quenching temperature can increase the hardness, but too high will lead to coarse grains. Therefore, the adjustment items may include: slightly increasing the carbon content (such as from 0.38% to 0.40%), increasing the quenching temperature (such as from 1020℃ to 1040℃), increasing the number of tempering, etc. With these adjustment items, the mold base material and process parameters can be optimized to obtain a new preparation process and processing method. The optimized process may include: adjusting the alloy ratio, increasing the quenching temperature, increasing the number of tempering, extending the holding time, etc. These adjustments are aimed at increasing the hardness of the mold while maintaining good toughness and wear resistance. The mold base is regenerated through the optimized preparation process and processing method. This process may involve steps such as re-melting, casting, and heat treatment. Each step needs to be strictly controlled to ensure the quality of the final product. The newly generated mold base needs to be tested for performance indicators to obtain performance data. This may include hardness testing (such as Rockwell hardness testing), impact toughness testing (such as Charpy impact testing), and wear resistance testing (such as pin-on-disc wear testing). Assume that the hardness test result of the new mold base is 52HRC and the impact toughness is 40J / cm 2 , the wear resistance loss is 0.015g / h. Finally, compare these performance data with the test mold standard to determine whether they meet the standard.

[0045] ≥50HRC, impact toughness ≥35J / cm 2 , the wear resistance loss is ≤0.02g / h, then it can be determined that the new mold base has met the performance requirements. This process not only ensures the quality of the mold, but also provides valuable data and experience for future mold design and optimization.

[0046] S107. Obtain the actual performance data of the mold through mold trial verification, use the mold life prediction model, combine the mold repair and maintenance strategy, predict the service life of the mold, and formulate a mold remanufacturing plan.

[0047] Acquire the mold trial data, and use the performance data to analyze the actual status of the mold; establish a mold performance database based on the mold trial data, and extract key features from the performance data; use a pre-established life prediction model to predict the mold service life. If the mold performance data is lower than a preset threshold, trigger the prediction model to calculate the remaining service life of the mold; optimize the life prediction model parameters according to the repair strategy data and the maintenance strategy data, and generate an optimized mold service life prediction result; determine the mold remanufacturing demand based on the service life prediction result. If the prediction result is lower than the preset life threshold, determine that the mold needs to be remanufactured, and start the remanufacturing plan formulation process; optimize the mold performance through the remanufacturing plan, and update the mold performance database; use machine learning technology to continuously optimize the life prediction model and the service life prediction model, and continuously improve the mold service life prediction accuracy.

[0048] Specifically, mold trial is a key step in evaluating mold performance. By collecting mold performance data under actual production conditions, a comprehensive mold performance database can be established. For example, for a car bumper mold, the product dimensional accuracy, surface quality, demolding difficulty and other indicators of each mold trial can be recorded. After analysis, these data can be used to extract key features, such as mold wear rate, deformation trend, etc. The life prediction model is an important tool for mold management. Taking injection molds as an example, a prediction model that considers mold materials, number of uses, production environment and other factors can be built based on historical data. When the mold performance data is lower than the preset threshold, such as the product qualification rate of a certain injection mold drops below 95%, the prediction model will be triggered to calculate the remaining life. Repair and maintenance strategies are essential to extend the life of the mold. For example, for stamping molds, a plan can be formulated for regular inspection and replacement of vulnerable parts. By optimizing these strategies, the parameters of the life prediction model can be adjusted to improve the prediction accuracy. If the prediction results show that the remaining life of the mold is lower than the preset threshold, such as 5,000 products are expected to be produced, the remanufacturing plan formulation process will be initiated. The remanufacturing plan aims to restore and improve mold performance. Taking die-casting molds as an example, it may involve repairing the cavity surface, replacing the cooling system, reheat treatment, etc. These measures can not only extend the life of the mold, but also improve product quality. After remanufacturing, it is necessary to update the mold performance database and record the improvement effect. Continuous optimization is the key to ensuring the accuracy of the prediction model. Through machine learning technology, new data can be continuously absorbed to adjust the model. For example, for a plastic bottle cap mold, the performance changes after each repair can be incorporated into the model to improve the accuracy of future life prediction. This series of measures forms a closed-loop system. Starting from the collection of trial mold data, through performance analysis, life prediction, remanufacturing decision-making, and finally back to performance improvement and data update. This systematic approach can significantly improve mold management efficiency, reduce unexpected downtime, optimize production plans, and ultimately achieve the purpose of extending the life of the mold and reducing production costs. By continuously accumulating data and optimizing models, this system can also provide valuable reference information for future mold design and manufacturing, and promote technological progress in the entire industry.

[0049] S108. According to the complexity of the mold structure and the processing accuracy requirements, a cost estimation model is used to calculate the manufacturing cost of the mold. By optimizing the mold base preparation process and the mold processing process, the mold cost is controlled within the budget.

[0050] The design parameters of the mold structure are obtained, and the complexity of the mold structure is determined by using a preset complexity analysis algorithm; the technical parameters of the mold processing are determined according to the complexity and the preset accuracy requirements, and the processing accuracy index is obtained; a pre-established cost estimation model is used, and the processing accuracy index and the complexity are input into the cost estimation model to calculate the manufacturing cost of the mold; if the mold manufacturing cost exceeds the preset budget range, the process optimization module is triggered to generate an optimization plan for the mold base preparation process; according to the optimization plan, the parameters of the mold processing process are adjusted, and the manufacturing cost of the mold is recalculated; it is determined whether the recalculated mold manufacturing cost is within the budget range, and if not, the process optimization module is iteratively executed; the final mold manufacturing cost and optimized process parameters are obtained, and a complete technical plan for mold manufacturing is generated.

[0051] Specifically, mold structure complexity analysis is a key step in the manufacturing process. Using a preset algorithm, the mold structure can be evaluated from multiple dimensions, such as geometric features, processing difficulty, etc. For example, for an automotive interior mold, it may be necessary to consider its surface complexity, number of detail features, and dimensional accuracy requirements. By analyzing these parameters, a complexity index can be given, such as 7 points in the range of 1-10, indicating a higher complexity. When determining the processing accuracy index, it is necessary to combine complexity and product requirements. Taking the above-mentioned automotive interior mold as an example, if the complexity is 7 points, it may be necessary to set accuracy indicators such as surface roughness Ra0.4μm and dimensional tolerance ±0.02mm. These indicators directly affect the selection of processing technology and processing time. The cost estimation model is an important tool for optimizing manufacturing solutions. The model may include factors such as material cost, processing time, and equipment depreciation. For a mold with a complexity of 7 points and high precision requirements, the estimated cost may reach 100,000 yuan. If the budget cap is 80,000 yuan, process optimization needs to be triggered. The process optimization module aims to reduce costs while ensuring quality. Possible optimization solutions include the use of new materials, optimization of processing paths, or the introduction of intelligent manufacturing technology. For example, the use of pre-hardened mold steel can reduce the heat treatment process, and the use of high-speed cutting technology can shorten the processing time. These optimizations may reduce the cost to 75,000 yuan. Iterative optimization is the key to ensuring the feasibility of the solution. If the cost is still over budget after the first round of optimization, further adjustments may be required, such as simplifying the machining accuracy of non-critical parts or adopting modular design to reduce the overall complexity. Through multiple rounds of optimization, the cost may eventually be controlled at 78,000 yuan to meet the budget requirements. The final technical solution not only includes cost control within the budget, but also lists the optimized process parameters in detail. For example, it may include specific process details such as using NAK80 mold steel, using a five-axis linkage machining center, and using a ball-end cutter to finish the main curved surface. This complete solution will guide the subsequent actual manufacturing process to ensure the quality and economy of the mold. Through this series of steps, the mold manufacturing process can achieve cost optimization while ensuring quality, reflecting the pursuit of lean production and cost control in modern manufacturing. This method is not only applicable to automotive interior parts molds, but can also be extended to other types of precision mold manufacturing, providing a powerful tool for enterprises to improve their competitiveness.

[0052] The present invention provides a mold manufacturing optimization system, which mainly includes:

[0053] The material selection module is used to select mold steel with high toughness and high wear resistance according to the mold structure design requirements, and optimize the heat treatment process parameters through the simulated annealing algorithm to improve the hardness and toughness of the mold material;

[0054] The process optimization module is used to prepare the mold base by combining casting and heat treatment. By optimizing the casting process parameters and heat treatment temperature, the dimensional accuracy and internal defects of the mold base are controlled to meet the mold base processing allowance requirements;

[0055] The mold base preparation module is used to optimize the surface treatment process based on the mold base surface quality requirements by using the particle swarm optimization algorithm. By controlling the surface roughness and lubricity, the matching degree between the mold base and the mold cavity is improved, and the mold base processing amount is reduced;

[0056] The surface treatment module is used to obtain real-time data during the mold base processing, and dynamically adjust the processing parameters to control the dimensional accuracy and surface quality of the mold base to meet the mold assembly process requirements;

[0057] The processing control module is used to use the mold performance prediction model to predict the hardness, toughness and wear resistance of the mold according to the mold base material, heat treatment and surface treatment process parameters, and determine whether the mold trial verification standard is met;

[0058] The performance prediction module is used to adjust the mold base material composition and preparation process parameters if the mold performance prediction result does not meet the requirements, and re-prepare and process the mold base until the mold performance meets the mold trial verification standard;

[0059] The life prediction module is used to obtain the actual performance data of the mold through mold trial verification, adopt the mold life prediction model, combine the mold repair and maintenance strategy, predict the service life of the mold, and formulate the mold remanufacturing plan;

[0060] The cost control module is used to calculate the manufacturing cost of the mold based on the complexity of the mold structure and the processing accuracy requirements, using the cost estimation model, and to control the mold cost within the budget by optimizing the mold base preparation process and the mold processing process.

[0061] What is disclosed above is only a preferred embodiment of the present invention, which certainly cannot be used to limit the scope of rights of the present invention. A person skilled in the art can understand that all or part of the processes of the above embodiments and equivalent changes made according to the claims of the present invention still fall within the scope of the invention.

Claims

1. A mold manufacturing optimization method, characterized in that: The method comprises the following steps: S101. According to the requirements of mold structure design, select mold steel with high toughness and high wear resistance, optimize heat treatment process parameters through simulated annealing algorithm, and improve the hardness and toughness of mold material; S102, preparing a mold base by a process combining casting and heat treatment, and controlling the dimensional accuracy and internal defects of the mold base by optimizing casting process parameters and heat treatment temperature to meet the mold base processing allowance requirements; S103. According to the surface quality requirements of the mold base, the particle swarm optimization algorithm is used to optimize the surface treatment process, and the matching degree between the mold base and the mold cavity is improved by controlling the surface roughness and lubricity, thereby reducing the mold base processing amount; S104, acquiring real-time data during the mold base processing, and dynamically adjusting the processing parameters to control the dimensional accuracy and surface quality of the mold base to meet the mold assembly process requirements; S105, using a mold performance prediction model, predicting the hardness, toughness and wear resistance of the mold according to mold base material, heat treatment and surface treatment process parameters, and determining whether the mold trial verification standard is met; S106. If the mold performance prediction result does not meet the requirements, the mold base material composition and preparation process parameters are adjusted, and the mold base is re-prepared and processed until the mold performance meets the mold trial verification standard; S107. Obtain actual performance data of the mold through mold trial verification, use a mold life prediction model, combine mold repair and maintenance strategies, predict the service life of the mold, and formulate a mold remanufacturing plan; S108. According to the complexity of the mold structure and the processing accuracy requirements, a cost estimation model is used to calculate the manufacturing cost of the mold. By optimizing the mold base preparation process and the mold processing process, the mold cost is controlled within the budget.

2. A mold manufacturing optimization method according to claim 1, characterized in that: The S101 includes: Obtain the mold structure design requirements and determine the high toughness and high wear resistance requirements of the mold steel; According to the die steel performance requirements, select die steel that meets the requirements of high toughness and high wear resistance; Using a simulated annealing algorithm, the heat treatment process parameters of the mold steel are optimized to obtain optimized heat treatment process parameters; Calculating the hardness and toughness of the mold material according to the optimized heat treatment process parameters; Determine whether the hardness value and toughness value meet the mold structure design requirements; If the hardness value and the toughness value do not meet the mold structure design requirements, the parameters of the simulated annealing algorithm are adjusted, and the optimization is re-executed until the hardness value and the toughness value that meet the mold structure design requirements are obtained; Determine the final heat treatment process parameters that meet the mold structure design requirements.

3. A mold manufacturing optimization method according to claim 1, characterized in that: The S102 includes: Obtaining preset mold base size accuracy threshold and defect threshold; Obtain mold base casting parameters and heat treatment temperature data, and establish a casting parameter and temperature optimization model; Iteratively calculating the casting parameters and heat treatment temperature according to the optimization model to obtain an optimal parameter combination; Generate a mold base casting and heat treatment process plan according to the optimal parameter combination, and output a process parameter file; Control casting equipment and heat treatment equipment through the process parameter file to execute the mold base preparation process; Obtain dimensional data and defect detection data during mold preparation; Determining whether the dimension data and defect detection data meet a preset mold base dimension accuracy threshold and defect threshold; If the size data or defect detection data does not meet the threshold, the optimization model parameters are adjusted, and iterative calculation is performed again to obtain an adjusted optimal parameter combination; The mold base casting and heat treatment process plans are updated according to the adjusted optimal parameter combination to complete the mold base preparation process.

4. A mold manufacturing optimization method according to claim 1, characterized in that: The S103 includes: Acquiring surface roughness data and lubricity index of the mold base, wherein the roughness data and lubricity index are used to establish a surface quality evaluation model; According to the surface quality evaluation model, determining the objective function and constraint conditions of the particle swarm optimization algorithm; Using the particle swarm optimization algorithm, searching for the optimal surface treatment process parameter combination in a preset parameter space; Inputting the optimal surface treatment process parameter combination into the surface treatment equipment to perform mold base surface treatment; Acquire processed mold base surface data, and calculate a matching index between the mold base surface and the mold cavity surface; If the matching index does not reach the preset threshold, adjust the weight coefficient of the particle swarm optimization algorithm and re-execute the optimization process until the matching index reaches the preset threshold; Output the mold base surface treatment process plan based on the final determined process parameter combination.

5. A mold manufacturing optimization method according to any one of claims 1 to 4, characterized in that: The S104 includes: Acquiring vibration, temperature and pressure data collected by a sensor network in a processing device during a processing process, wherein the data is processing data; Inputting the processing data into a pre-established neural network model to identify processing state features corresponding to the processing data; Calculating the deviation between the current processing parameters and the target parameters according to the processing state characteristics; Using a PID control algorithm, a machining parameter adjustment instruction is generated according to the deviation value; Sending the processing parameter adjustment instruction to the processing equipment controller to perform parameter optimization operation; Acquire the size data of the processed mold base collected by the online measurement system, and calculate the size error corresponding to the size data of the mold base; Using a genetic algorithm to optimize the weight parameters of the neural network model according to the size error to obtain an optimized neural network model; The optimized neural network model is applied to the subsequent processing parameter optimization process.

6. A mold manufacturing optimization method according to any one of claims 1 to 4, characterized in that: The S105 includes: Obtain the mold base material properties, heat treatment process parameters and surface treatment process parameters, and input them into the pre-established mold performance prediction model; The mold performance prediction model is used to calculate the predicted values ​​of mold hardness, toughness and wear resistance according to the mold base material properties, the heat treatment process parameters and the surface treatment process parameters; Obtain preset hardness thresholds, toughness standards, and wear resistance requirements; Determining whether the predicted value of the mold hardness reaches the preset hardness threshold; If yes, determining whether the predicted value of the mold toughness meets the preset toughness standard; If yes, further determining whether the predicted value of the mold wear resistance meets the preset wear resistance requirement; Determining whether the mold performance meets the preset mold trial verification standard based on the judgment results of the hardness, toughness and wear resistance; If it meets the requirements, the mold performance qualification result will be output; If not, the mold performance will be output as unqualified.

7. A mold manufacturing optimization method according to any one of claims 1 to 4, characterized in that: The S106 includes: Get the predicted value of mold performance; Determining whether the predicted value of the mold performance is lower than a preset threshold; If the predicted value of the mold performance is lower than the preset threshold, extracting mold base material composition information and process parameter information from a preset database; Generate a mold base material composition adjustment item list and a process parameter adjustment item list according to the correlation between the mold base material composition information and the process parameter information; Optimizing the mold base material composition according to the mold base material composition adjustment item list to obtain an optimized mold base material composition; Optimizing mold base preparation process parameters according to the process parameter adjustment item list to obtain optimized mold base preparation process parameters; Using the optimized mold base material composition and the optimized mold base preparation process parameters to prepare a new mold base; Obtaining performance test data of the new mold base; The performance test data is compared with the preset mold performance standard to obtain a judgment result on whether the mold performance meets the standard.

8. A mold manufacturing optimization system, characterized in that: The system is used to implement a mold manufacturing optimization method as described in any one of claims 1 to 7, and the system comprises: The material selection module is used to select mold steel with high toughness and high wear resistance according to the mold structure design requirements, and optimize the heat treatment process parameters through the simulated annealing algorithm to improve the hardness and toughness of the mold material; The process optimization module is used to prepare the mold base by combining casting and heat treatment. By optimizing the casting process parameters and heat treatment temperature, the dimensional accuracy and internal defects of the mold base are controlled to meet the mold base processing allowance requirements; The mold base preparation module is used to optimize the surface treatment process based on the mold base surface quality requirements by using the particle swarm optimization algorithm. By controlling the surface roughness and lubricity, the matching degree between the mold base and the mold cavity is improved, and the mold base processing amount is reduced; The surface treatment module is used to obtain real-time data during the mold base processing, and dynamically adjust the processing parameters to control the dimensional accuracy and surface quality of the mold base to meet the mold assembly process requirements; The processing control module is used to use the mold performance prediction model to predict the hardness, toughness and wear resistance of the mold according to the mold base material, heat treatment and surface treatment process parameters, and determine whether the mold trial verification standard is met; The performance prediction module is used to adjust the mold base material composition and preparation process parameters if the mold performance prediction result does not meet the requirements, and re-prepare and process the mold base until the mold performance meets the mold trial verification standard; The life prediction module is used to obtain the actual performance data of the mold through mold trial verification, adopt the mold life prediction model, combine the mold repair and maintenance strategy, predict the service life of the mold, and formulate the mold remanufacturing plan; The cost control module is used to calculate the manufacturing cost of the mold based on the complexity of the mold structure and the processing accuracy requirements, using the cost estimation model, and to control the mold cost within the budget by optimizing the mold base preparation process and the mold processing process.