Process parameter data and method for cooperatively regulating and controlling comprehensive performance of heterogeneous layered composite material

Through artificial neural network models and genetic algorithms and other technologies, the process parameters of heterogeneous layered composite materials are optimized, and the problem of comprehensive performance regulation of heterogeneous layered composite materials is solved, achieving optimal performance matching and efficiency improvement.

CN118886313APending Publication Date: 2024-11-01UNIV OF SCI & TECH BEIJING
View PDF 0 Cites 3 Cited by

Patent Information

Application Number
CN202410921548.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-10
Publication Date
2024-11-01

AI Technical Summary

Technical Problem

In the preparation process of heterogeneous layered composite materials, it is difficult to take into account the coordinated control of the properties of each heterogeneous component material, the composite interface performance and the integrated composite performance, resulting in the difficulty of optimal matching of the comprehensive performance.

Method used

Using artificial neural network models and genetic algorithms, we use technologies such as collecting and normalizing process parameters and performance data, establishing and optimizing process parameter models to achieve coordinated control of the performance of various parts of heterogeneous layered composite materials.

Benefits of technology

The optimal matching of the performance of each part of the heterogeneous layered composite material is achieved, the comprehensive performance is improved, the cost and time is reduced, the efficiency is improved, and the advantages of energy saving and environmental protection are provided.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118886313A_ABST
    Figure CN118886313A_ABST
Patent Text Reader

Abstract

The invention provides heterogeneous layered composite material comprehensive performance cooperative regulation and control technological parameter data and a method, and belongs to the technical field of heterogeneous layered composite material preparation. Comprising the following steps: collecting process parameter data and performance data of the heterogeneous layered composite material and each component material, processing the data as an input value or an output value, and establishing and training an artificial neural network model; providing design performance data, processing the design performance data, and inputting the processed design performance data into the trained model as an input value; and through comparison and confirmation of model output values, completion of collaborative regulation and control process parameter data optimization is confirmed, and process parameter data of heterogeneous layered composite material comprehensive performance collaborative regulation and control are obtained. On the basis of respective design performance, existing performance and process parameter data of the component material and the heterogeneous layered composite material, intelligent optimization of preparation process parameter data of comprehensive performance coordinated regulation and control of the heterogeneous layered composite material is completed, and the comprehensive performance of the composite material is remarkably improved; cost is reduced, time is saved, efficiency is improved, energy is saved, consumption is reduced, and low-carbon environmental protection is achieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of heterogeneous layered composite material preparation, and specifically relates to a process parameter data and method for coordinated control of the comprehensive performance of heterogeneous layered composite materials, and is particularly suitable for optimizing the process parameter data for preparing heterogeneous layered composite materials for differential temperature composite forming between heterogeneous component materials. Background Art

[0002] Heterogeneous layered composite materials are composed of two or more heterogeneous component materials in a layered manner. They have the advantages of each heterogeneous component material and overcome the shortcomings of a single component material. They are widely used. Compared with a single material, practical applications have higher and more comprehensive performance requirements for heterogeneous layered composite materials, involving the composite interface performance between each heterogeneous component material, the performance of each heterogeneous component material itself, and the integrated composite performance produced by the synergy of multiple heterogeneous component materials. They are a typical type of multi-objective performance composite material. Therefore, in the preparation process of heterogeneous layered composite materials, it is necessary to coordinate and regulate the organizational structure of each of the various heterogeneous component materials and the composite interface between the various heterogeneous component materials. The matching of its preparation process parameters is complex, with many influencing factors, and the final comprehensive performance is difficult to regulate. The optimization of the preparation process parameters of each process or the whole process is prominent. Because of this, in the current preparation process of heterogeneous layered composite materials, the preparation process parameters are usually optimized only with the goal of obtaining high composite interface performance, and it is impossible to take into account the comprehensive performance of the heterogeneous layered composite materials, the performance of each heterogeneous component layer itself, and the integrated composite performance produced by the synergy of multiple heterogeneous component materials.

[0003] Therefore, it is of great significance to develop a new method for synergistic regulation of the comprehensive properties of heterogeneous layered composites to solve the problem of synergistic regulation of the properties of each heterogeneous component material, the composite interface performance and the integrated composite performance of the heterogeneous layered composites to achieve optimal matching of the performance of each part and obtain high-performance heterogeneous layered composites with excellent comprehensive performance. Summary of the invention

[0004] In view of the above problems, the purpose of the present invention is to provide a process parameter data and method for coordinated regulation of the comprehensive performance of a heterogeneous layered composite material, so as to achieve coordinated regulation of the properties of each heterogeneous component material itself, the composite interface properties and the integrated composite performance of the heterogeneous layered composite material, so as to achieve optimal matching of the performance of each part of the heterogeneous layered composite material and obtain a high-performance heterogeneous layered composite material with excellent comprehensive performance.

[0005] According to a first aspect of the technical solution of the present invention, a method for coordinated regulation of comprehensive properties of heterogeneous layered composite materials is provided, characterized in that it comprises the following steps:

[0006] Step 1: collect the first preparation process parameter data of the heterogeneous layered composite material and the first forming process parameter data when each heterogeneous component material is formed independently, as well as the first composite interface performance data of the heterogeneous layered composite material and the first self performance data of each component material corresponding to each other, and perform normalization processing to obtain the first preparation process parameter value, the first forming process parameter value, the first composite interface performance value and the first self performance value respectively;

[0007] Step 2: respectively using the first preparation process parameter value and the first forming process parameter value as input value / output value, and using the first composite interface performance value and the first self performance value as output value / input value, establishing respective first artificial neural network models and second artificial neural network models and training them, so that their accuracies reach or exceed preset accuracies respectively;

[0008] Step 3: The designed composite interface performance data of the heterogeneous layered composite material and the designed self performance data of each of the component materials are given, and after normalization, they are input into the trained respective second artificial neural network models as input values ​​to obtain the respective initially optimized second preparation process parameter values ​​and second forming process parameter values;

[0009] Step 4: inputting the second preparation process parameter value and the second forming process parameter value respectively initially optimized into the first artificial neural network model respectively trained, and obtaining the second composite interface performance value of the heterogeneous layered composite material and the second self performance value of each of the component materials respectively;

[0010] Step 5: Denormalize the second preparation process parameter values ​​and the second forming process parameter values, the second composite interface performance values, and the second self performance values ​​that are initially optimized, to obtain the second preparation process parameter data and the second forming process parameter data that are initially optimized, the predicted composite interface performance data of the heterogeneous layered composite material, and the predicted self performance data of each of the component materials;

[0011] Step 6: Determine whether the respective predicted composite interface performance data and the predicted self performance data reach or exceed the respective corresponding designed composite interface performance data and the designed self performance data; if not, repeat steps 2-5; if yes, proceed to step 7;

[0012] Step 7: Determine whether the mutual matching accuracy of the second preparation process parameter data initially optimized and the same type of process parameter data in the second forming process parameter data reaches or exceeds the set accuracy; if not, repeat steps 2-5; if so, the coordinated control process parameter data optimization is completed, and the process parameter data for coordinated control of the comprehensive performance of the heterogeneous layered composite material is obtained.

[0013] Furthermore, the type of the heterogeneous layered composite material is at least one of a laminated composite structure type, a side composite structure type, a coated composite structure type or an inlaid composite structure type.

[0014] Furthermore, the component material is at least one of a metal material, an inorganic non-metal material, a polymer material or a composite material; the composite interface performance and the self performance are at least one of a mechanical property, a physical property or a chemical property.

[0015] Furthermore, the preparation process is at least one of solid-solid composite, liquid-solid composite, gas-solid composite, liquid-liquid composite or chemical composite, and the forming process is at least one of solid forming, liquid forming, gas forming or chemical forming.

[0016] Furthermore, the first preparation process parameter and the second preparation process parameter are full-process preparation process parameters or process preparation process parameters of the heterogeneous layered composite material, and the first forming process parameter and the second forming process parameter are full-process forming process parameters or process forming process parameters of the component material; wherein the full process includes multiple processes.

[0017] Furthermore, when the heterogeneous layered composite material contains multiple composite interfaces, if it is composited as a whole at one time, the first preparation process parameter data and the second preparation process parameter data refer to process parameter data for avoiding the generation of intermetallic compounds at the composite interface where intermetallic compounds are most likely to be generated when preparing the heterogeneous layered composite material; if it is composited separately for multiple times, the first preparation process parameter data and the second preparation process parameter data refer to process parameter data for each composite forming of the component materials during the preparation of the heterogeneous layered composite material.

[0018] Furthermore, the preset accuracy of the first artificial neural network model and the second artificial neural network model is not less than 0.85, and the setting accuracy of the same type of process parameter data is not less than 0.9 or satisfies the differential temperature composite forming between the component materials.

[0019] Furthermore, the same type of process parameters are at least one of the temperature, speed, time, cooling capacity, degree of deformation, forming force, friction coefficient, layer thickness ratio, surface quality or material state under the same preparation process or the same forming process.

[0020] Furthermore, at least one of a genetic algorithm, a simulated annealing algorithm, a taboo search algorithm, a particle swarm algorithm or an ant colony algorithm is used to optimize the weights or thresholds of the first artificial neural network model or the second artificial neural network model.

[0021] According to a second aspect of the technical solution of the present invention, there is provided process parameter data for synergistically regulating the comprehensive performance of a heterogeneous layered composite material, which is obtained by optimizing according to any of the above synergistic regulation methods.

[0022] Beneficial effects of the present invention:

[0023] The method of the present invention can be used to mine a large amount of existing data on the preparation process parameters and composite interface performance of heterogeneous layered composite materials, as well as a large amount of existing data on the forming process parameters and self-performance of each heterogeneous component material, and use artificial intelligence technology to realize the association of two or more independent process parameters and related independent performances, and obtain unified optimization and coordinated control process parameter data with high matching accuracy based on design performance, and on this basis, realize the coordinated control of the self performance, composite interface performance and integrated composite performance of each heterogeneous component material of the heterogeneous layered composite material, so as to achieve the purpose of optimal matching of the performance of each part, which is helpful to prepare a heterogeneous layered composite material with excellent overall comprehensive performance, and also has the advantages of reducing costs, saving time, improving efficiency, energy saving and consumption reduction, and low-carbon environmental protection. It is particularly suitable for optimizing the preparation process parameter data of heterogeneous layered composite materials for differential temperature composite forming between each heterogeneous component material. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments 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 described below are only some embodiments of the application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0025] Figure 1 The present invention is a flow chart of the method for coordinated regulation of comprehensive properties of heterogeneous layered composite materials. DETAILED DESCRIPTION

[0026] The present invention is described in detail below in conjunction with embodiments. It should be noted that the following embodiments are only used to further illustrate the present invention and cannot be understood as limiting the scope of protection of the present invention. Those skilled in the art may make non-essential improvements and adjustments based on the contents of the present invention.

[0027] The technical solution of the present invention provides a method for synergistically regulating the comprehensive properties of heterogeneous layered composite materials, such as Figure 1 As shown, the following steps are included:

[0028] S101: Collect the first preparation process parameter data of the heterogeneous layered composite material and the first forming process parameter data when each heterogeneous component material is formed independently, as well as the first composite interface performance data of the heterogeneous layered composite material and the first self performance data of each component material corresponding to each other, and normalize them to obtain the first preparation process parameter value, the first forming process parameter value, the first composite interface performance value and the first self performance value.

[0029] In a preferred embodiment, S101 specifically includes: collecting preparation process parameter data of heterogeneous layered composite materials and forming process parameter data when each heterogeneous component material constituting the heterogeneous layered composite material is formed independently, as well as composite interface performance data of the heterogeneous layered composite material and the inherent performance data of the component material corresponding to each other, and establishing a database; normalizing the preparation process parameter data, the forming process parameter data, the composite interface performance data and the inherent performance data respectively to obtain the preparation process parameter value, the forming process parameter value, the composite interface performance value and the inherent performance value.

[0030] In a preferred embodiment, the type of the heterogeneous layered composite material is at least one of a laminated composite structure type, a side composite structure type, a coated composite structure type or an inlaid composite structure type.

[0031] In a preferred embodiment, the component material is at least one of a metal material, an inorganic non-metal material, a polymer material or a composite material.

[0032] In a preferred embodiment, the preparation process is at least one of solid-solid composite, liquid-solid composite, gas-solid composite, liquid-liquid composite or chemical composite, and the forming process is at least one of solid forming, liquid forming, gas forming or chemical forming.

[0033] In a preferred embodiment, the composite interface property and the self property are at least one of mechanical property, physical property or chemical property.

[0034] In a preferred embodiment, the preparation process parameters are the full-process preparation process parameters or process preparation process parameters of the heterogeneous layered composite material, and the forming process parameters are the full-process forming process parameters or process forming process parameters of the component materials; wherein the full process includes multiple processes.

[0035] In a preferred embodiment, when the heterogeneous layered composite material contains multiple composite interfaces, if it is formed as a whole at one time, then the preparation process parameter data refers to the process parameter data for avoiding the generation of intermetallic compounds at the composite interface that is most likely to generate intermetallic compounds when preparing the heterogeneous layered composite material; if it is formed separately at multiple times, then the preparation process parameter data refers to the process parameter data for each composite forming of the component materials during the preparation of the heterogeneous layered composite material.

[0036] S102: respectively use the first preparation process parameter value and the first forming process parameter value as input value / output value, and use the first composite interface performance value and the first self performance value as output value / input value, establish respective first artificial neural network models and second artificial neural network models and train them so that their accuracies reach or exceed preset accuracies, respectively.

[0037] In a preferred embodiment, S102 specifically includes: taking the preparation process parameter values ​​and the forming process parameter values ​​as input values / output values, taking the composite interface performance values ​​and the self-performance values ​​as output values / input values, and establishing respective forward artificial neural network models and reverse artificial neural network models of the relationship between the preparation process parameters and the forming process parameters and the composite interface performance and the self-performance; and training the respective forward artificial neural network models and the reverse artificial neural network models so that their accuracies reach or exceed the preset accuracies.

[0038] In a preferred embodiment, the preset accuracy of the forward artificial neural network model and the reverse artificial neural network model is not less than 0.85, and the setting accuracy of the same type of process parameter data is not less than 0.9 or satisfies the differential temperature composite forming between the component materials.

[0039] In a preferred embodiment, at least one of a genetic algorithm, a simulated annealing algorithm, a taboo search algorithm, a particle swarm algorithm or an ant colony algorithm is used to optimize the weights or thresholds of the forward artificial neural network model or the reverse artificial neural network model.

[0040] S103: The designed composite interface performance data of the heterogeneous layered composite material and the designed own performance data of each of the component materials are given, and after normalization, they are input into the trained respective second artificial neural network models as input values ​​to obtain the respective initially optimized second preparation process parameter values ​​and second forming process parameter values.

[0041] In a preferred embodiment, S103 specifically includes: providing the designed composite interface performance data of the heterogeneous layered composite material and the designed own performance data of the component materials, and normalizing them respectively, and then inputting them as input values ​​into the trained respective inverse artificial neural network models to obtain their respective initial optimized preparation process parameter values ​​and initial optimized forming process parameter values.

[0042] S104: Inputting the second preparation process parameter values ​​and the second forming process parameter values ​​that are initially optimized into the first artificial neural network models that have been trained, respectively, to obtain the second composite interface performance values ​​of the heterogeneous layered composite material and the second self performance values ​​of the component materials.

[0043] In a preferred embodiment, S104 specifically includes: inputting the respective initial optimized preparation process parameter values ​​and the initial optimized forming process parameter values ​​as input values ​​into the respective trained forward artificial neural network models, and respectively obtaining the predicted composite interface performance values ​​of the heterogeneous layered composite material and the predicted self-performance values ​​of the component materials.

[0044] S105: Denormalize the second preparation process parameter values ​​and the second forming process parameter values, the second composite interface performance values, and the second self-performance values ​​that are initially optimized, to obtain the second preparation process parameter data and the second forming process parameter data that are initially optimized, as well as the predicted composite interface performance data of the heterogeneous layered composite material and the predicted self-performance data of each of the component materials.

[0045] In a preferred embodiment, S105 specifically includes: performing denormalization processing on the respective initial optimized preparation process parameter values, the initial optimized forming process parameter values, the predicted composite interface performance values ​​and the predicted own performance values ​​to obtain the respective initial optimized preparation process parameter data, the initial optimized forming process parameter data, the predicted composite interface performance data of the heterogeneous layered composite material and the predicted own performance data of the component material.

[0046] S106: Determine whether the respective predicted composite interface performance data and the predicted own performance data reach or exceed the respective corresponding designed composite interface performance data and the designed own performance data; if not, repeat S102-105; if so, proceed to S107.

[0047] In a preferred embodiment, S106 specifically includes: determining whether the respective predicted composite interface performance data and the predicted own performance data reach or exceed the respective corresponding designed composite interface performance data and the designed own performance data; if not, re-establishing and re-training the respective forward artificial neural network model or the reverse artificial neural network model, and repeating S103-105; if so, proceeding to S107.

[0048] S107: Determine whether the mutual matching accuracy of the second preparation process parameter data initially optimized and the same type of process parameter data in the second forming process parameter data reaches or exceeds the set accuracy; if not, repeat S102-105; if so, the coordinated control process parameter data optimization is completed, and the process parameter data for coordinated control of the comprehensive performance of the heterogeneous layered composite material is obtained.

[0049] In a preferred embodiment, S107 specifically includes: determining whether the mutual matching accuracy of the respective initial optimized preparation process parameter data and the same type of process parameter data in the initial optimized forming process parameter data reaches or exceeds the set accuracy; if not, re-establishing and re-training the respective forward artificial neural network model or the reverse artificial neural network model, and repeating steps 103-105; if so, the optimization of the collaborative control process parameter data is completed, and the optimized collaborative control process parameter data of the heterogeneous layered composite material is obtained.

[0050] In a preferred embodiment, the same type of process parameters are at least one of the temperature, speed, time, cooling capacity, degree of deformation, forming force, friction coefficient, layer thickness ratio, surface quality or material state under the same preparation process or the same forming process.

[0051] According to the technical solution of the present invention, there is also provided process parameter data for coordinated regulation of the comprehensive performance of a heterogeneous layered composite material, which is obtained by optimization according to any of the above coordinated regulation methods.

[0052] Embodiment 1:

[0053] The comprehensive performance of rolled copper / aluminum laminated composite materials is coordinated and controlled by process parameter data optimization. The specific steps are as follows:

[0054] Step 1: Collect the process parameter data such as rolling temperature, rolling speed and reduction amount when the copper / aluminum layered composite material is rolled and bonded, and the forming process parameter data such as rolling temperature, rolling speed and reduction amount when the copper material and aluminum material constituting the copper / aluminum layered composite material are individually rolled and formed, as well as the composite interface bonding strength data of the copper / aluminum layered composite material corresponding to each other, and the tensile strength, yield strength and conductivity data of the copper material and the aluminum material, and establish a database;

[0055] Step 2: Normalizing the rolling composite process parameter data of the copper / aluminum layered composite material, the rolling forming process parameter data of the copper material and the aluminum material, the composite interface bonding strength data, and the tensile strength, yield strength and electrical conductivity of the copper material and the aluminum material, respectively, to obtain the corresponding rolling composite process parameter values, rolling forming process parameter values, and composite interface bonding strength, tensile strength, yield strength and electrical conductivity values;

[0056] Step 3: respectively taking the rolling composite process parameter values ​​and the rolling forming process parameter values ​​as input values / output values, and taking the composite interface bonding strength, tensile strength, yield strength and electrical conductivity as output values / input values, and establishing respective forward artificial neural network models and reverse artificial neural network models of the relationship between the rolling composite process parameters and the rolling forming process parameters and the composite interface bonding strength, tensile strength, yield strength and electrical conductivity;

[0057] Step 4: Train the forward artificial neural network model and the reverse artificial neural network model respectively, so that their accuracy is not less than a preset accuracy of 0.85;

[0058] Step 5: The designed composite interface bonding strength data of the copper / aluminum layered composite material and the designed tensile strength, designed yield strength and designed conductivity of the copper and aluminum materials are given, and are normalized respectively, and then input as input values ​​into the trained respective reverse artificial neural network models to obtain the respective initial optimized rolling composite process parameter values ​​and initial optimized rolling forming process parameter values;

[0059] Step 6: Input the respective initial optimized rolling composite process parameter values ​​and the initial optimized rolling forming process parameter values ​​as input values ​​into the trained respective forward artificial neural network models, and obtain the predicted composite interface bonding strength value of the copper / aluminum layered composite material and the predicted tensile strength, predicted yield strength and predicted conductivity of the copper and aluminum materials respectively;

[0060] Step 7: Denormalize the respective initial optimized rolling composite process parameter values, initial optimized rolling forming process parameter values, predicted composite interface bonding strength values, and predicted tensile strength, predicted yield strength, and predicted conductivity values ​​to obtain respective initial optimized rolling composite process parameter data, initial optimized rolling forming process parameter data, predicted composite interface bonding strength data of copper / aluminum layered composite materials, and predicted tensile strength, predicted yield strength, and predicted conductivity data of copper and aluminum materials;

[0061] Step 8: Determine whether the respective predicted composite interface bonding strength, predicted tensile strength, predicted yield strength and predicted conductivity data reach or exceed the respective corresponding designed composite interface bonding strength, designed tensile strength, designed yield strength and designed conductivity data; if not, re-establish and re-train the respective forward artificial neural network model or reverse artificial neural network model, and repeat steps 5 to 7; if yes, proceed to step 9;

[0062] Step 9: Determine whether the mutual matching accuracy of the respective initial optimized rolling composite process parameter data and the same type of process parameter data in the initial optimized rolling forming process parameter data is not less than the set accuracy of 0.9; if not, re-establish and re-train the respective forward artificial neural network model or reverse artificial neural network model, and repeat steps 5-7; if so, the coordinated control process parameter data optimization is completed, and the optimized coordinated control rolling temperature, rolling speed and reduction amount and other process parameter data of the copper / aluminum layered composite material are obtained.

[0063] Embodiment 2:

[0064] The comprehensive performance of the drawn composite copper-clad carbon steel layered composite material is coordinated and controlled by process parameter data optimization. The specific steps are as follows:

[0065] Step 1: collecting the process parameter data such as drawing temperature, drawing speed, drawing force and pass reduction rate when drawing and compounding the copper-clad carbon steel layered composite material, and the forming process parameter data such as drawing temperature, drawing speed, drawing force and pass reduction rate when the copper material and carbon steel material constituting the copper-clad carbon steel layered composite material are independently drawn and formed, as well as the composite interface bonding strength data of the copper-clad carbon steel layered composite material corresponding to them, the electrical conductivity data of the copper material, and the tensile strength data and yield strength data of the carbon steel material, and establishing a database;

[0066] Step 2: Normalize the drawing composite process parameter data of the copper-clad carbon steel layered composite material, the drawing forming process parameter data of the copper material and the carbon steel material, the composite interface bonding strength data, the electrical conductivity data, the tensile strength data and the yield strength data, respectively, to obtain the corresponding drawing composite process parameter values, the drawing forming process parameter values, and the composite interface bonding strength values, the electrical conductivity values, the tensile strength values ​​and the yield strength values;

[0067] Step 3: respectively taking the drawing composite process parameter values ​​and the drawing forming process parameter values ​​as input values / output values, and taking the composite interface bonding strength values, electrical conductivity values, tensile strength values ​​and yield strength values ​​as output values / input values, and establishing respective forward artificial neural network models and reverse artificial neural network models of the relationships between the drawing composite process parameters and the drawing forming process parameters and the composite interface bonding strength, electrical conductivity, tensile strength and yield strength;

[0068] Step 4: Train the forward artificial neural network model and the reverse artificial neural network model respectively, so that their accuracy is not less than a preset accuracy of 0.85;

[0069] Step 5: The designed composite interface bonding strength data of the copper-clad carbon steel layered composite material, the designed electrical conductivity data of the copper material, and the designed tensile strength data and the designed yield strength data of the carbon steel material are given, and normalized respectively, and then input as input values ​​into the trained respective reverse artificial neural network models to obtain the respective initial optimized drawing composite process parameter values ​​and the initial optimized drawing forming process parameter values;

[0070] Step 6: Inputting the respective initial optimized drawing composite process parameter values ​​and the initial optimized drawing forming process parameter values ​​as input values ​​into the trained respective forward artificial neural network models, and obtaining the predicted composite interface bonding strength value of the copper-clad carbon steel layered composite material, the predicted conductivity value of the copper material, and the predicted tensile strength value and the predicted yield strength value of the carbon steel material;

[0071] Step 7: Denormalize the respective initial optimized drawing composite process parameter values, initial optimized drawing forming process parameter values, predicted composite interface bonding strength values, predicted conductivity, predicted tensile strength values, and predicted yield strength values ​​to obtain respective initial optimized drawing composite process parameter data, initial optimized drawing forming process parameter data, predicted composite interface bonding strength data of copper-clad carbon steel layered composite materials, predicted conductivity data of copper materials, and predicted tensile strength data and predicted yield strength data of carbon steel materials;

[0072] Step 8: Determine whether the respective predicted composite interface bonding strength data, predicted electrical conductivity data, predicted tensile strength data and predicted yield strength data reach or exceed the respective corresponding designed composite interface bonding strength data, designed electrical conductivity data, designed tensile strength data and designed yield strength data; if not, re-establish and re-train the respective forward artificial neural network model or reverse artificial neural network model, and repeat steps 5 to 7; if yes, proceed to step 9;

[0073] Step 9: Determine whether the mutual matching accuracy of the respective initial optimized drawing composite process parameter data and the same type of process parameter data in the initial optimized drawing forming process parameter data is not less than the set accuracy of 0.9; if not, re-establish and re-train the respective forward artificial neural network model or reverse artificial neural network model, and repeat steps 5-7; if so, the coordinated control process parameter data optimization is completed, and the optimized coordinated control drawing temperature, drawing speed, drawing force and pass reduction rate and other process parameter data of the copper-clad carbon steel layered composite material are obtained.

[0074] Embodiment 3:

[0075] The comprehensive performance of rolled composite titanium / aluminum / stainless steel layered composite materials is coordinated and controlled to optimize the process parameter data. The specific steps are as follows:

[0076] Step 1: Collect the process parameter data such as rolling temperature, rolling speed and reduction amount when the titanium / aluminum / stainless steel layered composite material is rolled and bonded, and the forming process parameter data such as rolling temperature, rolling speed and reduction amount when the titanium material, aluminum material and stainless steel material constituting the titanium / aluminum / stainless steel layered composite material are individually rolled and formed, as well as the corresponding data of each composite interface bonding strength of the titanium / aluminum / stainless steel layered composite material and the tensile strength, yield strength and elongation after fracture of the titanium material, aluminum material and stainless steel material, and establish a database;

[0077] Step 2: Normalize the rolling composite process parameter data of titanium / aluminum / stainless steel layered composite materials, the rolling forming process parameter data of titanium, aluminum and stainless steel materials, the composite interface bonding strength data, and the tensile strength, yield strength and elongation after fracture of titanium, aluminum and stainless steel materials, respectively, to obtain the corresponding rolling composite process parameter values, rolling forming process parameter values, and composite interface bonding strength, tensile strength, yield strength and elongation after fracture values;

[0078] Step 3: respectively taking the rolling composite process parameter values ​​and the rolling forming process parameter values ​​as input values / output values, and taking the composite interface bonding strength, tensile strength, yield strength and elongation after fracture as output values / input values, and establishing respective forward artificial neural network models and reverse artificial neural network models of the relationship between the rolling composite process parameters and the rolling forming process parameters and the composite interface bonding strength, tensile strength, yield strength and elongation after fracture;

[0079] Step 4: Train the forward artificial neural network model and the reverse artificial neural network model respectively, so that their accuracy is not less than a preset accuracy of 0.85;

[0080] Step 5: The designed composite interface bonding strength data of the titanium / aluminum / stainless steel layered composite materials and the designed tensile strength, designed yield strength and designed elongation after fracture of the titanium, aluminum and stainless steel materials are given, and normalized respectively, and then input as input values ​​into the trained respective reverse artificial neural network models to obtain the respective initial optimized rolling composite process parameter values ​​and initial optimized rolling forming process parameter values;

[0081] Step 6: Input the respective initial optimized rolling composite process parameter values ​​and the initial optimized rolling forming process parameter values ​​as input values ​​into the trained respective forward artificial neural network models, and obtain the predicted composite interface bonding strength values ​​of the titanium / aluminum / stainless steel layered composite materials and the predicted tensile strength, predicted yield strength and predicted elongation after fracture of the titanium material, aluminum material and stainless steel material;

[0082] Step 7: Denormalize the respective initial optimized rolling composite process parameter values, initial optimized rolling forming process parameter values, predicted composite interface bonding strength values, and predicted tensile strength, predicted yield strength, and predicted elongation after fracture to obtain the respective initial optimized rolling composite process parameter data, initial optimized rolling forming process parameter data, predicted composite interface bonding strength data of titanium / aluminum / stainless steel layered composite materials, and predicted tensile strength, predicted yield strength, and predicted elongation after fracture data of titanium, aluminum, and stainless steel materials;

[0083] Step 8: Determine whether the respective predicted composite interface bonding strength, predicted tensile strength, predicted yield strength and predicted elongation after fracture data reach or exceed the respective corresponding designed composite interface bonding strength, designed tensile strength, designed yield strength and designed elongation after fracture data; if not, re-establish and re-train the respective forward artificial neural network model or reverse artificial neural network model, and repeat steps 5 to 7; if yes, proceed to step 9;

[0084] Step 9: Determine whether the mutual matching accuracy of the respective initial optimized rolling composite process parameter data and the same type of process parameter data in the initial optimized rolling forming process parameter data is not less than the set accuracy of 0.9; if not, re-establish and re-train the respective forward artificial neural network model or reverse artificial neural network model, and repeat steps 5-7; if so, the coordinated control process parameter data optimization is completed, and the optimized coordinated control rolling temperature, rolling speed and reduction amount and other process parameter data of the titanium / aluminum / stainless steel layered composite material are obtained.

[0085] In summary, the technical solution of the present invention mines the existing data of the process parameters of the heterogeneous layered composite material and the component materials, the corresponding composite interface performance and the self-performance, uses artificial intelligence technology to realize the association of two or more independent process parameters and related independent performances, obtains independent process parameter data based on the optimization of their respective design performances, and realizes the optimization of the process parameter data of the synergistic regulation of the comprehensive performance of the heterogeneous layered composite material through mutual approximation and matching. The advantage of the present invention is that it can complete the intelligent optimization of the preparation process parameter data of the synergistic regulation of the comprehensive performance of the heterogeneous layered composite material based on the design performance, existing performance and process parameter data of the component materials and the heterogeneous layered composite material, significantly improve the comprehensive performance of the composite material, reduce costs, save time, improve efficiency, save energy and reduce consumption, and be low-carbon and environmentally friendly.

[0086] The embodiments of the present invention are described above, but the present invention is not limited to the above-mentioned specific implementation modes. The above-mentioned specific implementation modes are merely illustrative and not restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which are all within the protection of the present invention.

Claims

1. A method for synergistically regulating the comprehensive properties of heterogeneous layered composite materials, characterized in that: The steps include: Step 1: collect the first preparation process parameter data of the heterogeneous layered composite material and the first forming process parameter data when each heterogeneous component material is formed independently, as well as the first composite interface performance data of the heterogeneous layered composite material and the first self performance data of each component material corresponding to each other, and perform normalization processing to obtain the first preparation process parameter value, the first forming process parameter value, the first composite interface performance value and the first self performance value respectively; Step 2: respectively using the first preparation process parameter value and the first forming process parameter value as input value / output value, and using the first composite interface performance value and the first self performance value as output value / input value, establishing respective first artificial neural network models and second artificial neural network models and training them, so that their accuracies reach or exceed preset accuracies respectively; Step 3: The designed composite interface performance data of the heterogeneous layered composite material and the designed self performance data of each of the component materials are given, and after normalization, they are input into the trained respective second artificial neural network models as input values ​​to obtain the respective initially optimized second preparation process parameter values ​​and second forming process parameter values; Step 4: inputting the second preparation process parameter value and the second forming process parameter value respectively initially optimized into the first artificial neural network model respectively trained, and obtaining the second composite interface performance value of the heterogeneous layered composite material and the second self performance value of each of the component materials respectively; Step 5: Denormalize the second preparation process parameter values ​​and the second forming process parameter values, the second composite interface performance values, and the second self performance values ​​that are initially optimized, to obtain the second preparation process parameter data and the second forming process parameter data that are initially optimized, the predicted composite interface performance data of the heterogeneous layered composite material, and the predicted self performance data of each of the component materials; Step 6: Determine whether the respective predicted composite interface performance data and the predicted self performance data reach or exceed the respective corresponding designed composite interface performance data and the designed self performance data; if not, repeat steps 2-5; If yes, go to step 7; Step 7: Determine whether the mutual matching accuracy of the second manufacturing process parameter data and the same type of process parameter data in the second forming process parameter data respectively initially optimized reaches or exceeds the set accuracy; If not, repeat steps 2-5; if so, the coordinated control process parameter data optimization is completed, and the process parameter data for coordinated control of the comprehensive performance of the heterogeneous layered composite material is obtained.

2. The method for coordinated regulation of comprehensive properties of heterogeneous layered composite materials according to claim 1, characterized in that: The type of the heterogeneous layered composite material is at least one of a laminated composite structure type, a side composite structure type, a coated composite structure type or an inlaid composite structure type.

3. The method for coordinated regulation of comprehensive properties of heterogeneous layered composite materials according to claim 1, characterized in that: The component material is at least one of a metal material, an inorganic non-metal material, a polymer material or a composite material; the composite interface performance and the self performance are at least one of a mechanical property, a physical property or a chemical property.

4. The method for coordinated regulation of comprehensive properties of heterogeneous layered composite materials according to claim 1, characterized in that: The preparation process is at least one of solid-solid composite, liquid-solid composite, gas-solid composite, liquid-liquid composite or chemical composite, and the forming process is at least one of solid forming, liquid forming, gas forming or chemical forming.

5. The method for coordinated regulation of comprehensive properties of heterogeneous layered composite materials according to claim 1, characterized in that: The first preparation process parameter and the second preparation process parameter are the full-process preparation process parameters or process preparation process parameters of the heterogeneous layered composite material, and the first forming process parameter and the second forming process parameter are the full-process forming process parameters or process forming process parameters of the component material; wherein the full process includes multiple processes.

6. The method for coordinated regulation of comprehensive properties of heterogeneous layered composite materials according to claim 1, characterized in that: When the heterogeneous layered composite material contains a plurality of the composite interfaces, if the composite is formed as a whole at one time, the first preparation process parameter data and the second preparation process parameter data refer to process parameter data for avoiding the generation of the intermetallic compound at the composite interface where the intermetallic compound is most likely to be generated when preparing the heterogeneous layered composite material; If the composite forming is performed separately for multiple times, the first preparation process parameter data and the second preparation process parameter data refer to the process parameter data of each composite forming of the component materials in the process of preparing the heterogeneous layered composite material.

7. The method for coordinated regulation of comprehensive properties of heterogeneous layered composite materials according to claim 1, characterized in that: The preset accuracy of the first artificial neural network model and the second artificial neural network model is not less than 0.85, and the setting accuracy of the same type of process parameter data is not less than 0.9 or satisfies the differential temperature composite forming between the component materials.

8. The method for coordinated regulation of comprehensive properties of heterogeneous layered composite materials according to claim 1, characterized in that: The same type of process parameters are at least one of the temperature, speed, time, cooling capacity, degree of deformation, forming force, friction coefficient, layer thickness ratio, surface quality or material state under the same preparation process or the same forming process.

9. The method for coordinated regulation of comprehensive properties of heterogeneous layered composite materials according to claim 1, characterized in that: At least one of a genetic algorithm, a simulated annealing algorithm, a taboo search algorithm, a particle swarm algorithm or an ant colony algorithm is used to optimize the weight or threshold of the first artificial neural network model or the second artificial neural network model.

10. A method for synergistically regulating process parameter data for comprehensive performance of heterogeneous layered composite materials, characterized in that: The synergistic control process parameter data is optimized and obtained by the synergistic control method for comprehensive performance of heterogeneous layered composite materials according to any one of claims 1 to 9.

Citation Information

Cited By

  • Method for testing interfacial strength of magnesium-aluminum laminated composite board

    CN119375145A

  • Method for testing interface strength of magnesium-aluminum layered composite plate

    CN119375145B

  • Manufacturing optimization method, device and equipment of composite material, medium and product

    CN122452194A