Intelligent die-casting machining method and system for automobile parts

Abstract

The invention discloses an intelligent die-casting machining method and system for an automobile part, and relates to the technical field of metal casting. The method comprises the steps that an automobile part die-casting raw material feature data flow of the automobile part to be die-cast is obtained; loading a die feature data stream corresponding to the die-casting die; activating an automobile part die-casting temperature control factor; die-casting temperature expectation excavation is conducted, and automobile part die-casting temperature expectation distribution is obtained; an automobile part die-casting temperature control population is constructed; setting an automobile part die-casting temperature evaluation factor; die-casting temperature control optimization seeds are generated; and die-casting temperature control is conducted on the to-be-die-cast automobile The technical problems that according to existing die-casting temperature control, for complex and changeable die-casting environments and material characteristics, the die-casting temperature is difficult to adjust in a self-adaptive mode according to raw material characteristics and die characteristics of to-be-die-cast automobile parts, and then the precision of die-casting temperature control is insufficient, and self-adaptability is lacked are solved. The technical effect of improving the die-casting temperature control precision and the self-adaptability is achieved.

Description

Technical Field

[0001] This application relates to the field of metal casting technology, specifically to a smart die-casting processing method and system for automotive parts. Background Technology

[0002] With the rapid development of the automotive industry, the production efficiency and quality requirements of automotive parts are constantly increasing. In the production process of automotive parts, die casting technology is widely used because it can produce complex-shaped parts efficiently and accurately. However, the temperature control in the die casting process has a decisive impact on the quality of the final product. Traditional die casting temperature control methods often rely on the experience of operators and fixed parameter settings. They cannot adaptively adjust the die casting temperature according to the characteristics of the raw materials and molds of the automotive parts to be die cast. They lack adaptability and precision and are difficult to cope with the complex and ever-changing die casting environment and material properties.

[0003] Therefore, current die casting temperature control technologies suffer from several technical problems. Faced with complex and ever-changing die casting environments and material properties, it is difficult to adaptively adjust the die casting temperature based on the characteristics of the raw materials and molds of the automotive parts to be die-cast. This results in insufficient precision and a lack of adaptability in die casting temperature control. Summary of the Invention

[0004] This application provides a smart die-casting processing method and system for automotive parts. By employing techniques such as activating temperature control factors, expectation mining, and search optimization, it solves the technical problems of existing die-casting temperature control, which struggles to adaptively adjust the die-casting temperature based on the characteristics of the raw materials and molds of the automotive parts to be die-cast, in the face of complex and ever-changing die-casting environments and material properties. This results in insufficient accuracy and a lack of adaptability in die-casting temperature control, achieving the technical effect of improving the accuracy and adaptability of die-casting temperature control.

[0005] This application provides a smart die-casting processing method for automotive parts. The method includes: obtaining a feature data stream of the automotive part die-casting raw material for die-casting; loading a mold feature data stream corresponding to the die-casting mold of the automotive part; activating a die-casting temperature control factor for the automotive part, wherein the die-casting temperature control factor includes the pouring temperature of the automotive part raw material, the temperature of the automotive part die-casting mold, the temperature of the automotive part die-casting cooling water, and the ambient temperature of the automotive part die-casting; and determining the desired die-casting temperature based on the feature data stream of the automotive part die-casting raw material and the mold feature data stream, according to the die-casting temperature control factor. The process involves: mining to obtain the expected distribution of die-casting temperatures for automotive parts; constructing a die-casting temperature control population for automotive parts based on the expected distribution and control seed constraint rules; setting evaluation factors for die-casting temperatures of automotive parts, including dimensional accuracy, surface quality, and performance of the die-casting automotive parts; searching and optimizing the die-casting temperature control population based on the evaluation factors to generate a die-casting temperature control optimization seed; and controlling the die-casting temperature of the automotive parts to be die-casted based on the die-casting temperature control optimization seed.

[0006] In a possible implementation, based on the characteristic data stream of the automotive part die-casting raw material and the characteristic data stream of the mold, and according to the automotive part die-casting temperature control factor, the expected distribution of the automotive part die-casting temperature is obtained by performing expected mining of the die-casting temperature. The following processing is also performed: based on the characteristic data stream of the automotive part die-casting raw material and the characteristic data stream of the mold, the expected pouring temperature of the automotive part raw material is mined to obtain the expected distribution of the automotive part raw material pouring temperature; based on the characteristic data stream of the automotive part die-casting raw material and the characteristic data stream of the mold, the expected temperature of the automotive part die-casting mold is mined to obtain the expected distribution of the automotive part die-casting mold temperature; Based on the characteristic data stream of the automotive part die-casting raw material and the characteristic data stream of the mold, the expected distribution of the automotive part die-casting cooling water temperature is obtained by expectation mining; based on the characteristic data stream of the automotive part die-casting raw material and the characteristic data stream of the mold, the expected distribution of the automotive part die-casting environment temperature is obtained by expectation mining; integrating the expected distribution of the automotive part raw material pouring temperature, the expected distribution of the automotive part die-casting mold temperature, the expected distribution of the automotive part die-casting cooling water temperature, and the expected distribution of the automotive part die-casting environment temperature, the expected distribution of the automotive part die-casting temperature is generated.

[0007] In a possible implementation, based on the feature data stream of the automotive part die-casting raw materials and the feature data stream of the mold, the expected distribution of the automotive part raw material pouring temperature is obtained by expectation mining of the pouring temperature of the automotive part raw materials, and the following processing is performed: obtaining the part attribute feature information of the automotive part to be die-cast; using the part attribute feature information, the feature data stream of the automotive part die-casting raw materials, and the feature data stream of the mold as die-casting temperature retrieval constraints; using the pouring temperature of the automotive part raw materials as the die-casting temperature retrieval target; performing die-casting record retrieval according to the die-casting temperature retrieval constraints and the die-casting temperature retrieval target to obtain the automotive part raw material pouring temperature retrieval set; constructing an automotive part raw material pouring temperature distribution map according to the automotive part raw material pouring temperature distribution map; performing discrete point cleaning according to the automotive part raw material pouring temperature distribution map to generate an automotive part raw material pouring temperature concentration map; and performing central tendency analysis according to the automotive part raw material pouring temperature concentration map to generate the expected distribution of the automotive part raw material pouring temperature.

[0008] In a possible implementation, based on the expected distribution of the die-casting temperature of the automotive parts and the control seed constraint rules, a die-casting temperature control population for automotive parts is constructed, and the following processing is performed: the control seed constraint rules include control seed capacity constraints and control seed mutation constraints; die-casting temperature particles are modulated according to the expected distribution of the die-casting temperature of the automotive parts to obtain particle groups for modulating the raw material pouring temperature of the automotive parts, the die-casting mold temperature of the automotive parts, the cooling water temperature of the automotive parts, and the ambient temperature of the automotive parts; the modulated particles are randomly combined according to the particle groups for modulating the raw material pouring temperature of the automotive parts, the die-casting mold temperature of the automotive parts, the cooling water temperature of the automotive parts, and the ambient temperature of the automotive parts to obtain an initial die-casting temperature control population for automotive parts that satisfies the control seed capacity constraints; the initial die-casting temperature control population for automotive parts is mutated and optimized according to the control seed mutation constraints to generate the final die-casting temperature control population for automotive parts.

[0009] In a possible implementation, the initial automotive part die-casting temperature control population is subjected to mutation verification and optimization based on the control seed mutation constraint to generate the automotive part die-casting temperature control population. The following processing is also performed: pairwise difference comparison evaluation is conducted based on the initial automotive part die-casting temperature control population to generate multiple control seed mutation indices; it is determined whether the multiple control seed mutation indices satisfy the control seed mutation constraint; if all the multiple control seed mutation indices satisfy the control seed mutation constraint, the initial automotive part die-casting temperature control population is added to the automotive part die-casting temperature control population.

[0010] In a possible implementation, to determine whether the plurality of control seed mutation indices satisfy the control seed mutation constraints, the following processing is also performed: if any one of the plurality of control seed mutation indices does not satisfy the control seed mutation constraints, an identification die-casting temperature control seed is obtained; the initial automotive part die-casting temperature control population is optimized based on the expected distribution of automotive part die-casting temperature and the identification die-casting temperature control seed to generate an optimized automotive part die-casting temperature control population; the optimized automotive part die-casting temperature control population is subjected to mutation verification optimization based on the control seed mutation constraints to obtain the automotive part die-casting temperature control population.

[0011] In a possible implementation, the following steps are performed: First, a first die-casting temperature control seed is extracted from the automotive part die-casting temperature control population based on the automotive part die-casting temperature evaluation factor; second, a second die-casting temperature control seed is extracted from the automotive part die-casting temperature control population; third, based on the automotive part die-casting temperature evaluation factor, the second die-casting temperature control seed is evaluated to obtain a first die-casting temperature control evaluation coefficient; fourth, a fifth, a sixth, a seventh, a truncation temperature control seed is extracted from the automotive part die-casting temperature control population; and fifth, based on the automotive part die-casting temperature evaluation factor, the second die-casting temperature control seed is evaluated to obtain a first die-casting temperature control evaluation coefficient. The process involves calculating a second die-casting temperature control evaluation coefficient; performing current optimization based on the first die-casting temperature control evaluation coefficient, the second die-casting temperature control evaluation coefficient, the first die-casting temperature control seed, and the second die-casting temperature control seed to generate a current optimization die-casting temperature control evaluation coefficient and a current optimization die-casting temperature control seed; and iteratively optimizing the current optimization die-casting temperature control seed based on the current optimization die-casting temperature control evaluation coefficient, according to the automotive part die-casting temperature control population and the automotive part die-casting temperature evaluation factor, to obtain a die-casting temperature control optimization seed that meets the iterative optimization number threshold.

[0012] In a possible implementation, the first die-casting temperature control seed is evaluated based on the automotive part die-casting temperature evaluation factor to obtain a first die-casting temperature control evaluation coefficient. The following processing is also performed: Die-casting temperature control simulation is conducted based on the first die-casting temperature control seed to obtain a first die-casting temperature control simulation result, wherein the first die-casting temperature control simulation result includes simulated data of die-cast automotive part dimensional characteristics, simulated data of die-cast automotive part surface characteristics, and simulated data of die-cast automotive part performance characteristics; An automotive part die-casting temperature evaluation component is constructed based on the automotive part die-casting temperature evaluation factor, wherein the automotive part die-casting temperature evaluation component includes a die-cast automotive part dimensional accuracy evaluation channel, a die-cast automotive part surface quality evaluation channel, and a die-cast automotive part performance evaluation channel; The first die-casting temperature control simulation result is input into the automotive part die-casting temperature evaluation component to obtain a first automotive part die-casting temperature evaluation result; The first automotive part die-casting temperature evaluation result is weighted according to the die-casting temperature evaluation weight conditions to generate the first die-casting temperature control evaluation coefficient.

[0013] This application also provides an intelligent die-casting processing system for automotive parts, comprising: a die-casting raw material feature data stream acquisition module, which is used to acquire the automotive part die-casting raw material feature data stream for the automotive part to be die-cast; a mold feature data stream loading module, which is used to load the mold feature data stream corresponding to the die-casting mold of the automotive part to be die-cast; a die-casting temperature control factor activation module, which activates the automotive part die-casting temperature control factor, wherein the automotive part die-casting temperature control factor includes the automotive part raw material pouring temperature, the automotive part die-casting mold temperature, the automotive part die-casting cooling water temperature, and the automotive part die-casting ambient temperature; and a die-casting temperature expectation distribution acquisition module, which is used to determine the die-casting temperature period based on the automotive part die-casting raw material feature data stream and the mold feature data stream, according to the automotive part die-casting temperature control factor. The system includes: a die-casting temperature control population construction module, which constructs a die-casting temperature control population for automotive parts based on the expected distribution of die-casting temperatures and control seed constraints; a die-casting temperature evaluation factor setting module, which sets evaluation factors for die-casting temperatures of automotive parts, including dimensional accuracy, surface quality, and performance of the die-casting automotive parts; a die-casting temperature control optimization seed generation module, which searches and optimizes the die-casting temperature control population based on the evaluation factors to generate a die-casting temperature control optimization seed; and a die-casting temperature control module, which controls the die-casting temperature of the automotive parts to be die-cast based on the optimization seed.

[0014] This application proposes a smart die-casting processing method and system for automotive parts. The method involves: obtaining a data stream of the raw material characteristics of the automotive parts to be die-cast; loading the corresponding mold characteristic data stream; activating the die-casting temperature control factor; mining the expected die-casting temperature to obtain the expected distribution of the automotive parts' die-casting temperature; constructing a die-casting temperature control population; setting evaluation factors for the automotive parts' die-casting temperature; generating optimization seeds for die-casting temperature control; and controlling the die-casting temperature of the automotive parts to be die-cast. This method solves the technical problem of existing die-casting temperature control systems, which struggle to adaptively adjust the die-casting temperature based on the characteristics of the raw material and mold of the automotive parts to be die-cast in the face of complex and variable die-casting environments and material properties. This results in insufficient accuracy and a lack of adaptability in die-casting temperature control, achieving the technical effect of improving the accuracy and adaptability of die-casting temperature control. Attached Figure Description

[0015] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings of the embodiments of this disclosure will be briefly described below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, various steps can be processed in reverse order or simultaneously as needed. Furthermore, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0016] Figure 1 A schematic diagram of the intelligent die-casting process for automotive parts provided in an embodiment of this application; Figure 2 This is a schematic diagram of the intelligent die-casting processing system for automotive parts provided in an embodiment of this application.

[0017] Figure labeling: Module 10 for obtaining characteristic data stream of die casting raw materials, Module 20 for loading characteristic data stream of mold, Module 30 for activating die casting temperature control factor, Module 40 for obtaining expected distribution of die casting temperature, Module 50 for constructing population of die casting temperature control, Module 60 for setting evaluation factor of die casting temperature, Module 70 for generating seed for optimization of die casting temperature control, and Module 80 for die casting temperature control. Detailed Implementation

[0018] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application.

[0019] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description of this application will be provided in conjunction with the accompanying drawings. The described embodiments should not be considered as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] In the following description, references to "some embodiments" describe a subset of all possible embodiments. However, it is understood that "some embodiments" may be the same or different subsets of all possible embodiments and may be combined with each other without conflict. The terms "first" and "second" are used merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules not explicitly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only.

[0021] This application provides an intelligent die-casting method for automotive parts, such as... Figure 1 As shown, the method includes: Step S100: Obtain the characteristic data stream of the raw materials for die casting of the automotive parts to be die-cast. Obtaining the characteristic data stream of the raw materials for die casting of the automotive parts to be die-cast specifically refers to obtaining detailed data and information about the physical, chemical, and mechanical properties of the raw materials from the raw materials of the automotive parts to be die-cast through various technical means and data analysis methods. Specifically, the characteristic data stream of the raw materials for die casting may include material composition data, the chemical elemental composition of the raw materials, such as the content and proportion of elements like magnesium, aluminum, zinc, and cerium in the Mg-9Al-1Zn-0.5Ce alloy, and the impact of impurity content on the melting point and die-casting performance of the material; physical property data, such as the material's density, melting point, and coefficient of thermal expansion, which directly affect temperature control during the die-casting process. Thermal conductivity and thermal stability are crucial for controlling heat distribution during die casting and preventing overheating or excessive cooling of the material. Mechanical property data, such as tensile strength, yield strength, and elongation, affect the final strength and toughness of the product. Fatigue performance and impact resistance can assess the product's durability and reliability in actual use. Die-castability data, including material flowability (its ability to fill the mold during die casting), directly affects the product's molding effect and integrity. Solidification characteristics and shrinkage rate influence defects such as porosity and shrinkage cavities in the product. During die casting, sensors acquire real-time data on the temperature and pressure of the raw materials. By collecting and analyzing this raw material characteristic data stream, parameters such as temperature and pressure during die casting can be controlled more precisely, ensuring that requirements for dimensional accuracy, surface quality, and performance are met.

[0022] Step S200: Load the mold feature data stream corresponding to the die-casting mold of the automotive part to be die-cast. Acquiring and loading data and information related to the die-casting mold of the automotive part to be die-cast provides accurate mold parameters and characteristics for adaptive die-casting temperature control. This allows for a better understanding of the mold's structure, performance, and characteristics, ensuring more precise and effective temperature control during the die-casting process. Specifically, the mold feature data stream may include mold design parameters (mold size and shape, number of cavities, layout and dimensions), mold material properties (physical properties such as thermal conductivity and coefficient of thermal expansion of the mold material, and mechanical properties such as hardness, strength, and wear resistance of the mold material), mold usage status (real-time temperature distribution, wear level, and damage condition of the mold), mold heat exchange performance (cooling channel design, number, and layout of the mold, layout and power of the mold's heating elements), mold and die-casting machine compatibility (interface dimensions and fitting accuracy between the mold and the die-casting machine, compatibility of the mold and the die-casting machine's control system), and historical die-casting data (temperature control parameters, production efficiency, and product quality data of the mold in past die-casting processes). By loading these mold feature data streams, a comprehensive understanding of the mold's structure, performance, and characteristics can be obtained, providing accurate data support for adaptive die-casting temperature control.

[0023] Step S300: Activate the automotive parts die-casting temperature control factors. These factors include the automotive parts raw material pouring temperature, the automotive parts die-casting mold temperature, the automotive parts die-casting cooling water temperature, and the automotive parts die-casting ambient temperature. Activating the automotive parts die-casting temperature control factors refers to setting and adjusting various temperature factors affecting the quality of the die-cast parts during the die-casting process to ensure that the die-casting process is carried out under optimal temperature conditions. Specifically, the automotive parts raw material pouring temperature refers to the temperature at which the molten metal enters the mold cavity from the pressure chamber to fill it. For castings of different shapes and structures, the pouring temperature... The temperature can be controlled within a certain range, such as 630-730℃. Higher temperatures are suitable for thin-walled complex parts to improve the fluidity of the molten metal and achieve better forming. Lower temperatures are suitable for thick-walled structural parts to reduce solidification shrinkage. Excessively high pouring temperatures may increase the amount of air absorbed by the molten aluminum, making the thick-walled parts prone to defects such as pinholes, shrinkage cavities, and surface blistering, while also accelerating mold corrosion. Conversely, excessively low pouring temperatures result in poor fluidity and are prone to defects such as cold shuts, flow lines, and incomplete pouring. The temperature of the die-casting mold for automotive parts refers to the surface temperature of the mold, which affects the mechanical properties of the die-cast parts. The temperature of the die-casting mold has a significant impact on dimensional accuracy and mold life. The standard mold temperature should be about one-third of the alloy liquid pouring temperature, usually between 100 and 300°C. The die-casting mold needs to be preheated to a certain temperature before use and maintained within a certain temperature range during production. If the mold temperature is too low, the liquid metal may lose its fluidity quickly due to rapid cooling in the mold, affecting the forming of the casting. If the temperature is too high, the die-casting may deform because it does not have enough time to solidify, or even cause the moving parts of the mold to jam. The cooling water temperature for automotive parts die casting is used to control the cooling rate of the die-casting mold, indirectly affecting the quality of the die-casting and the mold life. It needs to be set reasonably according to the die-casting material and mold design to ensure that the mold maintains an appropriate temperature during the die-casting process. The ambient temperature for automotive parts die casting refers to the temperature around the die-casting workshop or die-casting equipment. Although the ambient temperature does not have as direct an impact on the die-casting process as the temperature control factors mentioned above, it will affect the mold preheating, heat preservation, and cooling rate of the die-casting. Higher ambient temperatures may make it difficult for the mold to dissipate heat, requiring appropriate adjustments to cooling measures. Lower ambient temperatures may increase the mold preheating time and energy consumption.

[0024] Step S400: Based on the raw material feature data stream and the mold feature data stream of the automotive parts die casting, the expected die casting temperature is mined according to the die casting temperature control factors of the automotive parts to obtain the expected distribution of die casting temperature for automotive parts. Using data analysis techniques (such as machine learning and data mining), combined with historical die casting data and real-time monitoring data, a deep analysis of the temperature control factors is performed. Based on the raw material feature data stream and the mold feature data stream, the quality and performance of die castings under different process parameters are predicted. Through simulation and experimental verification, the optimal combination of temperature control factors, i.e., the expected die casting temperature, is found. Based on the obtained expected die casting temperature, the distribution of temperature in different regions and at different time points is further analyzed. Considering the differences in materials, molds, and environment, as well as the dynamic changes during the die casting process, a reasonable range and trend of temperature distribution are determined, ultimately forming the expected distribution of die casting temperature for automotive parts, providing precise guidance for temperature control in the die casting process.

[0025] In one possible implementation, step S400 further includes step S410, which involves mining the expected pouring temperature of the automotive part raw material based on the characteristic data stream of the automotive part die-casting material and the characteristic data stream of the mold, to obtain the expected distribution of the pouring temperature of the automotive part raw material. Utilizing the characteristic data stream of the automotive part die-casting material (including the chemical composition, physical properties, historical usage data, etc. of the raw material), combined with die-casting process requirements and material characteristics, and through data analysis and model prediction techniques, the optimal pouring temperature range for the automotive part raw material is mined. For example, for aluminum alloy materials, the pouring temperature is generally selected between 600-700 degrees Celsius, but the specific range needs to be adjusted according to the actual material and process.

[0026] Step S400 further includes step S420, which involves performing expectation mining on the temperature of the automotive part die-casting mold based on the characteristic data stream of the raw material and the characteristic data stream of the mold, to obtain the expected temperature distribution of the automotive part die-casting mold. By analyzing the mold data stream and combining it with the die-casting process requirements and the heat resistance of the mold, suitable ranges for mold preheating temperature, holding temperature, and cooling temperature can be determined. Controlling the mold temperature is crucial for the forming quality of the casting and the mold life. For example, for aluminum alloy die-casting molds, the preheating temperature is generally selected at around 200 degrees Celsius, and the mold temperature is controlled between 220 and 280 degrees Celsius.

[0027] Step S400 further includes step S430, which involves performing expectation mining on the cooling water temperature of the automotive part die-casting based on the characteristic data stream of the raw material and the characteristic data stream of the mold, to obtain the expected distribution of the cooling water temperature in the automotive part die-casting. By analyzing the cooling water temperature data stream during the die-casting process, combined with the characteristics of the mold material and the casting material, a suitable cooling water temperature range can be determined. The temperature of the cooling water has little impact on actual production, but an appropriate cooling water temperature can improve production efficiency. Typically, the cooling water temperature can be set between 30 and 50 degrees Celsius.

[0028] Step S400 further includes step S440, which involves performing expectation mining on the die-casting environment temperature of the automotive parts based on the characteristic data stream of the raw materials and the characteristic data stream of the mold, to obtain the expected distribution of the die-casting environment temperature. By analyzing the environmental temperature data stream of the die-casting workshop and combining it with the die-casting process requirements, the environmental temperature range that needs to be maintained during the die-casting process can be determined. The working environment temperature of die-casting is usually high, especially in hot summer weather, so effective measures need to be taken to reduce the environmental temperature in order to improve work efficiency and safety.

[0029] Step S400 further includes step S450, integrating the expected distribution of the raw material pouring temperature of the automotive part, the expected distribution of the die-casting mold temperature of the automotive part, the expected distribution of the cooling water temperature for die-casting of the automotive part, and the expected distribution of the ambient temperature for die-casting of the automotive part to generate the expected die-casting temperature distribution of the automotive part. By integrating the obtained expected distributions of the raw material pouring temperature, mold temperature, cooling water temperature, and ambient temperature, and comprehensively considering the mutual influence and constraints between various factors, a complete expected die-casting temperature distribution for automotive parts is generated through data analysis and optimization algorithms. This will provide an important reference for temperature control in the die-casting process and help achieve high-quality die-cast products.

[0030] In one possible implementation, step S410 further includes step S411, obtaining the part attribute feature information of the automotive part to be die-cast. The part attribute feature information includes part name, category, size, quality requirements, etc. It also includes step S412, using the part attribute feature information, the automotive part die-casting raw material feature data stream, and the mold feature data stream as die-casting temperature retrieval constraints. The part attribute feature information, the automotive part die-casting raw material feature data stream (such as the chemical composition and physical properties of the raw material), and the mold feature data stream (such as mold material, size, thermal conductivity, etc.) are used as constraints for die-casting temperature retrieval. It also includes step S413, using the automotive part raw material pouring temperature as the die-casting temperature retrieval target. The retrieval target is the automotive part raw material pouring temperature, i.e., the target temperature to be retrieved and analyzed. Finally, it includes step S414, performing a die-casting record retrieval based on the die-casting temperature retrieval constraints and the die-casting temperature retrieval target to obtain a retrieval set of automotive part raw material pouring temperatures. Based on the defined search constraints and objectives, a search is performed in the die casting record database to obtain a set of raw material pouring temperatures related to the automotive parts to be die cast. This set includes information such as the raw material pouring temperatures used in historical die casting processes, corresponding part attributes, raw material characteristics, and mold characteristics.

[0031] Step S410 further includes step S415, constructing a casting temperature distribution map of automotive parts raw materials based on the retrieved casting temperature set. The retrieved casting temperature data is processed, including removing duplicate and outlier data. Based on the processed data, a casting temperature distribution map of automotive parts raw materials is drawn to visually display the temperature distribution. Step S416 further includes step S416, performing discrete point cleaning on the casting temperature distribution map of automotive parts raw materials to generate a concentrated casting temperature map of automotive parts raw materials. Discrete point cleaning refers to identifying and removing discrete points in the distribution map that have little impact on the overall trend, based on a set threshold, making the data more concentrated and accurate. The concentrated casting temperature map of automotive parts raw materials, compared to the original distribution map, has more concentrated data points and can more clearly display the main data distribution trends. Step S417 further includes step S417, performing central tendency analysis on the concentrated casting temperature map of automotive parts raw materials to generate the expected distribution of the casting temperature of automotive parts raw materials. Statistical methods (such as mean, median, mode, etc.) are used to analyze the data in the central tendency plot to assess the central tendency and trend of the data. Based on the results of the central tendency analysis, the expected distribution of the casting temperature of automotive parts raw materials is generated, that is, the predicted casting temperature range.

[0032] Step S500: Based on the expected distribution of die-casting temperature for automotive parts and the control seed constraint rules, construct a temperature control population for die-casting automotive parts. The control seed constraint rules are a series of restrictions set to ensure the safety, efficiency, and product quality of the die-casting process. These may include maximum and minimum mold temperature limits, cooling water flow and pressure limits, and the range of pouring temperatures. The temperature control population for die-casting automotive parts refers to a set of candidate die-casting temperature control parameters. Each set contains specific values ​​for all temperature control factors. Specifically, based on the expected temperature distribution and constraint rules, an initial set of temperature control parameters is randomly generated. The effectiveness of these parameter sets in the actual die-casting process is verified through simulation or experimentation, and their merits are evaluated. Based on the evaluation results, a subset of well-performing parameter sets are selected as seeds. The selected seeds are then cross-referenced (combining the advantages of multiple seeds) and mutated (introducing new elements or changes) to generate new parameter sets. The steps of evaluation, selection, cross-reference, and mutation are repeated to gradually optimize and obtain the temperature control population for die-casting automotive parts.

[0033] In one possible implementation, step S500 further includes step S510, where the control seed constraint rules include control seed capacity constraints and control seed mutation constraints. Control seed capacity constraints limit the number of control seeds (or particles) in the initial automotive part die-casting temperature control population, ensuring the population size is within a manageable range based on experimental conditions, etc. Control seed mutation constraints limit the degree or range of particle mutation in the population, ensuring mutations occur within a reasonable range, avoiding excessive or insufficient mutations to maintain population diversity and optimization efficiency. Step S520 further includes modulating die-casting temperature particles according to the desired distribution of automotive part die-casting temperature, obtaining a particle population modulated with the automotive part raw material pouring temperature, a particle population modulated with the automotive part die-casting mold temperature, a particle population modulated with the automotive part die-casting cooling water temperature, and a particle population modulated with the automotive part die-casting environment temperature. Die casting temperature particle modulation refers to the random setting of the raw material pouring temperature, die casting mold temperature, die casting cooling water temperature, and die casting ambient temperature of automotive parts based on the desired temperature distribution of automotive parts die casting. Specifically, the raw material pouring temperature modulation particle group includes multiple randomly set pouring temperatures, the die casting mold temperature modulation particle group includes multiple randomly set mold temperatures, the die casting cooling water temperature modulation particle group includes multiple randomly set cooling water temperatures, and the die casting ambient temperature modulation particle group includes multiple randomly set die casting ambient temperatures.

[0034] Step S500 further includes step S530, which involves randomly combining modulated particles based on the particle groups modulating the casting temperature of the automotive part raw material, the temperature of the automotive part die-casting mold, the temperature of the automotive part die-casting cooling water, and the temperature of the automotive part die-casting environment to obtain an initial automotive part die-casting temperature control population that satisfies the control seed capacity constraint. The particles in the four modulated particle groups are randomly combined, with each combination representing a possible die-casting temperature control scheme, i.e., the initial automotive part die-casting temperature control population. These combinations need to satisfy the control seed capacity constraint, i.e., the total number of combinations (or population size) must be within a preset range. Step S540 further includes performing mutation verification and optimization on the initial automotive part die-casting temperature control population according to the control seed mutation constraint to generate the automotive part die-casting temperature control population. According to the control seed mutation constraint, mutation operations are performed on the particles in the initial population. The mutation can be a small adjustment or a large change, depending on the setting of the mutation constraint. After mutation verification and optimization, the final automotive part die-casting temperature control population, containing multiple possible temperature control schemes, is obtained.

[0035] In one possible implementation, step S540 further includes step S541, which involves performing pairwise difference comparisons and evaluations based on the initial automotive part die-casting temperature control population to generate multiple control seed mutation indices. For each temperature control scheme (or "seed") in the initial automotive part die-casting temperature control population, pairwise difference comparisons are performed. Difference indices between seeds are calculated using Euclidean distance, Manhattan distance, etc., to assess the similarity and differences between these temperature control schemes. Based on the above difference comparisons, a mutation index is calculated for each seed, reflecting the degree of difference between that seed and other seeds in the population. Step S542 further includes determining whether the multiple control seed mutation indices satisfy the control seed mutation constraints. Each control seed mutation index is compared with the control seed mutation constraints, where the control seed mutation constraints are a pre-set threshold range used to determine whether the mutation index meets the requirements. If all control seed mutation indices satisfy the mutation constraints, the next step is performed; otherwise, the mutation strategy is adjusted or the mutation operation is repeated. The method also includes step S543, where if all the multiple control seed mutation indices satisfy the control seed mutation constraints, the initial automotive part die-casting temperature control population is added to the automotive part die-casting temperature control population. When all control seed mutation indices satisfy the mutation constraints, all seeds (i.e., temperature control schemes) in the initial automotive part die-casting temperature control population are added to the automotive part die-casting temperature control population, ultimately resulting in a set of automotive part die-casting temperature control populations that meet the requirements.

[0036] In one possible implementation, step S542 further includes step S544, whereby if any one of the plurality of control seed mutation indices does not satisfy the control seed mutation constraint, an identified die-casting temperature control seed is obtained. If any control seed mutation index is found to not satisfy the constraint, this unsatisfied control seed is identified, i.e., an identified die-casting temperature control seed is obtained. The implementation also includes step S545, where the initial automotive part die-casting temperature control population is optimized based on the expected distribution of automotive part die-casting temperatures and the identified die-casting temperature control seed, generating an optimized automotive part die-casting temperature control population. Die-casting temperature control seeds that do not satisfy the constraint are adjusted to meet the mutation constraint, using the expected distribution to guide the optimization direction, such as fine-tuning towards the center or a better region of the expected distribution, to generate an optimized automotive part die-casting temperature control population, i.e., an optimized automotive part die-casting temperature control population.

[0037] Step S542 further includes step S546, which involves performing mutation verification optimization on the optimized automotive part die-casting temperature control population according to the control seed mutation constraint, to obtain the automotive part die-casting temperature control population. The optimized automotive part die-casting temperature control population is further optimized using mutation operations, ensuring that the mutated population meets the preset control seed mutation constraint. Specifically, the mutation operation is used to generate new possible solutions based on existing solutions, i.e., adjusting one or more parameters in the temperature control scheme (such as raw material pouring temperature, mold temperature, cooling water temperature, etc.). After the mutation operation, the newly generated solutions need to be verified to ensure they meet the control seed mutation constraint. If the mutated solutions meet the mutation constraint and are better than the original solutions under a certain evaluation criterion (such as being closer to the desired distribution, having higher quality prediction, etc.), these solutions are added to the automotive part die-casting temperature control population. The final automotive part die-casting temperature control population will contain multiple solutions that meet the mutation constraint and have superior performance.

[0038] Step S600: Set evaluation factors for the die-casting temperature of automotive parts. These evaluation factors include the dimensional accuracy, surface quality, and performance of the die-cast automotive parts. The impact of temperature on the final quality of automotive parts during die casting is addressed by setting evaluation factors for the die-casting temperature of automotive parts, including dimensional accuracy, surface quality, and performance. Specifically, the dimensional accuracy of die-cast automotive parts refers to the degree of conformity between the actual dimensions of the die-cast part and the design dimensions. The mold temperature directly affects the shrinkage rate of the casting, thus affecting dimensional accuracy. For example, excessively high mold temperatures may lead to castings that are too large, while excessively low temperatures may lead to castings that are too small. Excessively high pouring temperatures may result in excessively fluid molten metal, causing castings that are too large, while excessively low pouring temperatures may lead to incomplete filling and smaller dimensions. Cooling water temperature directly affects the cooling effect of the mold, thus affecting the dimensional accuracy of the casting. The surface quality of automotive parts refers to the smoothness, defects (such as porosity, inclusions, sand holes, cracks, etc.) and coating quality of the casting surface. Uneven or excessively high mold temperatures may cause defects such as sticking and scratches on the casting surface, while excessively low pouring temperatures may cause defects such as cold shuts and flow lines. Excessively high or low ambient temperatures may also affect the surface quality of castings, such as causing oxidation and peeling. The performance of die-cast automotive parts refers to the mechanical, physical, and chemical properties of the casting under specific conditions. Mold temperature has a direct impact on the crystal structure, grain size, and mechanical properties of the casting. The pouring temperature affects the chemical composition and microstructure of the casting, thus affecting its performance. Cooling water temperature affects the solidification rate and microstructure of the casting, thereby affecting its performance.

[0039] Step S700: The die-casting temperature control population for automotive parts is searched and optimized according to the evaluation factors for the die-casting temperature of the automotive parts, generating a seed for die-casting temperature control optimization. Based on the set evaluation factors, an evaluation value is calculated for each set of temperature control parameters. Specifically, a comprehensive score of the temperature control parameters within the die-casting temperature control population is calculated by weighting the dimensional accuracy, surface quality, and performance of the die-casting automotive parts. Specifically, a particle swarm optimization algorithm is used, simulating the foraging behavior of a flock of birds to find the optimal solution in the search space. In each iteration, the fitness of each individual in the population is calculated according to the evaluation function. Then, the population is updated using a search strategy to generate a new set of temperature control parameters. One or more convergence conditions are set, such as reaching the maximum number of iterations or the population fitness not significantly improving for multiple generations. When the convergence conditions are met, the search stops, and the individual with the highest fitness is selected from the last generation of the population as the seed for die-casting temperature control optimization, which includes optimized parameters such as raw material pouring temperature, mold temperature, and cooling water temperature.

[0040] In one possible implementation, step S700 further includes step S710, extracting a first die-casting temperature control seed based on the automotive parts die-casting temperature control population. A die-casting temperature control scheme is randomly selected from the automotive parts die-casting temperature control population or selected based on a strategy (such as roulette wheel selection) as the first die-casting temperature control seed. It also includes step S720, evaluating the first die-casting temperature control seed based on the automotive parts die-casting temperature evaluation factors to obtain a first die-casting temperature control evaluation coefficient. The first die-casting temperature control seed is evaluated based on preset automotive parts die-casting temperature evaluation factors (such as casting quality, production efficiency, energy consumption, etc.) to obtain a specific quantitative value as the first die-casting temperature control evaluation coefficient, used to measure the comprehensive performance of the control scheme. It also includes step S730, extracting a second die-casting temperature control seed based on the automotive parts die-casting temperature control population. Similarly, another die-casting temperature control scheme is randomly selected from the automotive parts die-casting temperature control population as the second die-casting temperature control seed. The method also includes step S740, which calculates a second die-casting temperature control evaluation coefficient based on the automotive part die-casting temperature evaluation factor and the second die-casting temperature control seed. Similarly, the second die-casting temperature control seed is evaluated based on the automotive part die-casting temperature evaluation factor to obtain the second die-casting temperature control evaluation coefficient.

[0041] Step S700 further includes step S750, which involves performing current optimization based on the first die-casting temperature control evaluation coefficient, the second die-casting temperature control evaluation coefficient, the first die-casting temperature control seed, and the second die-casting temperature control seed to generate the current optimal die-casting temperature control evaluation coefficient and the current optimal die-casting temperature control seed. The first die-casting temperature control evaluation coefficient and the second die-casting temperature control evaluation coefficient are compared to identify a better-performing control scheme. This better-performing control scheme is then used as the current optimal die-casting temperature control seed, and its corresponding evaluation coefficient is used as the current optimal die-casting temperature control evaluation coefficient.

[0042] Step S700 further includes step S760, which involves iteratively optimizing the current die-casting temperature control seed based on the current optimal die-casting temperature control evaluation coefficient, according to the automotive parts die-casting temperature control population and the automotive parts die-casting temperature evaluation factor, to obtain the die-casting temperature control optimization seed that meets the iteration optimization number threshold. Based on the current optimal die-casting temperature control evaluation coefficient, new die-casting temperature control seeds are extracted from the automotive parts die-casting temperature control population. The newly extracted seeds are evaluated and compared with the current optimal die-casting temperature control seed. If the evaluation coefficient of the new seed is better, the current optimal die-casting temperature control seed and the current optimal die-casting temperature control evaluation coefficient are updated, and the above iterative process is repeated until the preset iteration optimization number threshold is reached. Finally, the final die-casting temperature control optimization seed, i.e., the die-casting temperature control scheme with the best performance in the entire control population, is output.

[0043] In one possible implementation, step S720 further includes step S721, performing a die-casting temperature control simulation based on the first die-casting temperature control seed to obtain a first die-casting temperature control simulation result. This first die-casting temperature control simulation result includes simulated data on the dimensional characteristics of die-cast automotive parts, simulated data on the surface characteristics of die-cast automotive parts, and simulated data on the performance characteristics of die-cast automotive parts. Using the first die-casting temperature control seed to perform the die-casting temperature control simulation involves using simulation software or experimental equipment to simulate the impact of temperature control on automotive parts during the die-casting process, predicting and evaluating the dimensions, surface quality, and performance of automotive parts under specific temperature control conditions, and obtaining the first die-casting temperature control simulation result. This result includes simulated data on the dimensional characteristics of die-cast automotive parts, simulated data on the surface characteristics of die-cast automotive parts, and simulated data on the performance characteristics of die-cast automotive parts. Specifically, the simulated data on the dimensional characteristics of die-cast automotive parts reflects the impact of different temperature control parameters (such as mold preheating temperature, pouring temperature, cooling rate, etc.) on the dimensions of automotive parts during the die-casting process, and may include the length, width, height, wall thickness, etc. Key dimension parameters, and the correlation and trends between these parameters and temperature control parameters; surface feature simulation data of die-cast automotive parts focuses on the quality status of the automotive parts surface, which may include the number, distribution and size of defects such as porosity, cracks, and impurities, as well as appearance features such as surface roughness and gloss; performance feature simulation data of die-cast automotive parts evaluates the performance of automotive parts under specific temperature control conditions, which may include mechanical properties (such as tensile strength, yield strength, elongation, etc.), physical properties (such as thermal stability, electrical conductivity, etc.), or chemical properties (such as corrosion resistance, wear resistance, etc.), the relationship between these performance parameters and temperature control parameters, and the performance change trends under different temperature control conditions.

[0044] The method also includes step S722, which involves constructing an automotive part die-casting temperature evaluation component based on the automotive part die-casting temperature evaluation factors. This component includes a die-cast automotive part dimensional accuracy evaluation channel, a die-cast automotive part surface quality evaluation channel, and a die-cast automotive part performance evaluation channel. Based on the evaluation factors, corresponding evaluation channels are constructed. For example, dimensional accuracy, surface quality, and performance evaluation channels can be set. Each channel focuses on evaluating the quality performance of the die-cast part in a specific aspect. Specifically, an evaluation model is constructed based on a neural network or decision tree. Historical data related to temperature control during the die-casting process, such as melting temperature, pouring temperature, and mold temperature, are collected. This historical data is used to supervise the training of the evaluation model, resulting in the dimensional accuracy, surface quality, and performance evaluation channels. By integrating these three channels, the automotive part die-casting temperature evaluation component is obtained, which can comprehensively evaluate the performance of the die-cast part in terms of dimensional accuracy, surface quality, and performance, thereby providing strong support for optimizing the die-casting temperature control scheme. The die-cast automotive parts dimensional accuracy evaluation channel is used to assess the dimensional accuracy of die-cast parts. Based on preset dimensional tolerances or standards, it compares the dimensional data of simulated or actual die-cast parts to determine whether the die-cast parts meet the dimensional requirements. The die-cast automotive parts surface quality evaluation channel focuses on the quality assessment of the die-cast parts surface, considering surface smoothness, flatness, presence of porosity, cracks, impurities, and other defects. The die-cast automotive parts performance evaluation channel is used to assess the performance of die-cast parts under specific conditions.

[0045] Step S720 further includes step S723, inputting the first die-casting temperature control simulation result into the automotive part die-casting temperature evaluation component to obtain the first automotive part die-casting temperature evaluation result. The automotive part die-casting temperature evaluation component compares the first die-casting temperature control simulation result with preset standards or expected values ​​to assess whether the die-casting part meets the requirements in terms of size, surface quality, and performance. Based on the comparison results, the evaluation component comprehensively evaluates the overall quality of the die-casting part and finally outputs the first automotive part die-casting temperature evaluation result, indicating the performance of the die-casting part in various indicators and whether it meets the quality requirements. Step S724 further includes weighted calculation of the first automotive part die-casting temperature evaluation result according to the die-casting temperature evaluation weight conditions to generate the first die-casting temperature control evaluation coefficient. Weight values ​​are set for different evaluation channels (dimensional accuracy, surface quality, performance), and the evaluation results of each channel are weighted and summed according to the weight values. The final weighted sum is the first die-casting temperature control evaluation coefficient, which can more accurately understand the effect of die-casting temperature control.

[0046] Step S800: The die-casting temperature of the automotive part to be die-cast is controlled according to the die-casting temperature control optimization seed. In the actual die-casting process, the optimal set of temperature control parameters obtained through search and optimization (i.e., the die-casting temperature control optimization seed) is used to accurately control the temperature during the die-casting process, so as to ensure that the dimensional accuracy, surface quality and performance of the automotive part reach the optimal level.

[0047] In the above text, refer to Figure 1 A smart die-casting method for automotive parts according to embodiments of the present invention is described in detail. Next, reference will be made to... Figure 2 A smart die-casting system for automotive parts is described according to an embodiment of the present invention.

[0048] The intelligent die-casting system for automotive parts according to embodiments of the present invention addresses the technical problems of existing die-casting temperature control, which struggles to adaptively adjust the die-casting temperature based on the characteristics of the raw materials and molds of the automotive parts to be die-cast, especially in the face of complex and variable die-casting environments and material properties. This results in insufficient accuracy and a lack of adaptability in die-casting temperature control. The system improves the accuracy and adaptability of die-casting temperature control. The intelligent die-casting system for automotive parts includes: a die-casting raw material characteristic data stream acquisition module 10, a mold characteristic data stream loading module 20, a die-casting temperature control factor activation module 30, a die-casting temperature expected distribution acquisition module 40, a die-casting temperature control population construction module 50, a die-casting temperature evaluation factor setting module 60, a die-casting temperature control optimization seed generation module 70, and a die-casting temperature control module 80.

[0049] Die casting raw material feature data stream acquisition module 10, the die casting raw material feature data stream acquisition module 10 is used to acquire the automotive part die casting raw material feature data stream of the automotive part to be die cast; Mold feature data stream loading module 20, the mold feature data stream loading module 20 is used to load the mold feature data stream corresponding to the die-casting mold of the automotive part to be die-cast; Die casting temperature control factor activation module 30 activates automotive part die casting temperature control factors, wherein the automotive part die casting temperature control factors include automotive part raw material pouring temperature, automotive part die casting mold temperature, automotive part die casting cooling water temperature and automotive part die casting ambient temperature. Die casting temperature expected distribution acquisition module 40 is used to mine the expected distribution of die casting temperature of automobile parts based on the characteristic data stream of the die casting raw material of the automobile parts and the characteristic data stream of the mold, and according to the die casting temperature control factor of the automobile parts. Die casting temperature control population construction module 50, which is used to construct an automotive part die casting temperature control population based on the desired distribution of automotive part die casting temperature and control seed constraint rules; The die casting temperature evaluation factor setting module 60 is used to set the die casting temperature evaluation factor for automotive parts, wherein the die casting temperature evaluation factor for automotive parts includes the dimensional accuracy of die-cast automotive parts, the surface quality of die-cast automotive parts, and the performance of die-cast automotive parts. Die casting temperature control optimization seed generation module 70 is used to search and optimize the die casting temperature control population of automotive parts according to the evaluation factor of automotive part die casting temperature, and generate die casting temperature control optimization seed. The die-casting temperature control module 80 is used to control the die-casting temperature of the automotive parts to be die-cast according to the die-casting temperature control optimization seed.

[0050] The specific configuration of the die casting temperature desired distribution acquisition module 40 will be described in detail below. The die-casting temperature expectation distribution acquisition module 40 may further include: performing expectation mining on the pouring temperature of the automotive part raw material based on the automotive part die-casting raw material feature data stream and the mold feature data stream to obtain the automotive part raw material pouring temperature expectation distribution; performing expectation mining on the automotive part die-casting mold temperature based on the automotive part die-casting raw material feature data stream and the mold feature data stream to obtain the automotive part die-casting mold temperature expectation distribution; performing expectation mining on the automotive part die-casting cooling water temperature based on the automotive part die-casting raw material feature data stream and the mold feature data stream to obtain the automotive part die-casting cooling water temperature expectation distribution; performing expectation mining on the automotive part die-casting ambient temperature based on the automotive part die-casting raw material feature data stream and the mold feature data stream to obtain the automotive part die-casting ambient temperature expectation distribution; and integrating the automotive part raw material pouring temperature expectation distribution, the automotive part die-casting mold temperature expectation distribution, the automotive part die-casting cooling water temperature expectation distribution, and the automotive part die-casting ambient temperature expectation distribution to generate the automotive part die-casting temperature expectation distribution.

[0051] The following will describe in detail the specific configuration of the die-casting temperature expected distribution acquisition module 40. The die-casting temperature expected distribution acquisition module 40 further includes: acquiring the part attribute feature information of the automotive part to be die-cast; using the part attribute feature information, the automotive part die-casting raw material feature data stream, and the mold feature data stream as die-casting temperature retrieval constraints; using the automotive part raw material pouring temperature as the die-casting temperature retrieval target; performing die-casting record retrieval based on the die-casting temperature retrieval constraints and the die-casting temperature retrieval target to obtain an automotive part raw material pouring temperature retrieval set; constructing an automotive part raw material pouring temperature distribution map based on the automotive part raw material pouring temperature retrieval set; performing discrete point cleaning based on the automotive part raw material pouring temperature distribution map to generate an automotive part raw material pouring temperature concentration map; and performing central tendency analysis based on the automotive part raw material pouring temperature concentration map to generate the expected distribution of the automotive part raw material pouring temperature.

[0052] The specific configuration of the die-casting temperature control population construction module 50 will be described in detail below. The die-casting temperature control population construction module 50 may further include: the control seed constraint rules include control seed capacity constraints and control seed mutation constraints; based on the expected distribution of the automotive part die-casting temperature, die-casting temperature particles are modulated to obtain a particle group modulated for the automotive part raw material pouring temperature, a particle group modulated for the automotive part die-casting mold temperature, a particle group modulated for the automotive part die-casting cooling water temperature, and a particle group modulated for the automotive part die-casting environment temperature; based on the particle group modulated for the automotive part raw material pouring temperature, the particle group modulated for the automotive part die-casting mold temperature, the particle group modulated for the automotive part die-casting cooling water temperature, and the particle group modulated for the automotive part die-casting environment temperature, the modulated particles are randomly combined to obtain an initial automotive part die-casting temperature control population that satisfies the control seed capacity constraints; based on the control seed mutation constraints, the initial automotive part die-casting temperature control population is mutated and optimized to generate the automotive part die-casting temperature control population.

[0053] The specific configuration of the die-casting temperature control population construction module 50 will be described in detail below. The die-casting temperature control population construction module 50 may further include: performing pairwise difference comparisons and evaluations based on the initial automotive part die-casting temperature control population to generate multiple control seed mutation indices; determining whether the multiple control seed mutation indices satisfy the control seed mutation constraints; and if all the multiple control seed mutation indices satisfy the control seed mutation constraints, adding the initial automotive part die-casting temperature control population to the automotive part die-casting temperature control population.

[0054] The specific configuration of the die-casting temperature control population construction module 50 will be described in detail below. The die-casting temperature control population construction module 50 may further include: if any one of the plurality of control seed mutation indices does not satisfy the control seed mutation constraint, obtaining an identified die-casting temperature control seed; optimizing the initial automotive part die-casting temperature control population based on the expected distribution of the automotive part die-casting temperature and the identified die-casting temperature control seed to generate an optimized automotive part die-casting temperature control population; and performing mutation verification optimization on the optimized automotive part die-casting temperature control population based on the control seed mutation constraint to obtain the final automotive part die-casting temperature control population.

[0055] The specific configuration of the die-casting temperature control optimization seed generation module 70 will be described in detail below. The die-casting temperature control optimization seed generation module 70 further includes: extracting a first die-casting temperature control seed based on the automotive parts die-casting temperature control population; evaluating the first die-casting temperature control seed based on the automotive parts die-casting temperature evaluation factor to obtain a first die-casting temperature control evaluation coefficient; extracting a second die-casting temperature control seed based on the automotive parts die-casting temperature control population; calculating a second die-casting temperature control evaluation coefficient based on the automotive parts die-casting temperature evaluation factor and the second die-casting temperature control seed; performing current optimization based on the first die-casting temperature control evaluation coefficient, the second die-casting temperature control evaluation coefficient, the first die-casting temperature control seed, and the second die-casting temperature control seed to generate a currently optimized die-casting temperature control evaluation coefficient and a currently optimized die-casting temperature control seed; and iteratively optimizing the currently optimized die-casting temperature control seed based on the currently optimized die-casting temperature control evaluation coefficient, the automotive parts die-casting temperature control population, and the automotive parts die-casting temperature evaluation factor to obtain the die-casting temperature control optimization seed that meets the iterative optimization number threshold.

[0056] The specific configuration of the die-casting temperature control optimization seed generation module 70 will be described in detail below. The die-casting temperature control optimization seed generation module 70 further includes: performing die-casting temperature control simulation based on the first die-casting temperature control seed to obtain a first die-casting temperature control simulation result, wherein the first die-casting temperature control simulation result includes simulated data of die-cast automotive part dimensional characteristics, simulated data of die-cast automotive part surface characteristics, and simulated data of die-cast automotive part performance characteristics; constructing an automotive part die-casting temperature evaluation component based on the automotive part die-casting temperature evaluation factor, wherein the automotive part die-casting temperature evaluation component includes a die-cast automotive part dimensional accuracy evaluation channel, a die-cast automotive part surface quality evaluation channel, and a die-cast automotive part performance evaluation channel; inputting the first die-casting temperature control simulation result into the automotive part die-casting temperature evaluation component to obtain a first automotive part die-casting temperature evaluation result; and performing a weighted calculation on the first automotive part die-casting temperature evaluation result according to the die-casting temperature evaluation weight conditions to generate the first die-casting temperature control evaluation coefficient.

[0057] The intelligent die-casting system for automotive parts provided in this embodiment of the invention can execute the intelligent die-casting method for automotive parts provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0058] Although this application makes various references to certain modules in the system according to the embodiments of this application, any number of different modules can be used and run on user terminals and / or servers. The various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy distinction between each other and are not used to limit the scope of protection of this invention.

[0059] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A smart die-casting processing method for automotive parts, characterized in that, The method includes: Obtain the feature data stream of the raw materials for die casting of the automotive parts to be die-cast; Load the mold feature data stream corresponding to the die-casting mold of the automotive part to be die-cast; Activate the automotive parts die casting temperature control factor, wherein the automotive parts die casting temperature control factor includes the automotive parts raw material pouring temperature, automotive parts die casting mold temperature, automotive parts die casting cooling water temperature and automotive parts die casting ambient temperature. Based on the characteristic data stream of the raw materials for die casting of automotive parts and the characteristic data stream of the mold, the expected distribution of die casting temperature of automotive parts is obtained by mining the expected temperature of die casting based on the die casting temperature control factor of automotive parts. Based on the desired distribution of die-casting temperature of automotive parts and the control seed constraint rules, a die-casting temperature control population for automotive parts is constructed. An evaluation factor for the die-casting temperature of automotive parts is set, wherein the evaluation factor for the die-casting temperature of automotive parts includes the dimensional accuracy of die-cast automotive parts, the surface quality of die-cast automotive parts, and the performance of die-cast automotive parts. Based on the evaluation factor of the die casting temperature of automotive parts, the population of die casting temperature control of automotive parts is searched and optimized to generate a seed for die casting temperature control optimization. The die-casting temperature of the automotive parts to be die-cast is controlled according to the die-casting temperature control optimization seed.

2. The intelligent die-casting processing method for automotive parts as described in claim 1, characterized in that, Based on the raw material feature data stream and the mold feature data stream of the automotive parts die casting, the expected die casting temperature is mined according to the automotive parts die casting temperature control factor to obtain the expected distribution of automotive parts die casting temperature, including: Based on the characteristic data stream of the die-casting raw materials for automotive parts and the characteristic data stream of the mold, the expected distribution of the pouring temperature of the raw materials for automotive parts is obtained by expectation mining. Based on the characteristic data stream of the raw materials for die casting of automotive parts and the characteristic data stream of the mold, the expected temperature of the die casting mold of automotive parts is mined to obtain the expected temperature distribution of the die casting mold of automotive parts. Based on the feature data stream of the raw materials for die casting of automotive parts and the feature data stream of the mold, the expected distribution of the cooling water temperature for die casting of automotive parts is obtained by expectation mining of the cooling water temperature for die casting of automotive parts. Based on the feature data stream of the raw materials for die casting of automotive parts and the feature data stream of the mold, the expected distribution of the environment temperature for die casting of automotive parts is obtained by expectation mining of the environment temperature for die casting of automotive parts. The expected distribution of the casting temperature of the raw materials for automotive parts, the expected distribution of the temperature of the die-casting mold for automotive parts, the expected distribution of the cooling water temperature for die-casting of automotive parts, and the expected distribution of the ambient temperature for die-casting of automotive parts are integrated to generate the expected distribution of the die-casting temperature of automotive parts.

3. The intelligent die-casting processing method for automotive parts as described in claim 2, characterized in that, Based on the characteristic data stream of the die-casting raw materials for automotive parts and the characteristic data stream of the mold, the expected distribution of the casting temperature of the raw materials for automotive parts is obtained by expectation mining, including: Obtain the part attribute feature information of the automotive part to be die-cast; The die casting temperature retrieval constraints are the part attribute feature information, the automotive part die casting raw material feature data stream, and the mold feature data stream. The casting temperature of the raw material for the automotive parts is used as the target for the die-casting temperature search. Based on the die casting temperature retrieval constraints and the die casting temperature retrieval target, a die casting record retrieval is performed to obtain a retrieval set of casting temperatures for automotive parts raw materials. Based on the aforementioned automotive parts raw material casting temperature retrieval set, construct an automotive parts raw material casting temperature distribution map; Based on the discrete point cleaning of the casting temperature distribution map of the automotive parts raw materials, a concentrated map of the casting temperature of the automotive parts raw materials is generated. Based on the central tendency analysis of the casting temperature concentration map of the automotive parts raw materials, the expected distribution of the casting temperature of the automotive parts raw materials is generated.

4. The intelligent die-casting processing method for automotive parts as described in claim 1, characterized in that, Based on the desired distribution of die-casting temperature for automotive parts and the control seed constraint rules, a die-casting temperature control population for automotive parts is constructed, including: The seed constraint rules include seed capacity constraints and seed variation constraints. Based on the desired distribution of die casting temperature for automotive parts, die casting temperature particle modulation is performed to obtain particle groups for modulating the pouring temperature of automotive parts raw materials, the temperature of automotive parts die casting mold, the temperature of automotive parts die casting cooling water, and the temperature of automotive parts die casting environment. Based on the particle group for modulating the casting temperature of the automotive parts raw materials, the particle group for modulating the temperature of the automotive parts die casting mold, the particle group for modulating the temperature of the automotive parts die casting cooling water, and the particle group for modulating the temperature of the automotive parts die casting environment, the modulation particles are randomly combined to obtain an initial automotive parts die casting temperature control population that satisfies the control seed capacity constraint. The initial automotive part die-casting temperature control population is subjected to mutation verification and optimization based on the control seed mutation constraint to generate the automotive part die-casting temperature control population.

5. The intelligent die-casting processing method for automotive parts as described in claim 4, characterized in that, Based on the control seed mutation constraint, the initial automotive part die-casting temperature control population is mutated and optimized to generate the automotive part die-casting temperature control population, including: Based on the initial automotive part die-casting temperature control population, pairwise difference comparisons were performed to evaluate and generate multiple control seed variation indices. Determine whether the plurality of control seed mutation indices satisfy the control seed mutation constraints; If all of the multiple control seed mutation indices satisfy the control seed mutation constraints, the initial automotive part die-casting temperature control population is added to the automotive part die-casting temperature control population.

6. The intelligent die-casting processing method for automotive parts as described in claim 5, characterized in that, Determining whether the plurality of control seed mutation indices satisfy the control seed mutation constraints includes: If any one of the plurality of control seed variation indices does not satisfy the control seed variation constraint, an identification die casting temperature control seed is obtained. The initial automotive part die-casting temperature control population is optimized based on the expected distribution of the automotive part die-casting temperature and the identified die-casting temperature control seed, thereby generating an optimized automotive part die-casting temperature control population. The mutation verification and optimization of the optimized automotive part die-casting temperature control population are performed based on the control seed mutation constraint to obtain the automotive part die-casting temperature control population.

7. The intelligent die-casting processing method for automotive parts as described in claim 1, characterized in that, Based on the evaluation factors for die casting temperature of automotive parts, a search and optimization process is performed on the die casting temperature control population of automotive parts to generate a die casting temperature control optimization seed, including: Based on the aforementioned automotive parts die-casting temperature control population, extract the first die-casting temperature control seed; The first die-casting temperature control seed is evaluated based on the automotive part die-casting temperature evaluation factor to obtain the first die-casting temperature control evaluation coefficient. Based on the aforementioned automotive parts die-casting temperature control population, a second die-casting temperature control seed is extracted. Based on the aforementioned automotive part die-casting temperature evaluation factor, and according to the second die-casting temperature control seed, the second die-casting temperature control evaluation coefficient is calculated. Based on the first die casting temperature control evaluation coefficient, the second die casting temperature control evaluation coefficient, the first die casting temperature control seed, and the second die casting temperature control seed, current optimization is performed to generate the current optimization die casting temperature control evaluation coefficient and the current optimization die casting temperature control seed. Based on the current optimization evaluation coefficient for die casting temperature control, the current optimization seed for die casting temperature control is iteratively optimized according to the die casting temperature control population of automotive parts and the evaluation factor of die casting temperature of automotive parts, so as to obtain the optimization seed for die casting temperature control that meets the threshold of the number of iterations.

8. The intelligent die-casting processing method for automotive parts as described in claim 7, characterized in that, The first die-casting temperature control seed is evaluated based on the aforementioned automotive part die-casting temperature evaluation factor to obtain the first die-casting temperature control evaluation coefficient, including: The die casting temperature control simulation is performed based on the first die casting temperature control seed to obtain the first die casting temperature control simulation result, wherein the first die casting temperature control simulation result includes simulation data of the dimensional characteristics of die casting automotive parts, simulation data of the surface characteristics of die casting automotive parts, and simulation data of the performance characteristics of die casting automotive parts. Based on the aforementioned automotive parts die casting temperature evaluation factor, an automotive parts die casting temperature evaluation component is constructed, wherein the automotive parts die casting temperature evaluation component includes a die casting automotive parts dimensional accuracy evaluation channel, a die casting automotive parts surface quality evaluation channel, and a die casting automotive parts performance evaluation channel. The first die-casting temperature control simulation result is input into the automotive part die-casting temperature evaluation component to obtain the first automotive part die-casting temperature evaluation result. The evaluation results of the die casting temperature of the first automotive part are weighted according to the evaluation weight conditions of the die casting temperature to generate the first die casting temperature control evaluation coefficient.

9. A smart die-casting system for automotive parts, characterized in that, The system is used to implement the intelligent die-casting processing method for automotive parts according to any one of claims 1-8, and the system includes: A die-casting raw material feature data stream acquisition module is used to acquire the automotive part die-casting raw material feature data stream to be die-cast; A mold feature data stream loading module is used to load the mold feature data stream corresponding to the die-casting mold of the automotive part to be die-cast; Die casting temperature control factor activation module, wherein the die casting temperature control factor activation module activates the die casting temperature control factor for automotive parts, wherein the die casting temperature control factor for automotive parts includes the pouring temperature of the raw material for automotive parts, the temperature of the die casting mold for automotive parts, the temperature of the cooling water for die casting of automotive parts, and the ambient temperature for die casting of automotive parts. The module for obtaining the expected distribution of die casting temperature is used to mine the expected distribution of die casting temperature of automotive parts based on the characteristic data stream of the die casting raw materials of the automotive parts and the characteristic data stream of the mold, and according to the die casting temperature control factor of the automotive parts. A die-casting temperature control population construction module is used to construct a die-casting temperature control population for automotive parts based on the expected distribution of die-casting temperature of the automotive parts and the control seed constraint rules. A die casting temperature evaluation factor setting module is used to set the die casting temperature evaluation factor for automotive parts, wherein the die casting temperature evaluation factor for automotive parts includes the dimensional accuracy of die-cast automotive parts, the surface quality of die-cast automotive parts, and the performance of die-cast automotive parts. The die casting temperature control optimization seed generation module is used to search and optimize the die casting temperature control population of automotive parts according to the evaluation factor of the die casting temperature of automotive parts, and generate a die casting temperature control optimization seed. A die-casting temperature control module is provided, wherein the die-casting temperature control is used to control the die-casting temperature of the automotive part to be die-cast according to the die-casting temperature control optimization seed.

Images