Performance constraint based engineering material extrusion control system

Abstract

The application discloses a kind of engineering material extrusion control systems based on performance constraint, it is related to engineering manufacturing relevant technical field, the system includes: obtaining the performance analysis data of engineering material;Carry out data stability probability analysis, determine constraint performance based on data trend stability probability;Supporting degree relationship operation of decomposed parameter is carried out using process target result, obtain process core control parameter;The mapping relationship of constraint performance and process core control parameter is established;Control target maximum control parameter optimization is carried out, obtains extrusion control information, sends to control center and carries out extrusion operation process control.It solves the technical problems that the existing engineering material extrusion control exists, such as the key parameters in the extrusion process cannot be monitored in real time and accurately controlled, thereby leading to unstable product quality and low production efficiency, realizes the automatic adjustment of extrusion parameters, and achieves the technical effects of improving the stability of product quality and production efficiency.

Description

Technical Field

[0001] This application relates to the field of engineering manufacturing technology, specifically to a performance-constrained extrusion control system for engineering materials. Background Technology

[0002] Engineering material extrusion control systems are one of the key technologies in modern industrial manufacturing, playing a crucial role, especially in the processing of engineering materials such as plastics, rubber, and composite materials. With the continuous development of industrial manufacturing technology, the requirements for engineering material extrusion control systems are also increasing. In actual production applications, the extrusion process of engineering materials involves multiple complex variables that directly affect product quality and production efficiency. Traditional extrusion control systems often cannot achieve precise control of key parameters such as material flow rate, temperature, and pressure during the extrusion process, resulting in unstable product quality and low production efficiency, making it difficult to meet the needs of modern industry for efficient and high-quality production.

[0003] Therefore, current technologies related to the control of extrusion in engineering materials suffer from the technical problem of difficulty in real-time monitoring and precise control of key parameters during the extrusion process, which leads to unstable product quality and low production efficiency. Summary of the Invention

[0004] This application provides a performance-constrained engineering material extrusion control system. By employing techniques such as parameter decomposition calculation, establishing mapping relationships, and backtracking search optimization, it solves the technical problems of existing engineering material extrusion control systems, which suffer from the difficulty in real-time monitoring and precise control of key parameters in the extrusion process, leading to unstable product quality and low production efficiency. The system achieves automatic adjustment of extrusion parameters, thereby improving the stability of product quality and the efficiency of production.

[0005] This application provides a performance-constrained extrusion control system for engineering materials. The system includes: a performance analysis data acquisition module, which connects to a performance analysis platform to acquire performance analysis data of the engineering materials, including material viscosity, temperature-flowability, pressure-deformation relationship, and material composition-performance relationship; a constraint performance determination module, which performs data stability probability analysis based on the performance analysis data and determines constraint performance based on the data trend stability probability, wherein the constraint performance is a performance parameter whose data trend stability probability exceeds a preset range; a decomposition parameter calculation module, which decomposes the extrusion control process into parameters and performs support relationship calculation on the decomposed parameters using the process target results to obtain core process control parameters, wherein the core process control parameters are process control parameters whose support meets the screening requirements; a mapping relationship establishment module, which establishes a mapping relationship between the constraint performance and the core process control parameters and configures process optimization variables; and an extrusion operation process control module, which optimizes control parameters based on the process optimization variables to maximize the control target, obtains extrusion control information, and sends it to the control center for extrusion operation process control.

[0006] In a possible implementation, the extrusion operation process control module further performs the following processing: based on the process optimization variables, sets search constraints to search the control parameter sample set, randomly generating a first population and a second population; based on the first population and the second population, determines the update search center and update search direction, wherein the update search center is determined by the magnitude of a random number; using the update search center and update search direction, performs process variable control scheme mutation according to a set step size to obtain a mutated population; swaps individual elements in the second population with elements at the same position in the mutated population to generate new samples; when the evaluation value of the new sample exceeds the evaluation value of individual elements in the second population, performs population update; when the evaluation value of the new sample is lower than the evaluation value of individual elements in the second population, eliminates the new sample and marks the corresponding individual sample as a termination marker to indicate that update search is prohibited; repeats the population update iteratively until the optimization stopping target is reached, and obtains the process variable control scheme with the optimal evaluation value as the extrusion control information.

[0007] In a possible implementation, the performance analysis data acquisition module further performs the following processing: constructing a twin simulation module and inserting it into the performance analysis platform; using the twin simulation module, based on temperature, pressure, and material composition ratio as independent variables, performing target quantity tests on material viscosity, flowability, deformation, and material stability, and recording simulation test data; performing data fitting on independent variables and target quantities respectively to obtain the influence relationship; establishing the mapping relationship between the influence relationship, independent variables, and target quantities to construct the performance analysis data of the engineering material.

[0008] In a possible implementation, the performance analysis data acquisition module further performs the following processing: based on the adjustment step size and influence relationship of the independent variable, performs stability probability analysis to determine the stable trend of the data; based on the stable trend of the data, performs trend segmentation, including regular trend regions and abnormal drop regions, wherein the regular trend regions are stable development regions that match the influence relationship, and the abnormal drop regions are regions where the development trend direction changes and does not match the influence relationship; and determines the constraint performance according to the segmentation nodes of the regular trend regions and abnormal drop regions.

[0009] In a possible implementation, the decomposition parameter calculation module further performs the following processing: obtaining the control parameters and process target results of the extrusion control process, wherein the control parameters are parameters that the control center can adjust and control, and the process target results are target parameters used to evaluate the extrusion quality of process nodes; performing influence relationship analysis based on the control parameters of the extrusion control process and the process target results to obtain influence relationship coefficients; obtaining the support based on the influence relationship coefficients, setting screening requirements, and using the control parameters whose support meets the screening requirements as the core control parameters of the process.

[0010] In a possible implementation, the decomposition parameter calculation module further performs the following processing: extracting a historical case dataset based on the control parameters of the extrusion control process and the target result of the process; setting a search accuracy constraint value, searching from the historical case dataset to determine the target case dataset; performing hierarchical clustering based on the target case dataset as the cluster center to obtain multi-level clusters, and fitting the relationship parameters of each layer of clusters respectively; setting a deviation threshold, stopping clustering when the deviation value of the multi-level relationship parameters reaches the deviation threshold; configuring multi-level weights, performing an average weighted calculation of the multi-level relationship coefficients to obtain the influence relationship coefficients, wherein the relationship parameter weights of the target case dataset are the largest.

[0011] In a possible implementation, the decomposition parameter calculation module further performs the following processing: performing contour coefficient calculation on the multi-layer cluster to obtain contour coefficients for each layer; performing decentralization processing based on all contour coefficients for each layer to obtain the mean value of the coefficients; calculating the deviation value between the contour coefficients for each layer and the mean value of the coefficients to determine the adjustment coefficients; and reconstructing the multi-layer weights using the adjustment coefficients.

[0012] In a possible implementation, the decomposition parameter calculation module further performs the following processing: calculating the deviation value using the contour coefficients of each layer and the mean value of the coefficients, and determining the adjustment coefficient, including, according to the formula: ,in, The adjustment coefficient for the i-th layer, Let k be the contour coefficient of the i-th layer, k be the mean coefficient, and i be the number of clustering layers.

[0013] This application proposes a performance-constrained engineering material extrusion control system that connects to a performance analysis platform to acquire performance analysis data of the engineering materials. Based on this data, a data stability probability analysis is performed, and constraint performance is determined based on the data trend stability probability. The extrusion control process is then decomposed into parameters, and the support relationship of the decomposed parameters is calculated using the process target results to obtain the core control parameters. A mapping relationship between the constraint performance and the core control parameters is established, and process optimization variables are configured. Based on these optimization variables, the control parameters are optimized to maximize the control target, resulting in extrusion control information, which is then sent to the control center for extrusion operation process control. This solution addresses the technical problem in existing engineering material extrusion control systems where it is difficult to monitor and accurately control key parameters in the extrusion process in real time, leading to unstable product quality and low production efficiency. It achieves automatic adjustment of extrusion parameters, thereby improving product quality stability and production efficiency. Attached Figure Description

[0014] 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.

[0015] Figure 1 A schematic diagram of a performance-constrained engineering material extrusion control system provided in an embodiment of this application; Figure 2A schematic diagram illustrating the execution process of the performance analysis data acquisition module in a performance-constrained engineering material extrusion control system provided in this application embodiment; Figure 3 This is a schematic diagram illustrating the execution process of the decomposition parameter calculation module in a performance-constrained engineering material extrusion control system provided in an embodiment of this application.

[0016] Figure labeling: Performance analysis data acquisition module 10, constraint performance determination module 20, decomposition parameter calculation module 30, mapping relationship establishment module 40, extrusion operation process control module 50. Detailed Implementation

[0017] 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.

[0018] 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.

[0019] In the following description, references to "some embodiments" describe a subset of all possible embodiments. However, it is understood that "some embodiments" can be the same or different subsets of all possible embodiments and can 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, system, product, or server that comprises 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, 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.

[0020] This application provides an engineering material extrusion control system based on performance constraints, such as... Figure 1 As shown, the system includes: The performance analysis data acquisition module 10 is used to connect to a performance analysis platform to acquire performance analysis data of engineering materials, including material viscosity, temperature-fluidity relationship, pressure-deformation relationship, and material composition-performance relationship. By connecting to the performance analysis platform and acquiring the performance analysis data of engineering materials, the platform—a tool for analyzing and evaluating the performance of engineering materials—typically integrates multiple technologies to collect, analyze, and visualize material performance data. Specifically, after connecting to the performance analysis platform, users can obtain the aforementioned performance analysis data by inputting specific material information and test conditions. Material viscosity refers to the internal friction property of engineering materials (fluids), i.e., the magnitude of internal resistance during material flow. In engineering materials, viscosity affects the material's fluidity and processing performance. The performance analysis platform provides data support for adjusting and controlling production processes. The temperature-fluidity relationship describes the material's flow properties at different temperatures. Temperature changes directly affect the molecular motion and viscosity of the material. The performance analysis platform can monitor the impact of temperature changes on material flowability in real time, affecting its processing and molding properties, helping engineers optimize processing temperatures and improve production efficiency. The pressure-deformation relationship reflects the degree of deformation of a material under external force, which is crucial for predicting its performance in actual use. The performance analysis platform measures the deformation of engineering materials by applying different pressures, providing detailed data for material mechanical property analysis. The material composition-performance relationship refers to the influence of each component in the material on its properties. Different combinations of components lead to differences in the physical, chemical, and mechanical properties of the material. The performance analysis platform can reveal the relationships between these components by analyzing the chemical composition, microstructure, and performance data of the material, facilitating further quality control of engineering materials.

[0021] The constraint performance determination module 20 is used to perform data stability probability analysis based on the performance analysis data. Based on the data trend stability probability, it determines the constraint performance, which refers to performance parameters whose data trend stability probability exceeds a preset range. Statistical methods are used to perform data stability probability analysis on the acquired engineering material performance analysis data to assess its trend stability. This includes analyzing the distribution, trend, and fluctuation range of data points to determine the stability and reliability of the material performance analysis data. Based on the data stability probability analysis results, performance parameters whose data trend stability probability exceeds a preset range are identified. These parameters are used to determine whether the performance parameters are in an ideal stable state. For example, when the data trend stability probability of a certain performance parameter is lower than the preset minimum stability probability, it means that the data of that parameter fluctuates greatly and is unstable, which may affect the processing quality or performance of the material, and is considered a constraint performance. Similarly, if the data trend stability probability of a certain performance parameter is higher than the preset maximum stability probability, it may also mean that the data is too stable and lacks necessary flexibility or adaptability. Determining constraint performance helps identify key parameters that need special control during the material extrusion process. By optimizing and improving constraint performance, the processing quality, performance, and production stability and reliability of engineering materials can be improved.

[0022] The parameter decomposition module 30 is used to decompose the extrusion control process into parameters. It calculates the support relationships of the decomposed parameters using the process target results to obtain the core control parameters of the process. These core control parameters are process control parameters whose support meets the screening requirements. Specifically, the extrusion control process involves detailed analysis of each key step and stage, breaking down and classifying the various parameters involved, including parameters from each stage such as raw material preparation, extrusion molding, and cooling and sizing, such as temperature, pressure, flow rate, and cooling rate. The support relationships of the decomposed parameters are calculated using the process target results, i.e., these parameters are quantified and evaluated. Based on the expected extruded product quality, production efficiency, and other targets, the contribution and influence of each parameter in achieving these targets are calculated. By performing support relationship calculations on decomposed parameters, we can identify those parameters that have a significant impact on achieving process objectives, namely the core process control parameters. These core process control parameters not only meet the screening requirements in terms of support, but also have high controllability and adjustability in actual operation. By adjusting these parameters, we can effectively optimize the extrusion control process and improve product quality and production efficiency.

[0023] The mapping relationship establishment module 40 is used to establish the mapping relationship between the constraint performance and the core process control parameters, and to configure process optimization variables. It associates the determined constraint performance with the core process control parameters, clarifies their mutual influence and correspondence, and selects and sets variables for process optimization according to actual needs. These variables are typically those that have a significant impact on the constraint performance and are easy to adjust and control in actual operation; these are the process optimization variables. This allows for a better understanding and control of the entire extrusion process. Specifically, it analyzes the relationship between constraint performance and core process control parameters, representing it in the form of a mapping table or mathematical model. When a constraint performance changes, the relevant core process control parameters can be quickly identified, and corresponding adjustment strategies can be determined. Based on the mapping relationship, core process control parameters with significant potential for improving constraint performance are identified. The adjustment range and limitations of these parameters are analyzed to determine their reasonable value ranges. These parameters are set as process optimization variables, and corresponding adjustment strategies and optimization objectives are formulated. By configuring process optimization variables, the extrusion process can be improved more specifically, enhancing product quality and performance.

[0024] The extrusion operation process control module 50 is used to optimize control parameters based on the process optimization variables, aiming to maximize the control objective, obtain extrusion control information, and send it to the control center for extrusion operation process control. Utilizing the previously determined process optimization variables, and guided by maximizing the control objective (such as improving product quality, increasing production efficiency, and reducing energy consumption), the control parameters of the extrusion process are optimized to obtain extrusion control information, which is then input to the control center to achieve extrusion operation process control. The control center is the core command system of the extrusion operation process, responsible for receiving and executing this control information. Upon receiving the extrusion control information, it automatically adjusts the operating parameters of the extrusion equipment to ensure that the extrusion process proceeds according to the optimized parameters. Through this process, refined control of the extrusion operation process can be achieved, reducing production costs and energy consumption, and improving product quality and production efficiency.

[0025] The performance-constrained engineering material extrusion control system according to embodiments of the present invention addresses the technical problems of existing engineering material extrusion control systems, such as the difficulty in real-time monitoring and precise control of key parameters during the extrusion process, leading to unstable product quality and low production efficiency. The system achieves automatic adjustment of extrusion parameters, thereby improving product quality stability and production efficiency. The performance-constrained engineering material extrusion control system includes: a performance analysis data acquisition module 10, a constraint performance determination module 20, a decomposition parameter calculation module 30, a mapping relationship establishment module 40, and an extrusion operation process control module 50.

[0026] The specific configuration of the performance analysis data acquisition module 10 will be described in detail below. The performance analysis data acquisition module 10 may further include: constructing a twin simulation module inserted into the performance analysis platform; using the twin simulation module as independent variables (temperature, pressure, and material composition ratio) to perform target quantity tests on material viscosity, flowability, deformation, and material stability, and recording the simulation test data. Utilizing digital twin and simulation technology, a twin simulation module is constructed to perform a more comprehensive and accurate analysis of the performance of engineering materials. The twin simulation module can perform target quantity tests such as material viscosity, flowability, deformation, and material stability based on set independent variables (such as temperature, pressure, and material composition ratio), thereby acquiring simulation test data. Specifically, the twin simulation module will simulate the material extrusion process in a virtual environment based on input parameters such as temperature, pressure, and material composition ratio, and record and analyze the material's performance under different conditions in real time. By adjusting these independent variables, the changing trends of material performance can be observed and analyzed, thereby finding the optimal material formulation and process parameters, and recording them as simulation test data. Data fitting of independent variables and target quantities is performed separately to obtain the influence relationships. Data fitting is performed on independent variables (including temperature, pressure, material composition ratio, etc.) and target quantities (including material viscosity, flowability, deformation, material stability, etc.) to obtain the influence relationships between them. Specifically, through data fitting, the mathematical relationship between independent variables and target quantities is obtained, which helps to predict the changing trend of target quantities under different independent variable conditions. The mapping relationship between the influence relationships, independent variables, and target quantities is established to construct the performance analysis data of the engineering material. Establishing the mapping relationship between the influence relationships, independent variables, and target quantities means linking the influence relationships, independent variables, and target quantities in a clear way. Constructing the performance analysis data of the engineering material means integrating all the above information to form a comprehensive and systematic dataset, including the original experimental data, the fitted influence relationships, the mapping relationships, and the performance analysis results derived therefrom.

[0027] The specific configuration of the constraint performance determination module 20 will be described in detail below. The constraint performance determination module 20 further includes: performing stability probability analysis based on the adjustment step size and influence relationships of the independent variables to determine the stable trend of the data. The stability probability analysis based on the adjustment step size and influence relationships of the independent variables to determine the stable trend of the data, wherein the adjustment step size of the independent variables refers to the increment or decrement used when changing the independent variables (such as temperature, pressure, material composition ratio, etc.) in the experiment. The size of the adjustment step size directly affects the accuracy and resolution of the experimental data. An excessively large step size may lead to excessively drastic data changes that are difficult to analyze, while an excessively small step size may increase experimental costs and time. Specifically, using these influence relationships and the adjustment step size of the independent variables, a series of data points are obtained, and stability probability analysis is performed on them to calculate the stability probability of the data trend. The stability probability refers to the probability that a data point fluctuates within a certain range without significant change; it reflects the stability and reliability of the data trend. Trend segmentation based on the stable trend of the data includes regular trend regions and abnormal drop regions. Regular trend regions are stable development regions that match the influencing relationships, while abnormal drop regions are regions where the development trend direction changes and does not match the influencing relationships. Trend segmentation based on the stable trend of the data is an important step in data analysis, used to divide the overall trend into different regions or stages. Specifically, trend segmentation can be performed on the stable trend of the data using moving averages, filtering algorithms, or cluster analysis. Regular trend regions refer to regions that match known influencing relationships and exhibit stable development characteristics; abnormal drop regions refer to regions that do not match the influencing relationships and where the development trend direction changes significantly. The constraint performance is determined based on the segmentation nodes of the regular trend regions and abnormal drop regions. The dividing points between regular trend regions and abnormal drop regions are key points where significant changes occur in data trends. Within regular trend regions, data develops steadily according to the expected influence relationship; while abnormal drop regions indicate that the data trend has changed in ways that do not meet expectations. By analyzing the location, characteristics, and corresponding changes in independent and target variables of these dividing points, the specific parameters and conditions of constraint performance can be determined. Constraint performance usually refers to the performance limits or restrictions that engineering materials can achieve under specific conditions. For example, in material strength testing, dividing points may correspond to the points where the material begins to fracture, thus determining the maximum bearing capacity of the material.

[0028] The specific configuration of the decomposition parameter calculation module 30 will be described in detail below. The decomposition parameter calculation module 30 further includes: acquiring the control parameters and process target results of the extrusion control process. The control parameters are parameters that the control center can adjust and control, and the process target results are target parameters used to evaluate the extrusion quality of process nodes. By acquiring and controlling these key parameters, the control center can achieve precise control of the extrusion process, thereby ensuring that product quality and production efficiency reach their optimal state. Real-time monitoring and evaluation of the process target results also helps to promptly identify and solve problems, further improving the stability and reliability of the production process. Based on the control parameters of the extrusion control process and the process target results, an influence relationship analysis is performed to obtain influence relationship coefficients. The influence relationship coefficient represents the degree of influence between the control parameters and the process target results. The sign of the influence relationship coefficient tells us whether the parameter has a positive or negative impact on the result, while the magnitude of the coefficient reflects the strength of the influence. Based on the influence relationship coefficients, the support level is obtained, screening requirements are set, and control parameters whose support meets the screening requirements are taken as the core control parameters of the process. These influence coefficients are used to calculate support, which measures the importance of a control parameter in influencing the process's target outcome. Specifically, support can be calculated based on the absolute or relative value of the influence coefficient to reflect the overall degree of influence of the parameter on the target outcome. After obtaining the support, we need to set screening criteria, which should consider multiple factors, including the parameter's adjustability, the degree of influence on the target outcome, and the cost required to implement control. For example, a support threshold can be set, and only control parameters that exceed this threshold are considered to have sufficient support. Control parameters that meet the support screening criteria are then used as core control parameters of the process.

[0029] The specific configuration of the decomposition parameter calculation module 30 will be described in detail below. The decomposition parameter calculation module 30 further includes: extracting a historical case dataset based on the control parameters of the extrusion control process and the process target result. According to the control parameters and process target result of the extrusion control process, relevant data records are collected and organized from past extrusion production processes. These data record the process target results obtained under different control parameter settings. This historical data is used to analyze and understand the relationship between control parameters and process target results, providing data support for optimizing the extrusion control process. A search precision constraint value is set, and a search is performed from the historical case dataset to determine the target case dataset. The search constraint value can be a specific numerical value or a specific condition, reflecting our requirements for the accuracy of the target cases. Based on the set search precision constraint value, a search is performed in the historical case dataset, and multiple historical cases that meet the search precision constraint value constitute the target case dataset. Based on the target case dataset as cluster centers, hierarchical clustering is performed to obtain multi-level clusters, and the relationship parameters of each level of clusters are fitted. Using the target case dataset as the cluster center, hierarchical clustering is performed. The similarity or distance between cases is calculated, and cases are progressively merged or split into different clusters based on these similarities or distances. As clustering progresses, multi-layered clusters are formed, each representing a different level of clustering results. The data within each layer of clusters is analyzed to discover relationships or patterns. By fitting these relationship parameters, we can better understand the intrinsic structure and characteristics of the data. A deviation threshold is set; clustering stops when the deviation value of the multi-layered relationship parameters reaches the threshold. A deviation threshold is set. Clustering stops when the deviation value of the multi-level relationship parameters reaches this threshold. This is used to evaluate the stability of the clustering results and control the clustering accuracy. The deviation threshold is a preset value used to quantify the degree of change or difference in the multi-level relationship parameters. By comparing the differences and rates of change of relationship parameters at different levels, the deviation value of the relationship parameters between adjacent levels is calculated. When this deviation value reaches or exceeds the set deviation threshold, it is considered that the clustering results have shown significant instability or change. Continuing clustering may lead to problems such as overfitting, so clustering is stopped to ensure the stability and consistency of the clustering results and avoid overly complex clustering structures. Multi-level weights are configured, and the multi-level relationship coefficients are averaged and weighted to obtain the influence relationship coefficients. The relationship parameters of the target case dataset have the largest weights. Different weights are assigned to clusters at different levels and their relationship parameters. The multi-level relationship coefficients are calculated by weighted averaging to obtain the influence relationship coefficients. The relationship parameters of the target case dataset are assigned the largest weights to emphasize their importance in the calculation.

[0030] The specific configuration of the decomposition parameter calculation module 30 will be described in detail below. The decomposition parameter calculation module 30 further includes: performing silhouette coefficient calculation on multi-layer clusters to obtain the silhouette coefficients for each layer. During hierarchical clustering, the silhouette coefficient evaluation method is applied to the clustering results of each layer to obtain the silhouette coefficient values ​​for each layer. The silhouette coefficient is an indicator for measuring clustering effectiveness; it comprehensively considers the cluster's compactness and separation. For each sample point, the silhouette coefficient (… The result can be calculated using the following formula: ; in, It is the average distance between a sample point and other points within the same cluster. This is the minimum average distance between a sample point and all points within other clusters. Decentralization is performed based on the contour coefficients of all layers to obtain the mean coefficient. The deviation between the contour coefficients of each layer and the mean coefficient is calculated to determine an adjustment coefficient. This adjustment coefficient is then used to reconstruct the multi-layer weights. The deviation between the contour coefficients of each layer and the mean coefficient is calculated. Based on the calculated deviation, an adjustment coefficient can be determined; for example, layers with larger deviations may be assigned larger adjustment coefficients. Using the determined adjustment coefficient, the original multi-layer weights are reconstructed, i.e., by multiplying the weight of each layer by the corresponding adjustment coefficient. By reconstructing the weights, layers with better clustering results can receive greater weight in subsequent weighted calculations, thereby improving the accuracy and reliability of the overall clustering results.

[0031] The specific configuration of the decomposition parameter calculation module 30 will be described in detail below. The decomposition parameter calculation module 30 may further include: calculating the deviation value using the contour coefficients of each layer and the mean value of the coefficients to determine the adjustment coefficient, including: according to the formula: ,in, The adjustment coefficient for the i-th layer, Let k be the contour coefficient of the i-th layer, k be the mean coefficient, and i be the number of clustering layers.

[0032] The specific configuration of the extrusion operation process control module 50 will be described in detail below. The extrusion operation process control module 50 further includes: based on the process optimization variables, setting search constraints to search the control parameter sample set, and randomly generating a first population and a second population; determining an update search center and an update search direction based on the first population and the second population, wherein the update search center is determined by the magnitude of a random number; using the update search center and update search direction, performing process variable control scheme mutation according to a set step size to obtain a mutated population; exchanging individual elements in the second population with elements at the same position in the mutated population to generate new samples; when the evaluation value of the new sample exceeds the evaluation value of individual elements in the second population, performing population update; when the evaluation value of the new sample is lower than the evaluation value of individual elements in the second population, eliminating the new sample and marking the corresponding individual sample as a termination marker to indicate that update search is prohibited; repeatedly iterating the population update until the optimization stopping target is reached, obtaining the process variable control scheme with the optimal evaluation value as the extrusion control information. Based on the process optimization variables, a process of setting search constraints to search the control parameter sample set, followed by a series of optimization operations, mainly utilizes a backtracking search optimization algorithm to find the optimal process variable control scheme. Specifically, after setting the search constraints, a first and second group are randomly generated. Based on the characteristics of the first and second groups, the search center point and direction are determined by random numbers, increasing the randomness and globality of the search. The search direction determines which direction to search in the search space, thus updating the search center and search direction in a definite manner. The process variable control scheme is mutated according to a set step size, and the process variable control scheme is mutated in the search space according to the set step size. New solutions, or new process variable control schemes, are generated according to certain rules. This involves adjusting parameters to generate new schemes, followed by crossover and mutation operations. Individual elements from the second population are exchanged with elements at the same position in the mutated population to generate new samples. These new samples are evaluated, and their evaluation values ​​are calculated. If the evaluation value of a new sample exceeds that of an individual element in the second population, the population is updated using the best solutions from both the second and mutated populations. If the evaluation value of a new sample is lower than that of an individual element in the second population, the new sample is eliminated, and a termination marker is added, indicating that this search direction will not be considered in subsequent iterations. This iterative process of population updating continues until an optimization stopping point is reached. That is, iteration stops when a certain stopping condition is met (e.g., reaching a preset number of iterations, or the evaluation value of the best individual in the population stabilizing and no longer changing). The individual with the best evaluation value in the population is the desired process variable control scheme, serving as the final exodus control information.

[0033] 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.

[0034] 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 performance-constrained engineering material extrusion control system, characterized in that, The system includes: The performance analysis data acquisition module is used to connect to the performance analysis platform and acquire the performance analysis data of the engineering materials, including material viscosity, temperature-flowability, pressure-deformation relationship, and material composition-performance relationship. The constraint performance determination module is used to perform data stability probability analysis based on the performance analysis data, and determine the constraint performance based on the data trend stability probability. The constraint performance is a performance parameter in which the data trend stability probability exceeds a preset range. The decomposition parameter calculation module is used to decompose the extrusion control process into parameters, and to calculate the support relationship of the decomposed parameters using the process target results to obtain the core control parameters of the process. The core control parameters of the process are process control parameters whose support meets the screening requirements. A mapping relationship establishment module is used to establish the mapping relationship between the constraint performance and the core control parameters of the process, and to configure process optimization variables; An extrusion operation process control module is used to optimize control parameters based on the process optimization variables to maximize the control target, obtain extrusion control information, and send it to the control center for extrusion operation process control. The steps performed by the decomposition parameter calculation module include: The control parameters and target results of the extrusion control process are obtained. The control parameters are parameters that the control center can adjust and control, and the target results are target parameters used to evaluate the extrusion quality of process nodes. Based on the control parameters of the extrusion control process and the target results of the process, an influence relationship analysis is performed to obtain the influence relationship coefficients; Based on the influence relationship coefficient, the support degree is obtained, the screening requirements are set, and the control parameters whose support degree meets the screening requirements are used as the core control parameters of the process. The steps performed by the decomposition parameter calculation module include: Based on the control parameters of the extrusion control process and the target results of the process, historical case datasets are extracted. Set a search precision constraint value, search from the historical case dataset, and determine the target case dataset; Based on the target case dataset as the cluster center, hierarchical clustering is performed to obtain multi-level clusters, and the relationship parameters of each level cluster are fitted respectively. Set a deviation threshold; when the deviation value of the multi-level relationship parameters reaches the deviation threshold, clustering is stopped. Configure multi-level weights and perform multi-level relation coefficient average weighting calculation to obtain the influence relation coefficients, wherein the relation parameter weights of the target case dataset are the largest.

2. The performance-constrained engineering material extrusion control system as described in claim 1, characterized in that, The extrusion operation process control module performs the following steps: Based on the process optimization variables, search constraints are set to search the control parameter sample set, and the first group and the second group are randomly generated. Based on the first group and the second group, the search center and the search direction are updated, wherein the search center is determined by the magnitude of a random number. The search center and search direction are updated, and the process variable control scheme is mutated according to the set step size to obtain a mutated population. Individual elements in the second population are exchanged with elements in the same position in the mutated population to generate new samples. When the evaluation value of the new sample exceeds the evaluation value of the individual elements in the second population, the population is updated. When the evaluation value of a new sample is lower than the evaluation value of an individual element in the second population, the new sample is eliminated and the corresponding individual sample is marked as terminated to indicate that the search is prohibited from being updated. The population is updated iteratively until the optimization stopping target is reached, and the process variable control scheme with the best evaluation value is obtained as the extrusion control information.

3. The performance-constrained engineering material extrusion control system as described in claim 1, characterized in that, The performance analysis data acquisition module performs the following steps: A twin simulation module is constructed and inserted into the performance analysis platform. The twin simulation module is used to test the target quantities of material viscosity, flowability, deformation and material stability based on temperature, pressure and material composition ratio as independent variables, and the simulation test data is recorded. Data fitting was performed separately for the independent variables and the target quantity to obtain the influence relationship; Establish the mapping relationship between the influencing factors, independent variables, and target quantities, and construct the performance analysis data of the engineering materials.

4. The performance-constrained engineering material extrusion control system as described in claim 3, characterized in that, The constraint performance determination module performs the following steps: Based on the adjustment step size and influence relationship of the independent variables, a stability probability analysis is performed to determine the stable trend of the data. Based on the stable trend of the data, trend segmentation is performed, including regular trend areas and abnormal drop areas. The regular trend areas are stable development areas that match the influence relationship, and the abnormal drop areas are areas where the development trend direction changes and does not match the influence relationship. The constraint performance is determined based on the segmentation nodes of the regular trend area and the abnormal drop area.

5. The performance-constrained engineering material extrusion control system as described in claim 1, characterized in that, The system also includes: The silhouette coefficients of each layer are calculated by performing silhouette coefficient calculations on multi-layer clusters. The mean value of the coefficients is obtained by decentralizing all the contour coefficients of each layer. The deviation value is calculated by using the contour coefficient of each layer and the mean value of the coefficient to determine the adjustment coefficient, and the multi-layer weights are reconstructed using the adjustment coefficient.

6. The performance-constrained engineering material extrusion control system as described in claim 5, characterized in that, The adjustment coefficient is determined by calculating the deviation value between the contour coefficient of each layer and the mean value of the coefficients, including: According to the formula: , ,in, The adjustment coefficient for the i-th layer, Let k be the contour coefficient of the i-th layer, k be the mean coefficient, and i be the number of clustering layers.

Images