Method for constructing high-precision prediction model for residual stress in heat treatment of cylinder cover

Abstract

The invention provides a cylinder cover heat treatment residual stress high-precision prediction model construction method, which comprises the following steps: firstly, carrying out quenching convective heat transfer coefficient solving and quenching residual stress prediction on a local sample piece model obtained after geometric cutting of a cylinder cover model, and carrying out iterative correction on material thermophysical property parameters to obtain a high-precision prediction model; the prediction result of the quenching residual stress of the local sample piece of the cylinder cover can meet the higher precision requirement; then the thermophysical parameters of the material calibrated by the sample piece model are used in the processes of convective heat transfer coefficient solving, quenching residual stress prediction and aging residual stress prediction of the cylinder cover model; and finally, for the cylinder cover model, according to the difference of the heat exchange coefficients of the inner and outer surfaces of the cylinder cover in the quenching process, solving the surface heat exchange coefficients of the cylinder cover model in a partitioned manner, and establishing a cylinder cover heat treatment residual stress high-precision prediction model. The method aims at high-efficiency and high-precision prediction of the residual stress of the whole quenching and aging process of the cylinder cover, and has engineering guiding significance for accurately mastering the distribution of the residual stress in heat treatment of the cylinder cover and proposing a residual stress control strategy by regulating and controlling key influence parameters, reducing the complexity of an iteration object and shortening a process simulation period.

Description

Technical Field

[0001] The present invention belongs to the field related to the technology of predicting residual stress during heat treatment of complex structural parts manufacturing process, and in particular to a method for constructing a high-precision prediction model for residual stress during heat treatment of a cylinder head. Background Art

[0002] With the rapid development of high-end equipment manufacturing fields such as aerospace, automobile manufacturing, and mechanical engineering, the performance and quality requirements for complex castings are becoming increasingly higher. Since the size and distribution of residual stress in castings directly affect the service life and safety of castings, it is urgent to develop high-precision residual stress prediction technology to achieve accurate prediction and effective control of residual stress generated in the manufacturing process of castings.

[0003] Aluminum alloy cylinder head castings for automotive engines usually undergo T6 / T7 heat treatment to improve their mechanical properties, which generally includes high-temperature solution treatment, rapid quenching under cooling medium (such as water), and aging treatment at medium temperature. For cast aluminum cylinder heads with complex structures, the highly non-uniform temperature distribution during rapid quenching will cause large thermal stress and residual stress, and its value can even reach an order of magnitude comparable to the material yield stress. The residual stress caused by the heat treatment process will subsequently have a significant impact on the fatigue performance of the cylinder head. In the design process of cast aluminum cylinder heads, finite element simulation analysis is usually used to check the design indicators and guide design optimization. If the influence of residual stress in the manufacturing process is not considered in the simulation analysis, it is often impossible to accurately evaluate its quality and performance. However, the current accurate prediction of residual stress in the manufacturing process of complex castings such as cylinder heads still faces huge challenges.

[0004] The transient temperature gradient at different positions of the cylinder head casting during the quenching process is the driving force for the generation of residual stress, and accurate temperature prediction is the basis for accurate calculation of residual stress. The heat transfer during the quenching process of aluminum alloy cylinder head castings is mainly divided into three stages: steam film stage, boiling stage, and convection heat transfer stage. At present, the quenching temperature measurement test is often carried out on the casting, and the temperature change history at different positions of the casting during the test is recorded by thermocouples, so as to obtain the heat transfer boundary conditions of the quenching process. In addition, when the local thermal stress caused by the temperature gradient inside the cylinder head during the quenching process exceeds the yield strength of the material, the material will undergo local plastic deformation, resulting in residual stress inside the cylinder head after cooling to room temperature. In the aging stage, the cylinder head undergoes continuous heating at the aging temperature, which causes the yield strength of the material to change, and produces stress relaxation, so that the residual stress inside the cylinder head is redistributed. By establishing the material constitutive relationship in the quenching stage and the aging stage, it is helpful to accurately reflect the intrinsic relationship between material stress and strain in the heat treatment process.

[0005] In this context, the present invention proposes a method for constructing a high-precision prediction model for residual stress in heat treatment of cylinder heads. This method selects a local sample model of the cylinder head as the iteration object, and uses the temperature-dependent parameters of the material thermophysical properties after calibration of the sample model for solving the heat transfer coefficient of the cylinder head model, predicting quenching residual stress, and predicting aging residual stress. The constitutive relationship is used to describe the high-temperature rheological behavior of the cylinder head material in the quenching and aging stages, respectively, in order to achieve the full-process prediction of residual stress in heat treatment of cylinder heads. This method is conducive to accurately predicting the distribution and size of residual stress, shortening the research and development cycle of heat treatment processes, reducing the number of tests and costs, and meeting the control of the quality of complex castings in engineering application fields. Summary of the invention

[0006] In view of this, the present invention aims to propose a method for constructing a high-precision prediction model for residual stress in cylinder head heat treatment, so as to address the problems of difficulty in predicting residual stress in the whole process of cylinder head heat treatment, long iterative calculation cycle and high R&D cost.

[0007] To achieve the above object, the technical solution of the present invention is achieved as follows:

[0008] A method for constructing a high-precision prediction model for residual stress in heat treatment of a cylinder head comprises the following steps:

[0009] S1. Select a local typical part of the cylinder head model and obtain a local sample model through geometric cutting;

[0010] S2, measuring the temperature of the cylinder head component at selected points during the quenching process, wherein the measuring the temperature of the cylinder head component at selected points during the quenching process includes drilling holes at selected points on the cylinder head local sample and the cylinder head casting according to the structural characteristics, arranging thermocouples, and obtaining the change of the actual temperature of each test point over time through a temperature collector;

[0011] S3. According to the chemical composition of the cylinder head material, the initial values ​​of the thermophysical parameters of the cylinder head material that change with temperature (hereinafter referred to as thermophysical temperature-dependent parameters) are obtained by using JMatPro software and experimental tests, including density, thermal conductivity, specific heat capacity, etc. Based on the temperature measurement data of the measuring points during the quenching process and the thermophysical temperature-dependent parameters of the material, the curve of the heat transfer coefficient of the sample surface changing with temperature is inversely calculated;

[0012] S4. Based on the dynamic compression mechanics test and high temperature tensile stress relaxation test of cylinder head materials, the material constitutive relations of the cylinder head in the quenching and aging stages are constructed, and the VUMAT subroutines of the constitutive relations of the cylinder head materials in the quenching stage and the aging stage are written using the Fortran language;

[0013] S5. Establish an ABAQUS finite element analysis model for the quenching process of the cylinder head sample, calculate the residual stress distribution of the cylinder head sample by using the temperature variation parameters of the thermophysical properties of the cylinder head material, the surface heat transfer coefficient that varies with temperature during the quenching process of the sample, and the VUMAT subroutine of the constitutive relationship of the material in the quenching stage, and compare the deviation with the residual stress test results;

[0014] S6. The temperature variation parameters of the thermophysical properties of the materials calibrated by the sample model are used in the process of solving the heat transfer coefficient of the cylinder head surface and predicting the residual stress after quenching. An ABAQUS finite element analysis model of the cylinder head quenching process is established. At the same time, the heat transfer coefficient of the inner and outer surfaces of the cylinder head quenching process that changes with temperature and the constitutive relationship of the cylinder head material quenching stage VUMAT subroutine are used for model calculation to obtain the residual stress distribution of the cylinder head after quenching.

[0015] S7. The temperature variation parameters of the material thermophysical properties calibrated by the sample model are used in the cylinder head aging residual stress prediction process, and the ABAQUS finite element analysis model of the cylinder head aging process is established. Based on the cylinder head quenching residual stress distribution results and the cylinder head material aging stage constitutive relationship VUMAT subroutine, the cylinder head aging residual stress distribution is obtained.

[0016] Furthermore, in step S3, the specific implementation method is:

[0017] Assume an initial value for the surface convection heat transfer coefficient, use the preset initial value to solve the heat conduction differential equation, and obtain the temperature calculation results of different measuring points of the sample; compare the deviation between the calculated temperature value and the test value at each measuring point, use the optimization algorithm to correct the surface heat transfer coefficient, and make the calculated temperature value close to the test value through cyclic iteration, so as to solve the surface heat transfer coefficient curve that changes with temperature;

[0018] The heat conduction differential equation is:

[0019]

[0020] Where λ is the thermal conductivity of the material, C P is the specific heat capacity of the material, and ρ is the density of the material.

[0021] Furthermore, in step S4, the specific implementation method is:

[0022] According to the range of undetermined parameters in the constitutive relationship of materials in the quenching and aging stages, the undetermined parameters are fitted by intelligent optimization algorithms such as genetic algorithm and particle swarm algorithm based on the data of dynamic compression mechanics test and high-temperature tensile stress relaxation test; the mean relative error (MAPE) is used as the objective function to compare the error between the deformation curve predicted by the constitutive relationship and the deformation curve tested by the test;

[0023] Among them, the definition expression of MAPE is:

[0024]

[0025] Where n is the number of test data points, y cal and exp Represent the calculated value and experimental value respectively. The smaller the MAPE value, the higher the fitting accuracy.

[0026] Furthermore, in step S5, the specific implementation method is:

[0027] The cylinder head sample quenching residual stress prediction model is used to obtain the sample quenching residual stress distribution, and the predicted value is compared with the residual stress test value. When the accuracy requirement is not met, the material thermophysical property temperature change parameters are iteratively corrected until the sample quenching residual stress prediction value that meets the accuracy requirement is obtained. At this time, the material thermophysical property temperature change parameter data calibrated by the sample model can be obtained.

[0028] An electronic device comprises a processor and a memory which is in communication with the processor and is used to store instructions executable by the processor, wherein the processor is used to execute the method for constructing a high-precision prediction model for residual stress in heat treatment of a cylinder head.

[0029] A server includes at least one processor and a memory connected to the processor in communication, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the processor to enable the at least one processor to execute the method for constructing a high-precision prediction model for residual stress in cylinder head heat treatment.

[0030] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for constructing a high-precision prediction model for residual stress in heat treatment of a cylinder head is described.

[0031] Compared with the prior art, the method for constructing a high-precision prediction model for residual stress in heat treatment of a cylinder head according to the present invention has the following advantages:

[0032] (1) The method for constructing a high-precision prediction model for residual stress during heat treatment of a cylinder head described in the present invention comprehensively utilizes a heat transfer coefficient inverse method based on heat transfer analysis and a material constitutive relationship construction method, and considers iterative optimization of temperature variation parameters of the thermophysical properties of the cylinder head material and differential partitioning of the heat transfer coefficient of the surface of the complex structure of the cylinder head. Under the framework of the finite element model and simulation analysis process, a high-precision prediction model for residual stress during the quenching and aging stages of the cylinder head is constructed, thereby solving the full-process simulation prediction of residual stress during the heat treatment process of the cylinder head.

[0033] (2) The method for constructing a high-precision prediction model for residual stress during heat treatment of a cylinder head described in the present invention predicts the distribution and magnitude of residual stress during heat treatment of a cylinder head casting, which can shorten the research and development cycle of the heat treatment process, reduce the number of experiments and costs, and is conducive to rationally controlling the residual stress during the cylinder head manufacturing process and improving its performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the accompanying drawings:

[0035] Figure 1 A schematic diagram of the method flow of the embodiment of the present invention;

[0036] Figure 2 A schematic diagram of the cylinder head model and sample selection according to an embodiment of the present invention;

[0037] Figure 3 A schematic diagram of a process for solving a surface heat transfer coefficient based on heat transfer analysis according to an embodiment of the present invention;

[0038] Figure 4 It is a schematic diagram of a curve showing the calculated value of the convective heat transfer coefficient of different heat transfer surfaces of the cylinder head according to an embodiment of the present invention as a function of temperature;

[0039] Figure 5 The equivalent residual stress distribution cloud diagram of the cylinder head model heat treatment process according to the embodiment of the present invention: (a) quenching stage, (b) aging stage schematic diagram;

[0040] Figure 6 Comparison between the predicted value and the tested value of residual stress in the cylinder head heat treatment according to the embodiment of the present invention: (a) quenching stage, (b) schematic diagram of aging stage. DETAILED DESCRIPTION

[0041] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.

[0042] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and the like are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, features defined as "first", "second", and the like may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "multiple" means two or more.

[0043] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood by specific circumstances.

[0044] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0045] like Figures 1 to 6 As shown in the figure, a high-precision prediction model construction method for residual stress in cylinder head heat treatment is used to predict the quenching residual stress and aging residual stress of aluminum alloy cylinder head castings during heat treatment. Compared with the test values, it shows a high prediction accuracy. Figure 1 As shown, the specific implementation steps are as follows:

[0046] Step 1: Select the fire plate part of the cylinder head model as the sample model, such as Figure 2 shown.

[0047] Step 2: Select points for drilling holes in the cylinder head casting and fire plate samples, arrange thermocouples, and conduct temperature measurement tests during the quenching process. Use a temperature acquisition instrument to obtain the actual temperature changes of each test point over time.

[0048] Step 3: According to the chemical composition of the cylinder head material, the initial values ​​of the thermophysical temperature variation parameters of the cylinder head material are obtained through JMatPro software and experimental tests, including density, thermal conductivity, specific heat capacity, etc. Based on the temperature measurement data of each measuring point in the quenching process and the thermophysical temperature variation parameters of the material, the surface heat transfer coefficient of the sample is reversed with the temperature variation curve. The implementation process is as follows: Figure 3 shown.

[0049] Specifically, an initial value is assumed for the surface heat transfer coefficient, and the heat conduction differential equation is solved using the preset initial value to obtain the temperature calculation results of different measuring points of the sample; the deviation between the calculated temperature value and the test value of each measuring point is compared, and the surface heat transfer coefficient is corrected using an optimization algorithm. The temperature calculation value is made close to the test value through cyclic iteration, thereby solving the surface heat transfer coefficient curve that changes with temperature;

[0050] The heat conduction differential equation is:

[0051]

[0052] Where λ is the thermal conductivity of the material, C P is the specific heat capacity of the material, and ρ is the density of the material.

[0053] Step 4: Perform dynamic compression mechanical tests and high-temperature tensile stress relaxation tests on the cylinder head material, construct the material constitutive relations of the cylinder head in the quenching and aging stages, and use Fortran language to write the VUMAT subroutine for the constitutive relation of the cylinder head material in the quenching stage and the VUMAT subroutine for the constitutive relation of the cylinder head material in the aging stage.

[0054] Specifically, according to the range of undetermined parameters in the constitutive relationship of the material in the quenching and aging stages, based on the dynamic compression mechanics test and high-temperature tensile stress relaxation test data, the undetermined parameters are fitted through intelligent optimization algorithms such as genetic algorithm and particle swarm algorithm; the mean relative deviation (MAPE) is used as the objective function to compare the errors of the deformation curve predicted by the constitutive relationship and the deformation curve of the experimental test;

[0055] Among them, the definition expression of MAPE is:

[0056]

[0057] Where n is the number of test data points, y cal and exp Represent the calculated value and experimental value respectively. The smaller the MAPE value, the higher the fitting accuracy.

[0058] Step 5: Establish an ABAQUS finite element analysis model for the quenching process of the cylinder head sample. Calculate the residual stress distribution of the cylinder head sample by using the temperature-dependent parameters of the material's thermophysical properties, the surface heat transfer coefficient that changes with temperature during the sample's quenching process, and the VUMAT subroutine of the material constitutive relationship during the quenching stage. Iteratively calibrate the temperature-dependent parameters of the material's thermophysical properties by comparing the deviation between the predicted value and the tested value.

[0059] Specifically, the cylinder head sample quenching residual stress prediction model is used to obtain the sample quenching residual stress distribution, and the predicted value is compared with the residual stress test value. When the accuracy requirement is not met, the material thermophysical property temperature change parameters are iteratively corrected until the sample quenching residual stress prediction value that meets the accuracy requirement is obtained. At this time, the material thermophysical property temperature change parameter data calibrated by the sample model can be obtained.

[0060] Step 6: Use the material thermophysical property temperature variation parameters calibrated by the sample model to solve the cylinder head surface heat transfer coefficient and predict the quenching residual stress. Establish the ABAQUS finite element analysis model of the cylinder head quenching process, and compare the data curves of the convection heat transfer coefficient of different heat transfer surfaces of the cylinder head during the quenching process with the temperature variation (such as Figure 4 As shown in the figure), the constitutive relation of the cylinder head material in the quenching stage VUMAT subroutine is used for model calculation to obtain the residual stress distribution of the cylinder head after quenching, as shown in the figure. Figure 5 As shown in a.

[0061] Step 7: Use the material thermophysical property temperature variation parameters calibrated by the sample model to predict the cylinder head aging residual stress, establish the ABAQUS finite element analysis model of the cylinder head aging process, and obtain the cylinder head aging residual stress distribution based on the cylinder head quenching residual stress distribution results and the cylinder head material aging stage constitutive relationship VUMAT subroutine, such as Figure 5 As shown in b, a residual stress prediction model for the whole process of quenching and aging heat treatment of cylinder head is established. Compared with the residual stress test value, the model has a higher prediction accuracy, as shown in Figure 6 shown.

[0062] The present invention is based on the heat transfer analysis of the quenching process, considers the constitutive relationship of the cylinder head material in the quenching and aging stages, and uses the temperature variation parameters of the material thermophysical properties calibrated by the sample model to solve the heat transfer coefficient of the cylinder head model, predict the quenching residual stress, and predict the aging residual stress, so as to establish a high-precision prediction model for the residual stress of the cylinder head heat treatment.

[0063] The present invention also proposes an electronic device, comprising a processor and a memory that is communicatively connected to the processor and is used to store executable instructions for the processor, wherein the processor is used to execute the method for constructing a high-precision prediction model for residual stress in heat treatment of a cylinder head.

[0064] The present invention also proposes a server, comprising at least one processor and a memory communicatively connected to the processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the processor so that the at least one processor executes the method for constructing a high-precision prediction model for residual stress in cylinder head heat treatment.

[0065] The present invention also proposes a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the method for constructing a high-precision prediction model for residual stress in heat treatment of a cylinder head is implemented.

[0066] Advantages of this method:

[0067] 1. The present invention discloses a method for constructing a high-precision prediction model for residual stress in heat treatment of a cylinder head. The method comprehensively utilizes a heat transfer coefficient inverse method based on heat transfer analysis and a material constitutive relationship construction method, considers iterative optimization of temperature variation parameters of thermophysical properties of cylinder head materials, and differential partitioning of heat transfer coefficients on the surface of complex structures of cylinder heads, and constructs a high-precision prediction model for residual stress in the quenching stage and aging stage of the cylinder head under the framework of a finite element model and simulation analysis process, thereby solving the full-process simulation prediction of residual stress in the heat treatment process of the cylinder head.

[0068] 2. The present invention discloses a method for constructing a high-precision prediction model for residual stress of cylinder head heat treatment, which predicts the distribution and size of residual stress of cylinder head castings during heat treatment. This can shorten the research and development cycle of heat treatment process, reduce the number of experiments and costs, and is conducive to reasonably controlling the residual stress of cylinder head manufacturing process and improving its performance.

[0069] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for constructing a high-precision prediction model for residual stress in cylinder head heat treatment, characterized in that: The following steps are involved: S1. Select a local typical part of the cylinder head model and obtain a local sample model through geometric cutting; S2, measuring the temperature of the cylinder head component at selected points during the quenching process, wherein the measuring the temperature of the cylinder head component at selected points during the quenching process includes drilling holes at selected points on the cylinder head local sample and the cylinder head casting according to the structural characteristics, arranging thermocouples, and obtaining the change of the actual temperature of each test point over time through a temperature collector; S3. According to the chemical composition of the cylinder head material, the initial value of the thermophysical property parameters of the cylinder head material that change with temperature is obtained by using JMatPro software and experimental testing. Based on the temperature measurement data of the measuring points during the quenching process and the temperature variation parameters of the thermophysical properties of the material, the curve of the heat transfer coefficient of the sample surface changing with temperature is inversely calculated; S4. Based on the dynamic compression mechanics test and high temperature tensile stress relaxation test of cylinder head materials, the material constitutive relations of the cylinder head in the quenching and aging stages are constructed, and the VUMAT subroutines of the constitutive relations of the cylinder head materials in the quenching stage and the aging stage are written using the Fortran language; S5. Establish an ABAQUS finite element analysis model for the quenching process of the cylinder head sample, calculate the residual stress distribution of the cylinder head sample by using the temperature variation parameters of the thermophysical properties of the cylinder head material, the surface heat transfer coefficient that varies with temperature during the quenching process of the sample, and the VUMAT subroutine of the constitutive relationship of the material in the quenching stage, and compare the deviation with the residual stress test results; S6. The temperature variation parameters of the thermophysical properties of the materials calibrated by the sample model are used in the process of solving the heat transfer coefficient of the cylinder head surface and predicting the residual stress after quenching. An ABAQUS finite element analysis model of the cylinder head quenching process is established. At the same time, the heat transfer coefficient of the inner and outer surfaces of the cylinder head quenching process that changes with temperature and the constitutive relationship of the cylinder head material quenching stage VUMAT subroutine are used for model calculation to obtain the residual stress distribution of the cylinder head after quenching. S7. The temperature variation parameters of the material thermophysical properties calibrated by the sample model are used in the cylinder head aging residual stress prediction process, and the ABAQUS finite element analysis model of the cylinder head aging process is established. Based on the cylinder head quenching residual stress distribution results and the cylinder head material aging stage constitutive relationship VUMAT subroutine, the cylinder head aging residual stress distribution is obtained.

2. The method for constructing a high-precision prediction model for residual stress in cylinder head heat treatment according to claim 1, characterized in that: In step S3, the initial values ​​of the thermophysical property parameters include density, thermal conductivity and specific heat capacity.

3. The method for constructing a high-precision prediction model for residual stress in cylinder head heat treatment according to claim 2, characterized in that: In step S3, the specific implementation method is: Assume an initial value for the surface convection heat transfer coefficient, use the preset initial value to solve the heat conduction differential equation, and obtain the temperature calculation results of different measuring points of the sample; compare the deviation between the calculated temperature value and the test value at each measuring point, use the optimization algorithm to correct the surface heat transfer coefficient, and make the calculated temperature value close to the test value through cyclic iteration, so as to solve the surface heat transfer coefficient curve that changes with temperature; The heat conduction differential equation is: Where λ is the thermal conductivity of the material, C P is the specific heat capacity of the material, and ρ is the density of the material.

4. The method for constructing a high-precision prediction model for residual stress in cylinder head heat treatment according to claim 1, characterized in that: In step S4, the specific implementation method is: According to the range of undetermined parameters in the constitutive relationship of materials in the quenching and aging stages, based on the dynamic compression mechanics test and high-temperature tensile stress relaxation test data, the undetermined parameters are fitted by genetic algorithm and particle swarm algorithm intelligent optimization algorithm; the average relative deviation is used as the objective function to compare the error between the deformation curve predicted by the constitutive relationship and the deformation curve tested by the experiment; Among them, the definition expression of the average relative deviation is: Where n is the number of test data points, y cal and exp Represent the calculated value and experimental value respectively. The smaller the MAPE value, the higher the fitting accuracy.

5. The method for constructing a high-precision prediction model for residual stress in cylinder head heat treatment according to claim 1, characterized in that: In step S5, the specific implementation method is: The cylinder head sample quenching residual stress prediction model is used to obtain the sample quenching residual stress distribution, and the predicted value is compared with the residual stress test value. When the accuracy requirement is not met, the material thermophysical property temperature change parameters are iteratively corrected until the sample quenching residual stress prediction value that meets the accuracy requirement is obtained. At this time, the material thermophysical property temperature change parameter data calibrated by the sample model can be obtained.

6. An electronic device, comprising a processor and a memory connected to the processor for storing instructions executable by the processor, characterized in that: The processor is used to execute the method for constructing a high-precision prediction model for residual stress during heat treatment of a cylinder head as described in any one of claims 1 to 5.

7. A server, characterized in that: It includes at least one processor and a memory that is communicatively connected to the processor, wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the processor so that the at least one processor executes the method for constructing a high-precision prediction model for residual stress in heat treatment of a cylinder head as described in any one of claims 1-5.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for constructing a high-precision prediction model for residual stress during heat treatment of a cylinder head according to any one of claims 1 to 5 is implemented.

Images