Dual-phase steel forming quality prediction and process adjustment method

Abstract

The invention provides a dual-phase steel forming quality prediction and process adjustment method, which relates to the technical field of dual-phase steel forming, and comprises the following steps: establishing a multi-dimensional data acquisition network; obtaining a process parameter combination; performing mapping correlation analysis on dual-phase steel forming quality fluctuation in the temperature field analog simulation space and the stress field analog simulation space in combination with process parameter combination; dividing the process parameter combination; and by taking a preset forming quality standard as a constraint condition, performing learning training on the second type of technological parameter components, the third type of technological parameter components and the fourth type of technological parameter components, and performing technological parameter adjustment. The technical problem that in the prior art, due to the fact that interaction of multiple technological parameters in the dual-phase steel forming process is complex, forming quality fluctuation is difficult to control accurately can be solved, accurate prediction of the forming quality and intelligent adjustment of the technological parameters are achieved by establishing the multi-dimensional data collection network and the analog simulation space, and the forming quality is accurately predicted. And the stability of product quality is ensured.

Description

Technical Field

[0001] The present application relates to the technical field of dual-phase steel forming, and in particular to a method for predicting the forming quality and adjusting the process of dual-phase steel. Background Art

[0002] Dual-phase steel is a high-strength low-alloy steel, mainly composed of ferrite and a small amount of martensite. It has good strength and plasticity. Therefore, it is widely used in the automotive, construction and manufacturing industries, especially for the forming of automobile bodies and structural parts. The forming process of dual-phase steel involves multiple variables, including forming temperature, pressure, time, material type, ratio, purity. There are complex interactions between these process parameters, and the effects of different process parameters on the final forming quality are not linear, which makes it difficult to accurately control the fluctuation of forming quality. Although common process parameters such as forming temperature, pressure and time can affect the performance of steel within a certain range, due to the complex interaction between these process parameters in actual production, it is difficult to take into account all influencing factors, resulting in unstable forming quality. Especially in the production process, due to slight changes in factors such as forming temperature and pressure, forming quality fluctuations often occur, which brings greater uncertainty to production.

[0003] In summary, the prior art has a technical problem that the forming quality fluctuation is difficult to accurately control due to the complex interaction of multiple process parameters in the dual-phase steel forming process. Summary of the invention

[0004] The purpose of this application is to provide a method for predicting the forming quality and adjusting the process of dual-phase steel, so as to solve the technical problem in the prior art that the forming quality fluctuation is difficult to accurately control due to the complex interaction of multiple process parameters in the dual-phase steel forming process.

[0005] In view of the above problems, the present application provides a method for predicting the forming quality and adjusting the process of dual-phase steel, wherein the method comprises: establishing a multi-dimensional data acquisition network, real-time monitoring of the dual-phase steel forming process, fitting the temperature field simulation space and the stress field simulation space; under standard environmental conditions, obtaining a combination of process parameters, wherein the combination of process parameters comprises the forming temperature, forming pressure, and forming time corresponding to the forming process indicators, and the material type, material ratio, and material purity corresponding to the material composition indicators; in the temperature field simulation space, mapping and correlating the dual-phase steel forming quality fluctuations with the combination of process parameters, and outputting a plurality of first influencing characteristics corresponding to the forming process indicators; in the stress field simulation space, In the simulation space, the process parameter combination is combined with the dual-phase steel forming quality fluctuation to perform mapping correlation analysis, and a plurality of second influencing characteristics corresponding to the material composition indicators are output; according to the plurality of first influencing characteristics and the plurality of second influencing characteristics, the process parameter combination is divided to obtain a first type of process parameter component, a second type of process parameter component, a third type of process parameter component, and a fourth type of process parameter component, wherein the first type of process parameter component is a parameter combination whose forming quality grade meets the preset forming quality standard; with the preset forming quality standard as a constraint condition, the second type of process parameter component, the third type of process parameter component, and the fourth type of process parameter component are learned and trained through the first type of process parameter component, and the process parameters are adjusted.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages: By establishing a multi-dimensional data acquisition network, the dual-phase steel forming process is monitored in real time, and the temperature field simulation space and the stress field simulation space are fitted; under standard environmental conditions, a process parameter combination is obtained, and the process parameter combination includes the forming temperature, forming pressure, and forming time corresponding to the forming process indicators, and the material type, material ratio, and material purity corresponding to the material composition indicators; in the temperature field simulation space, the process parameter combination is combined with the dual-phase steel forming quality fluctuation to perform mapping correlation analysis, and a plurality of first influencing characteristics corresponding to the forming process indicators are output; in the stress ... dual-phase steel forming quality fluctuation are output. Mapping association analysis is performed to output multiple second influencing characteristics corresponding to the material composition indexes; the process parameter combination is divided according to the multiple first influencing characteristics and the multiple second influencing characteristics to obtain the first type of process parameter components, the second type of process parameter components, the third type of process parameter components, and the fourth type of process parameter components, wherein the first type of process parameter components are parameter combinations whose forming quality levels meet the preset forming quality standards; with the preset forming quality standards as constraints, the second type of process parameter components, the third type of process parameter components, and the fourth type of process parameter components are trained and adjusted through the first type of process parameter components, and the process parameters are adjusted. In other words, by establishing a multidimensional data acquisition network, the key parameters in the dual-phase steel forming process are monitored in real time; in the temperature field and stress field simulation space, mapping association analysis is performed in combination with the process parameter combination to output the influencing characteristics; the process parameter combination is divided and trained according to the influencing characteristics, and the process parameters are adjusted, thereby realizing the accurate prediction of the forming quality and the intelligent adjustment of the process parameters, and ensuring the stability of the product quality.

[0007] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0009] Figure 1A schematic diagram of the process of the dual-phase steel forming quality prediction and process adjustment method of the present application; Figure 2 This is a schematic diagram of the process of loss calculation in the dual-phase steel forming quality prediction and process adjustment method of this application. DETAILED DESCRIPTION

[0010] This application solves the technical problem in the prior art that the fluctuation of forming quality is difficult to accurately control due to the complex interaction of multiple process parameters in the forming process of dual-phase steel by providing a method for predicting the forming quality and adjusting the process. By establishing a multi-dimensional data acquisition network, the key parameters in the dual-phase steel forming process are monitored in real time; in the temperature field and stress field simulation space, the process parameter combination is combined to perform mapping correlation analysis and output the influencing characteristics; the process parameter combination is divided and trained according to the influencing characteristics, and the process parameters are adjusted, thereby achieving accurate prediction of the forming quality and intelligent adjustment of the process parameters, ensuring the stability of product quality.

[0011] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0012] For examples, please see the attached Figure 1 The present application provides a dual-phase steel forming quality prediction and process adjustment method, wherein the dual-phase steel forming quality prediction and process adjustment method specifically includes the following steps: Step 1: Establish a multi-dimensional data acquisition network to monitor the dual-phase steel forming process in real time, and fit the temperature field simulation space and stress field simulation space.

[0013] Specifically, a multi-dimensional data acquisition network refers to a network that can collect multi-dimensional data in real time during the molding process. It obtains key data in the molding process in real time through sensors installed on production equipment (such as temperature sensors, pressure sensors, strain gauges, etc.), and transmits them to the analysis system to ensure that accurate data of molding temperature, stress and pressure can be obtained every second in the process. The layout of sensors should cover key areas of molding equipment, such as the inner wall of the mold, the working area of ​​the molding machine, etc. Multi-dimensional data usually includes molding temperature, pressure, stress distribution, displacement, etc. For example, select a thermocouple sensor that can measure high temperature, such as a K-type thermocouple, and ensure that its measurement range covers the temperature range during the molding process. Arrange multiple temperature sensors on the mold and material surface to monitor the temperature distribution at different locations. Select a sensor that can measure the pressure generated during the molding process, such as a piezoelectric pressure sensor or a strain gauge pressure sensor, and arrange a pressure sensor inside the mold or on the material surface to monitor the pressure changes during the molding process.

[0014] Select a strain gauge that can measure the strain of the material and stick it on the mold and material surface to monitor the strain distribution at different positions, and infer the stress by measuring the strain (deformation) of the material. When the material is deformed by force, the strain gauge will deform as the material expands and contracts, causing the resistance of the strain gauge to change. During deformation, the strain on the surface of the material is calculated by measuring the change in resistance of the strain gauge and the known strain coefficient. According to the stress-strain relationship of the material (such as Hooke's law), the strain value is converted into a stress value, which is usually obtained based on the elastic modulus of the material itself and the strain value measured by the strain gauge. The gauge coefficient is an important parameter used to describe the relationship between the change in resistance and the change in length of the material when it is deformed by force, reflecting the ratio between the change in resistance of the strain gauge and the actual deformation of the material. Different materials have different gauge coefficients. For example, the gauge coefficient of metals is usually between 2 and 5, and the gauge coefficient of semiconductors may be larger.

[0015] Continuous observation and recording of key process parameters during the forming process of dual-phase steel. The forming process of dual-phase steel is very sensitive to changes in temperature, pressure, and stress, so real-time monitoring of these data can help identify and control factors affecting quality, thereby ensuring that the product meets the preset requirements. Based on the collected temperature data, a temperature field model is generated in the simulation software. The construction of the temperature field usually relies on computer simulation software, such as finite element analysis (FEA) or computational fluid dynamics (CFD) and other simulation technologies to accurately simulate the temperature distribution in actual production. By establishing a temperature field model, the temperature distribution at different locations is predicted, thereby reflecting the temperature gradient of the material during the forming process. For example, there may be slight differences in temperature in different areas of the sheet forming, and these differences will affect the strength and performance of the material. The temperature field simulation simulation space refers to the three-dimensional space that uses computer models to simulate and predict the temperature distribution during the forming process, which can help engineers identify local temperature fluctuation problems and optimize the heating system to ensure uniform temperature.

[0016] The collected stress data is also used to construct a stress field model to predict the stress distribution of the material during the forming process. The stress field model can intuitively display the internal stress of the dual-phase steel plate during the forming process. For example, some areas may be at risk of fracture due to stress concentration. The establishment of a stress field simulation space can help optimize the mold design and forming pressure setting to ensure uniform strength of the material after forming and reduce structural weaknesses. By establishing a multi-dimensional data acquisition network and simulation space, accurate monitoring and control of the dual-phase steel forming process can be achieved, which helps to promptly discover and solve problems in the forming process, such as uneven temperature and stress distribution, thereby improving forming quality, reducing scrap rates, and improving production efficiency and material utilization.

[0017] Step 2: Under standard environmental conditions, a process parameter combination is obtained, wherein the process parameter combination includes a molding temperature, a molding pressure, a molding time corresponding to the molding process index, and a material type, a material ratio, and a material purity corresponding to the material composition index.

[0018] Specifically, standard environmental conditions refer to experiments or production under a specific, repeatable, and controllable environment, which usually includes certain temperature, humidity, air pressure and other factors to ensure that other variables in the production process are effectively controlled and the test results are highly comparable. Under standard environmental conditions, it is first necessary to define a controllable production environment. For example, set the temperature to 25°C and the humidity to 50%, and ensure that there are no other external interferences during the entire production process. Under this condition, collect and record various process parameters that affect the forming quality of duplex steel, including forming process indicators (such as forming temperature, forming pressure, forming time) and material composition indicators (such as material type, material ratio, material purity).

[0019] Forming process indicators refer to key process parameters directly related to the forming process, including but not limited to forming temperature, forming pressure, and forming time. Forming temperature refers to the temperature required to make the material (such as metal or alloy) reach a plastic state during the production process. For example, the setting of the forming temperature must ensure that the steel is in an ideal plastic state. Too high or too low will affect the quality of the final product. Usually, the forming temperature of duplex steel will be between 900°C and 1200°C. Forming pressure refers to the pressure applied to the material during the forming process, which is usually applied through a mold or forming equipment. The setting of the forming pressure is related to factors such as the design of the mold and the fluidity of the steel. Excessive pressure may lead to material waste, while too low pressure may lead to insufficient forming. Forming time refers to the length of time from the start of heating or pressurization of the material to the final completion of the forming. It depends on factors such as the heating rate of the material and the duration of the pressure, and needs to be optimized according to specific production conditions.

[0020] Material composition index refers to the composition of the material, including the type, proportion, purity, etc. of the material. The type of material refers to the specific material used to manufacture the product. For example, duplex steel may be composed of iron, carbon, chromium, nickel and other elements. The material proportion refers to the proportion of different elements or alloys that make up a certain material. The performance of duplex steel depends on the proportion of each component, and its performance is usually adjusted by the proportion of the alloy (such as carbon content, chromium content, etc.). Material purity refers to the proportion of pure components in the material. High-purity steel has better mechanical properties, and low-purity materials may have more impurities, affecting the quality of the final product.

[0021] According to the plan, prepare different types, different ratios, and different purity of dual-phase steel materials. Under standard environmental conditions, carry out multiple forming tests according to the test plan. In each test, record the forming process parameters (forming temperature, forming pressure, forming time, etc.) and material composition indicators (material type, material ratio, material purity, etc.). By obtaining the forming data under different process parameter combinations, analyze the influence of the forming process parameters on the forming quality, and determine the key process parameters that affect the forming quality.

[0022] Step three: in the temperature field simulation space, mapping and correlation analysis are performed on the dual-phase steel forming quality fluctuation in combination with the process parameter combination, and a plurality of first influencing characteristics corresponding to the forming process indicators are output.

[0023] Specifically, different preliminary process parameter combinations, including molding temperature, molding pressure, molding time, etc., are input into the temperature field simulation space to observe the effects of different parameter combinations on the temperature field. The fluctuation of the molding quality of dual-phase steel refers to the fluctuation or change of the molding quality due to the change of process parameters during the molding process. For example, a slight fluctuation in the molding temperature may cause a difference in the hardness or corrosion resistance of the dual-phase steel. Mapping association analysis is a method of associating and analyzing the relationship between different variables. By measuring the quality indicators of the finished product such as hardness, ductility, and corrosion resistance, and combining the fluctuation of the molding quality, a mapping association analysis is performed. By establishing a mapping relationship between each parameter (such as temperature, pressure, and time) and the molding quality, it is clear how different parameters affect the quality of the finished product, so as to optimize the process. For example, it is assumed that the toughness of the dual-phase steel decreases when the temperature is higher than 1000°C, and the strength of the material cannot meet the standard when it is lower than 950°C. The relationship between temperature fluctuation and quality fluctuation is quantified through the mapping association analysis method. Through mapping analysis, the correlation between the forming process indicators (such as temperature, pressure, and time) and the quality of the finished product is extracted, and the factors that have a significant impact on quality fluctuations are defined as the first influencing characteristics, including temperature uniformity, cooling rate, and time to maintain temperature. The first influencing characteristics refer to the key influencing factors directly related to the forming process indicators obtained through correlation analysis, which directly affect the forming quality. By performing mapping correlation analysis in the temperature field simulation space, the process parameters that have a significant impact on the forming quality of dual-phase steel are identified, and the optimal range of these parameters is determined, which helps to optimize the forming process and improve the forming quality.

[0024] Step 4: In the stress field simulation space, mapping and correlation analysis are performed on the dual-phase steel forming quality fluctuation in combination with the process parameter combination, and a plurality of second influencing characteristics corresponding to the material composition indicators are output.

[0025] Specifically, similar to the above steps, in the stress field simulation space, different combinations of process parameters are input to observe and analyze how these parameters affect the forming quality of dual-phase steel. During the simulation process, observe and record the quality fluctuations during the forming process. For example, by analyzing the simulation results, find out which material composition combinations will cause problems such as insufficient hardness or decreased ductility in the finished product. Establish a correlation mapping between quality fluctuations and material composition, and quantify the influence of material composition on stress distribution. For example, it is found that a certain material ratio will cause insufficient tensile strength of the material at a specific temperature. Through mapping correlation analysis, the key influencing factors of material composition indicators (such as type, ratio, purity) on quality fluctuations are obtained, which are called second influencing characteristics. The second influencing characteristics refer to the material composition indicator characteristics that have a significant impact on the forming quality obtained through correlation analysis, which directly reflect the influence of material composition on quality fluctuations, such as material toughness, fatigue performance, etc. For example, through simulation analysis, it is found that after increasing the purity of chromium-containing dual-phase steel to 95%, its toughness and stress distribution uniformity can be improved. By performing mapping correlation analysis in the stress field simulation space, the key material parameters that affect the molding quality, such as material type and material ratio, are determined, thereby optimizing material selection and ratio.

[0026] Step 5: According to the multiple first influencing characteristics and the multiple second influencing characteristics, the process parameter combinations are divided to obtain a first process parameter component, a second process parameter component, a third process parameter component, and a fourth process parameter component. The first process parameter component is a parameter combination whose molding quality grade meets the preset molding quality standard.

[0027] Specifically, through temperature field and stress field simulation, multiple first influencing characteristics of molding process indicators and multiple second influencing characteristics of material composition indicators are obtained respectively. Each molding process (temperature, pressure, time) and material composition (type, proportion, purity) has different effects on molding quality. Based on the combination of the first influencing characteristics and the second influencing characteristics, it is determined which parameter combinations are conducive to achieving high-quality finished products. According to the contribution of the first influencing characteristics and the second influencing characteristics to the molding quality, the parameter combinations are divided into different categories, namely the first process parameter component, the second process parameter component, the third process parameter component, and the fourth process parameter component.

[0028] The first type of process parameter component refers to a combination of parameters that can make the molding quality reach or exceed the preset standard, meet all molding quality standards, and usually show a stable and uniform state in terms of temperature, pressure, material composition, etc., which can ensure that the finished product meets the preset quality standards, and show excellent hardness, strength and ductility, which is an ideal production condition. In other words, under these combination conditions, the key performance indicators of duplex steel such as hardness, strength, ductility, and fatigue resistance fully meet or exceed the expected quality standards. The process conditions (such as molding temperature, molding pressure, molding time) and material composition (such as material type, ratio, purity) in these parameter combinations have a positive impact on molding quality and are positively correlated with molding quality indicators. The second type of process parameter component is a combination of process parameters that are negatively correlated with the first influencing characteristic and the molding quality grade does not meet the preset molding quality standard. In other words, certain process conditions (such as too high temperature and too high pressure) have an adverse effect on molding quality, resulting in substandard quality of the final finished product. The process conditions in the second category of parameter components have a negative impact on the molding quality. For example, too high a temperature will cause the material grains to coarsen and affect the hardness; or too long a molding time will cause the product surface to deform. There is often a certain deviation between the key quality indicators and the expected standards.

[0029] The third category of process parameter components is the parameter combination with the lowest molding quality grade and does not meet the preset molding quality standards. There are obvious deficiencies in temperature, pressure, material composition, etc., resulting in a molding quality that is significantly lower than the standard, and the process parameters need to be optimized. In the third category, not only the process conditions and material composition fail to meet the requirements, but also the impact on the molding quality is more significant. Whether it is the first or second influencing characteristics, it has an adverse effect on key indicators such as hardness and ductility of the finished product, and is usually not adopted. The fourth category of process parameter components is a combination of process parameters that is negatively correlated with the second influencing characteristic and the molding quality grade does not meet the preset molding quality standards. Negative correlation mainly refers to the negative impact of material composition (such as material type, ratio, purity) on molding quality. The material composition of the fourth category of components has an adverse effect on various indicators of molding quality. For example, low material purity will lead to a decrease in hardness and ductility, or an improper proportion of specific components will increase the brittleness of the finished product. The molding quality can be improved by optimizing the material composition (such as adjusting the purity or proportion). Through classification, it is clear to identify which process parameter combinations are effective and which need to be improved.

[0030] Step six: taking the preset molding quality standard as a constraint condition, the second process parameter component, the third process parameter component and the fourth process parameter component are trained through the first process parameter component, and the process parameters are adjusted.

[0031] Specifically, the preset forming quality standard is the target performance standard set according to the product application requirements before production. It is used to determine whether the forming process meets the standard. It covers the most important performance indicators in the forming of dual-phase steel, such as hardness, tensile strength, ductility, fatigue resistance, etc. The entire optimization process is constrained within the preset forming quality standard. In other words, no matter how the process parameters are adjusted, the ultimate goal is to make the product quality meet or approach the predetermined standard. The first type of process parameter component is an ideal process parameter combination that meets the preset forming quality standard. Learning and training are performed based on these ideal process parameter combinations. The goal of learning and training is to further understand which process parameters are most critical to the quality of the final product and how to optimize and improve the overall production efficiency and product quality through machine learning, data analysis or optimization algorithms. Feature extraction is performed on the first type of process parameter component to obtain the first primary model data. Feature extraction is performed on the second type of process parameter component, the third type of process parameter component, and the fourth type of process parameter component to obtain the second primary model data.

[0032] After learning and training the first type of process parameter components, a set of optimized process parameters can be obtained to meet the preset quality standards. On this basis, the second, third, and fourth types of process parameter components that do not meet the standards are adjusted. These non-standard parameter combinations are adjusted to be as close as possible to the first type of process parameter components to ensure that the non-standard parts of the production process can eventually reach or approach the predetermined molding quality standards through optimization. Through the loss function, the loss of the second primary model data is calculated with the first primary model data to measure the difference with the target. By optimizing the loss function, the model adjustment is guided so that the output process parameter combination can meet the set quality standards.

[0033] Furthermore, step five of this application also includes: The third category of process parameter components consists of parameter combinations whose molding quality grades do not meet the preset molding quality standards; the molding quality grades of the first category of process parameter components, the molding quality grades of the second category of process parameter components, and the molding quality grades of the fourth category of process parameter components are all higher than the molding quality grades of the third category of process parameter components.

[0034] Specifically, the molding quality grade refers to the grading of the molding quality of the product according to specific quality assessment standards during the production process, so as to clarify the quality level that can be achieved by each process parameter combination. The molding quality grade usually reflects the key physical and mechanical properties of the product, such as hardness, tensile strength, ductility, fatigue resistance, etc. The preset molding quality standard is the target performance standard set according to the product application requirements before production. It is used to judge whether the molding process meets the standard and covers the most important performance indicators in duplex steel molding, such as hardness, tensile strength, ductility, fatigue resistance, etc. The third category of process parameter components is a parameter combination whose quality grade does not meet the preset molding quality standard, indicating that it has significant deficiencies in temperature, pressure, time, material purity, etc., which may be due to improper material selection, unreasonable material ratio or unreasonable molding process parameter setting. Cause defects in the molding process, such as cracks, deformation, uneven organization, etc., ultimately lead to unqualified molding quality, and therefore are usually not used in actual production. Although the molding quality of the second and fourth category process parameter components may not fully meet the preset standard, it is still higher than the molding quality of the third category process parameter components. The third category of process parameter components has the lowest quality grade and cannot meet the preset molding quality standards, while the molding qualities of other categories (first, second and fourth categories) are higher than those of the third category.

[0035] Furthermore, the present application also includes the following steps: The second category of process parameter groups includes parameter combinations that are negatively correlated with the multiple first influencing characteristics and whose molding quality levels do not meet the preset molding quality standards; the fourth category of process parameter groups includes parameter combinations that are negatively correlated with the multiple second influencing characteristics and whose molding quality levels do not meet the preset molding quality standards.

[0036] Specifically, the process conditions (such as temperature, pressure, and time) in the second category of process parameter components are negatively correlated with multiple first influencing characteristics of molding quality. Negative correlation means that when one influencing characteristic increases, the molding quality decreases. For example, too high molding temperature may cause the material to become brittle, and too high pressure or too long time may cause structural deformation, all of which will reduce the molding quality level. The second category of process parameter components is a combination of parameters whose molding quality level does not meet the preset molding quality standards, such as key indicators such as hardness, ductility or tensile strength are lower than the specified values.

[0037] The material composition indicators (such as material type, composition ratio, purity) in the fourth category of process parameter components are negatively correlated with multiple secondary influencing characteristics of molding quality. For example, insufficient material purity may lead to reduced strength of the finished product, or excessive proportion of a certain material may lead to reduced toughness. The fourth category of process parameter components may fail to meet the standard requirements for material strength and toughness after molding due to improper material selection or unreasonable material ratio, such as using materials with poor performance or material ratios that do not meet the requirements.

[0038] Further, as attached Figure 2 As shown, the application also includes the following steps: Based on the first category of process parameter components, feature extraction is performed to obtain first primary model data; based on the second category of process parameter components, the third category of process parameter components, and the fourth category of process parameter components, feature extraction is performed to obtain second primary model data; a loss function is set according to the difference between the preset molding quality standard and the corresponding molding quality grade, and the loss of the second primary model data is calculated using the first primary model data.

[0039] Specifically, the first type of parameter components have met the molding quality standards, so the features of the optimal process parameter combination can be obtained in feature extraction, and these features represent the key indicators for successful production. Representative features are extracted from the first type of process parameter components to simplify the data volume and extract the key factors affecting molding quality. In process control, feature extraction includes data analysis of process conditions (such as temperature, pressure) and material composition (such as ratio, purity), identifying and selecting process parameters most relevant to molding quality, such as molding temperature, pressure, time, and material composition. In other words, according to the correlation of molding quality, the parameters that have the greatest impact on the molding results are selected as features, and then statistical methods (variance analysis, correlation analysis) or machine learning techniques (such as principal component analysis PCA, feature selection algorithm, etc.) are used to extract key features from the data, and the extracted features are combined into the first primary model data. Variance analysis specifically calculates the variance of the impact of each parameter on the quality index, so as to evaluate the contribution of each parameter to the fluctuation of molding quality. If the variance value of temperature is large, it means that temperature has a greater impact on the fluctuation of molding quality. Correlation analysis specifically calculates the correlation coefficient between process parameters and quality indicators (such as the Pearson correlation coefficient) and identifies the positive and negative correlation between parameters such as molding temperature and pressure and molding quality. Principal component analysis refers to converting multiple process and material parameters into a few principal components, thereby extracting comprehensive features that have an important impact on molding quality. Through principal component analysis, the most important components (such as the combination of temperature and material purity) are identified as the dominant features of molding quality, while ignoring some minor influencing factors. The feature selection algorithm determines the parameters that contribute most to molding quality by gradually removing features that have little impact on the model.

[0040] Similarly, features are extracted from the second, third, and fourth process parameter components that do not meet the quality standards to generate the second primary model data, which includes the features of process parameters that do not meet the quality standards due to improper process conditions or material composition, reflecting the adverse influencing factors. Based on the features of the second, third, and fourth process parameter components, data of substandard parameter combinations, namely the second primary model data, are constructed for subsequent comparative analysis with the first primary model data to optimize process conditions and material ratios.

[0041] According to the difference between the preset molding quality standard and the molding quality grade of different process parameter components, a loss function is designed to calculate the error between the first primary model data and the second primary model data to indicate the deviation between the parameter combination that does not meet the standard and the qualified parameter combination. The loss function is used to calculate the deviation or error between the model output and the expected target. By optimizing the loss function, the model is guided to be closer to the preset molding quality standard. According to the difference between the molding quality standard and the quality grade of different process parameter components, it is set to calculate the quality loss under different parameter combinations. The goal of the loss function is to reduce the difference between the first primary model data and the second primary model data through continuous iteration so that the data of the second primary model (i.e., the process parameter combination) can better meet the preset molding quality standard. Using the loss function, the loss calculation of the second primary model data is performed based on the first primary model data, and the loss function is continuously optimized to identify the key factors affecting the molding quality and the process conditions and material components that should be avoided. The defects in the suboptimal data are identified and corrected through high-quality data, so that the process parameters (such as temperature and pressure) can be adjusted to the range that meets the standard, thereby improving the overall quality level of the finished product.

[0042] Furthermore, the present application also includes the following steps: The second primary model data is updated iteratively through the loss function to update the second type of process parameter components, the third type of process parameter components, and the fourth type of process parameter components; the loss function: ;in, is a loss function used to measure the difference between the preset molding quality standard and the corresponding molding quality grade. is the cross entropy loss function, α is the weight coefficient, which is used to balance the consistency between the first primary model data and the second primary model data and the consistency between the second primary model data and the parameter combination under the true label. is the prediction function of the first primary model for the input data X, is the prediction function of the second primary model for the input data X, and y is the parameter combination under the true label.

[0043] Specifically, the loss function is used to measure the difference between the predicted result and the actual target. The specific formula is: Among them, L dp It is a loss function used to measure the difference between the preset molding quality standard and the corresponding molding quality grade. It is divided into two parts. measure the difference between the first primary model data and the second primary model data, Measures the difference between the second primary model data and the true label data. L ce is the cross entropy loss function, which is used to measure the difference between two probability distributions, that is, the difference between the predicted value and the true value. α is a weight coefficient, which is used to balance the consistency of the first primary model data with the second primary model data and the consistency of the parameter combination under the second primary model data and the true label. If α is large, more attention is paid to the data consistency of the first model, and if α is small, more attention is paid to the true label consistency of the second primary model. is the prediction function of the first primary model for the input data X, which represents the prediction function based on the input data X and The predicted output is It is the parameter of the first primary model, which predicts the process quality based on the first type of process parameter components, and aims to learn from the process parameters that meet the quality standards and generate high-quality prediction results. is the prediction function of the second primary model for the input data X, which represents the prediction function based on the input data X and The predicted output is is the parameter of the second primary model, which predicts the process quality based on the second, third and fourth process parameter components, aiming to learn from the process parameter combinations that do not meet the quality standards to optimize the production process and reduce the occurrence of unqualified products. y is the true label, that is, the preset target output, which represents the quality standard that the process parameters should achieve in actual production.

[0044] According to the input data X, through the first primary model and the second primary model The process parameter components are predicted and the prediction results are obtained. Then the cross entropy loss function L ce Calculate the difference between the predicted value and the true label. Weigh the difference between the prediction of the first primary model and the prediction of the second primary model, and adjust its importance using the weight coefficient α. Weigh the difference between the prediction of the second primary model and the true label (i.e., the process standard), and use (1-α) as the weight coefficient. In each training iteration, according to the calculated total loss L dp , update the model parameters through optimization algorithms (such as gradient descent) and , through multiple iterations of optimization, the model can gradually reduce the loss, and finally make the prediction results closer to the true label, and optimize the process parameter combination. By iteratively optimizing the loss function, the second, third, and fourth category process parameter components are gradually adjusted. Through the iterative process, the parameters of the model are gradually adjusted to better match the real data, resulting in the update of the second primary model data, so that it can more accurately predict the molding quality grade, reduce the fluctuation in the production process, and finally meet the quality standards. As the second primary model data is updated, the second, third, and fourth category process parameter components are re-evaluated and classified according to the new prediction results. Those parameter combinations that originally belonged to the second or fourth category may be reclassified as the first category if the new prediction results show that their molding quality grade has improved. Similarly, the parameter combinations that originally belonged to the third category may remain unchanged or further downgraded if the prediction results show that their molding quality grade has decreased. By iteratively optimizing with the loss function, the parameters of the second primary model (i.e., the process parameter combination) are continuously adjusted, and the process parameters (such as molding temperature, pressure, material composition, etc.) are gradually optimized, thereby improving the molding quality of the product.

[0045] Furthermore, the present application also includes the following steps: iteratively updating the second primary model data, ;in, is the parameter of the next update of the second primary model, is the last updated parameter of the second primary model, are the current parameters of the second primary model, is the learning rate, is the gradient of the loss function with respect to the second primary model data.

[0046] Specifically, the second primary model data is iteratively updated using the gradient descent method: ,in, It is the parameter of the next update of the second primary model, that is, the parameter after the update in this round of iteration. After each iteration, the parameters of the model will be adjusted until they reach the optimal value. are the parameters of the second primary model last updated, that is, the parameters before this iteration. The learning rate is a hyperparameter that controls the step size of each parameter update and determines the amplitude of parameter adjustment. A learning rate that is too small may lead to slow convergence, while a learning rate that is too large may lead to unstable training or failure to converge. is the gradient of the loss function with respect to the second primary model data. The gradient is a vector that indicates the rate of change of the loss function at the current parameter position. In other words, it indicates how to adjust the model parameters to reduce the value of the loss function. The direction of the gradient is the direction in which the loss function decreases fastest, and the magnitude of the gradient is the magnitude of the adjustment. dpIt is the loss function, which measures the difference between the current model output and the actual target, that is, the loss function of the second primary model (such as cross entropy loss or mean square error, etc.), which measures the error between the predicted result and the actual target. is the current parameter of the second primary model. First, calculate the loss function L dp About Model Parameters The gradient of , which represents the trend of the loss function under the current parameter settings, indicating in which directions the current model has room for improvement. According to the direction and size of the gradient, the model parameters are updated by subtracting the gradient multiplied by the learning rate. The core idea of ​​gradient descent is to adjust the parameters in the opposite direction of the gradient to reduce the value of the loss function (i.e., the optimization target). In this way, the parameters of the model continue to approach the optimal solution in each iteration, and eventually a model with minimum loss can be generated. By continuously iterating this process and updating the parameters, the performance of the model gradually improves until a convergence point is reached, that is, the loss function no longer changes significantly, or the change is very small, indicating that the model has found a better parameter combination. By calculating the gradient of the loss function with respect to the model parameters and updating them according to the gradient, the parameters of the model are continuously adjusted to gradually optimize the molding quality.

[0047] Furthermore, the present application also includes: Taking the preset molding quality standard as a constraint condition, feature extraction is performed based on the second and third process parameter components to obtain third primary model data; taking the preset molding quality standard as a constraint condition, feature extraction is performed based on the fourth and third process parameter components to obtain fourth primary model data; setting an upper limit on the number of iterations for the second, third and fourth primary model data, respectively, and introducing an iterative competition mechanism.

[0048] Specifically, according to the preset molding quality standard, attention is paid to those process parameters that can make the molding quality meet the standard. The combination of the third process parameter component and the second process parameter component is used to generate the third primary model data. Since the third process parameter component is usually a combination of parameters that do not meet the preset standard for the molding quality grade, and the second process parameter component is negatively correlated with multiple first influencing characteristics, these parameters are combined to understand how to improve and optimize the production process under process conditions that do not meet the quality standards. Features related to molding quality, such as process stability, quality fluctuation, molding time, etc., are extracted from the second process parameter component and the third process parameter component to form the third primary model data. The combination of the fourth process parameter component and the third process parameter component is used to generate the fourth primary model data. The fourth process parameter component is related to the influencing characteristics of molding quality fluctuations, especially when the molding quality does not meet the preset standard, it can provide valuable feedback for optimization. Features are extracted from the fourth process parameter component and the third process parameter component, especially focusing on those features related to the molding quality grade not meeting the standard, and further optimizing the process parameters.

[0049] Setting an upper limit on the number of iterations can prevent the model from overfitting and ensure that the optimization process is completed in a limited time. For each model (second, third, and fourth primary models), there is a fixed upper limit on the number of iterations. When the model has converged to a good solution before this upper limit, the iteration stops. If it does not converge within the upper limit, the iteration will continue until the maximum number is reached. The iterative competition mechanism compares and competes multiple primary models (second, third, and fourth primary models) to select the best model output. Specifically, the three models are trained and optimized at each iteration, and their performance is evaluated by the loss function. The goal of each model is to minimize the difference from the preset molding quality standard, that is, to achieve the best molding quality. In each round of iteration, all models compete with each other and calculate their own loss values. Finally, by comparing the loss values ​​of each model, the best performing model is selected for the next optimization. For example, if the data quality of the second primary model is better than that of the third and fourth primary models, the second primary model will be selected as the priority optimization object. By extracting features, setting an upper limit on the number of iterations, and introducing an iterative competition mechanism, the process parameters can be optimized efficiently to ensure that the final process can meet the preset molding quality standards. Through the combination of different categories of process parameters, multiple primary model data are generated, and the production process and product quality are continuously improved through competition mechanism and optimization process.

[0050] Furthermore, the present application also includes the following steps: A resource allocation matrix is ​​established according to the multiple first influencing characteristics and the multiple second influencing characteristics; and based on the resource allocation matrix, resource allocation adjustment is performed on the second primary model data, the third primary model data, and the fourth primary model data.

[0051] Specifically, the first influencing characteristic is usually related to the molding process indicators (such as temperature, pressure, etc.), representing the impact of the core parameters in the molding process on the product quality. The second influencing characteristic is usually related to the material composition, describing the impact of factors such as the material ratio, type, purity, etc. on the molding quality. The resource allocation matrix is ​​a mathematical tool that aims to express how to allocate resources between different parameters and features in the form of a matrix, and to show the relationship between multiple influencing factors (such as influencing characteristics) and different model data. Each influencing characteristic is associated with the corresponding process parameters and model data to find out which influencing characteristics have a greater impact on different primary models (such as the second primary model, the third primary model, etc.). The construction of the resource allocation matrix is ​​based on multiple first influencing characteristics and multiple second influencing characteristics, and resources are reasonably allocated by analyzing how these characteristics affect the adjustment of process parameters and model optimization.

[0052] The resource allocation matrix may be a two-dimensional matrix, with each row representing an influencing characteristic and each column representing a specific data model (such as the second primary model, the third primary model, etc.). Each element in the matrix represents the resource allocation relationship (such as weight or degree of influence) between the influencing characteristic and the model. For example, the elements of the matrix can be the correlation, weight or degree of influence between the influencing characteristic and the model. If a certain characteristic has a greater impact on a certain model, a larger value is assigned to the corresponding position in the matrix, indicating that more resources need to be allocated to the model. If some models respond more strongly to certain influencing characteristics, more resources are allocated to these models. On the contrary, fewer resources are allocated between characteristics and models with less impact. According to the results of the resource allocation matrix, the data of the second, third and fourth primary models are adjusted. Through the reasonable allocation of resources, the model training process is optimized to ensure that each primary model is most appropriately adjusted under its most important influencing characteristic, thereby improving the efficiency of process optimization and product quality.

[0053] In summary, the dual-phase steel forming quality prediction and process adjustment method provided in this application has the following technical effects: By establishing a multi-dimensional data acquisition network, the dual-phase steel forming process is monitored in real time, and the temperature field simulation space and the stress field simulation space are fitted; under standard environmental conditions, a process parameter combination is obtained, and the process parameter combination includes the forming temperature, forming pressure, and forming time corresponding to the forming process indicators, and the material type, material ratio, and material purity corresponding to the material composition indicators; in the temperature field simulation space, the process parameter combination is combined with the dual-phase steel forming quality fluctuation to perform mapping correlation analysis, and a plurality of first influencing characteristics corresponding to the forming process indicators are output; in the stress ... dual-phase steel forming quality fluctuation are output. Mapping association analysis is performed to output multiple second influencing characteristics corresponding to the material composition indexes; the process parameter combination is divided according to the multiple first influencing characteristics and the multiple second influencing characteristics to obtain the first type of process parameter components, the second type of process parameter components, the third type of process parameter components, and the fourth type of process parameter components, wherein the first type of process parameter components are parameter combinations whose forming quality levels meet the preset forming quality standards; with the preset forming quality standards as constraints, the second type of process parameter components, the third type of process parameter components, and the fourth type of process parameter components are trained and adjusted through the first type of process parameter components, and the process parameters are adjusted. In other words, by establishing a multidimensional data acquisition network, the key parameters in the dual-phase steel forming process are monitored in real time; in the temperature field and stress field simulation space, mapping association analysis is performed in combination with the process parameter combination to output the influencing characteristics; the process parameter combination is divided and trained according to the influencing characteristics, and the process parameters are adjusted, thereby realizing the accurate prediction of the forming quality and the intelligent adjustment of the process parameters, and ensuring the stability of the product quality.

[0054] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0055] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A method for predicting the forming quality and adjusting the process of dual-phase steel, characterized in that: include: Establish a multi-dimensional data acquisition network to monitor the dual-phase steel forming process in real time, and fit the temperature field simulation space and stress field simulation space; Under standard environmental conditions, a process parameter combination is obtained, wherein the process parameter combination includes a molding temperature, a molding pressure, and a molding time corresponding to a molding process index, and a material type, a material ratio, and a material purity corresponding to a material composition index; In the temperature field simulation space, mapping and correlation analysis are performed on the dual-phase steel forming quality fluctuation in combination with the process parameter combination, and a plurality of first influencing characteristics corresponding to the forming process indicators are output; In the stress field simulation space, mapping and correlation analysis are performed on the dual-phase steel forming quality fluctuation in combination with the process parameter combination, and a plurality of second influencing characteristics corresponding to the material composition indicators are output; According to the multiple first influencing characteristics and the multiple second influencing characteristics, the process parameter combination is divided to obtain a first type of process parameter component, a second type of process parameter component, a third type of process parameter component, and a fourth type of process parameter component, wherein the first type of process parameter component is a parameter combination whose molding quality level meets the preset molding quality standard; Taking the preset molding quality standard as a constraint condition, the second type of process parameter component, the third type of process parameter component and the fourth type of process parameter component are learned and trained through the first type of process parameter component, and the process parameters are adjusted.

2. The dual-phase steel forming quality prediction and process adjustment method according to claim 1, characterized in that: The third type of process parameter group is a parameter combination whose molding quality level does not meet the preset molding quality standard; The molding quality grade of the first category of process parameter components, the molding quality grade of the second category of process parameter components, and the molding quality grade of the fourth category of process parameter components are all higher than the molding quality grade of the third category of process parameter components.

3. The dual-phase steel forming quality prediction and process adjustment method according to claim 2, characterized in that: The second type of process parameter group is a parameter combination that is negatively correlated with the plurality of first influencing characteristics and whose molding quality level does not meet the preset molding quality standard; The fourth type of process parameter group includes parameter combinations that are negatively correlated with the plurality of second influencing characteristics and whose molding quality levels do not meet the preset molding quality standards.

4. The dual-phase steel forming quality prediction and process adjustment method according to claim 3, characterized in that: include: Perform feature extraction based on the first type of process parameter components to obtain first primary model data; Perform feature extraction based on the second type of process parameter components, the third type of process parameter components, and the fourth type of process parameter components to obtain second primary model data; A loss function is set according to the difference between the preset molding quality standard and the corresponding molding quality grade, and the loss calculation is performed on the second primary model data using the first primary model data.

5. The dual-phase steel forming quality prediction and process adjustment method according to claim 4, characterized in that: Iteratively updating the second primary model data through the loss function, updating the second type of process parameter components, the third type of process parameter components, and the fourth type of process parameter components; The loss function: ; in, is a loss function used to measure the difference between the preset molding quality standard and the corresponding molding quality grade. is the cross entropy loss function, α is the weight coefficient, which is used to balance the consistency between the first primary model data and the second primary model data and the consistency between the second primary model data and the parameter combination under the true label. is the prediction function of the first primary model for the input data X, is the prediction function of the second primary model for the input data X, is the parameter combination under the true label.

6. The dual-phase steel forming quality prediction and process adjustment method according to claim 5, characterized in that: iteratively updating the second primary model data, ; in, is the parameter of the next update of the second primary model, is the last updated parameter of the second primary model, are the current parameters of the second primary model, is the learning rate, is the gradient of the loss function with respect to the second primary model data.

7. The dual-phase steel forming quality prediction and process adjustment method according to claim 6, characterized in that: Taking the preset molding quality standard as a constraint condition, performing feature extraction based on the second type of process parameter components and the third type of process parameter components to obtain third primary model data; Taking the preset molding quality standard as a constraint condition, feature extraction is performed based on the fourth type of process parameter components and the third type of process parameter components to obtain fourth primary model data; An upper limit on the number of iterations is set for the second primary model data, the third primary model data, and the fourth primary model data, respectively, and an iteration competition mechanism is introduced.

8. The dual-phase steel forming quality prediction and process adjustment method according to claim 7, characterized in that: The third primary model data, the fourth primary model data, and the first primary model data are respectively set with an upper limit on the number of iterations, and an iteration competition mechanism is introduced, including: Establishing a resource allocation matrix according to the plurality of first influencing characteristics and the plurality of second influencing characteristics; Based on the resource allocation matrix, resource allocation adjustment is performed on the second primary model data, the third primary model data, and the fourth primary model data.

Images