A method for predicting the over-rotation fracture speed of a surrogate model

Abstract

This invention relates to the field of aero-engine technology and discloses a method for predicting the over-rotation fracture speed of a rotor disk based on a surrogate model. This invention utilizes a strain prediction surrogate model for analysis and calculation, which improves the accuracy and efficiency of rotor disk fracture speed prediction. This invention replaces the traditional finite element method with a strain prediction surrogate model for strain prediction calculation. It eliminates the need for numerous simulation models simulating rotor disk over-rotation fracture, requiring only a small number of sample points for finite element calculations to quickly output strain prediction results under any operating condition. This results in high computational efficiency, low computational cost, and the ability to meet real-time computational requirements. This invention considers the influence of uncertain parameters on rotor disk fracture behavior and predicts the fracture speed range under the influence of uncertain parameters, improving the accuracy and reliability of fracture speed prediction and providing a more scientific basis for rotor disk design and optimization.

Description

Technical Field

[0001] This invention relates to the field of aero-engine technology and discloses a method for predicting the over-rotation fracture speed of a wheel based on a surrogate model. Background Technology

[0002] To calculate and predict the fracture speed of a wheel in real time under scenarios such as virtual experiments, it is necessary to obtain the strain response of the wheel model. Although the traditional finite element method can provide strain field information of the wheel, the rapid nature of the over-rotation fracture test makes it difficult to guarantee real-time calculations if a physical model is used directly for prediction. Furthermore, traditional simulation analysis does not consider uncertainties affecting the wheel's fracture speed, resulting in simulation results that cannot fully represent the actual fracture state. Summary of the Invention

[0003] The purpose of this invention is to provide a method for predicting the over-rotation fracture speed of a wheel based on a surrogate model, which can meet the real-time requirements of calculation, and at the same time, introduces the prediction of fracture speed under uncertainty, which can improve the accuracy and efficiency of wheel fracture speed prediction.

[0004] To achieve the above-mentioned technical effects, the technical solution adopted by the present invention is as follows:

[0005] A method for predicting the over-rotation fracture speed of a chariot based on a surrogate model includes:

[0006] The theoretical fracture strain value and material parameters of the target wheel material are determined, and a finite element analysis model of the wheel is established; the material parameters include the density, Poisson's ratio, elastic modulus and material plasticity data of the target wheel.

[0007] Uncertainty parameters affecting the maximum strain value of the wheel are obtained, and key parameters are screened from these uncertainty parameters through sensitivity analysis. The key parameters include key dimensional parameters, elastic modulus, Poisson's ratio, material plasticity data, and rotational speed.

[0008] Based on the key parameters, an optimized Latin hypercube sampling method is used to generate several initial sample points in the design space; each initial sample point is input into the finite element analysis model for simulation to obtain the maximum strain analysis value of the disk at the corresponding rotational speed for each initial sample point; with the key parameters of all initial sample points as input and the maximum strain analysis value corresponding to each initial sample point as output, the Kriging model is used to construct the initial strain prediction proxy model of the disk.

[0009] The Latin hypercube sampling method is used to perform sequential point addition, generating training sample points within the design space of the key parameters. The training sample points are then input into the finite element analysis model for simulation to obtain the maximum strain analysis value corresponding to the training sample points. The initial strain prediction surrogate model is trained and reconstructed using the training sample points and the initial sample points. The accuracy of the reconstructed strain prediction surrogate model is then verified. If the reconstructed strain prediction surrogate model meets the accuracy requirements, a trained strain prediction surrogate model is obtained; otherwise, sequential point addition is performed again until a trained strain prediction surrogate model is obtained.

[0010] The trained strain prediction surrogate model is corrected, and then the strain prediction surrogate model is used to predict the fracture speed of the disk, so as to obtain the theoretical fracture speed of the disk and the fracture speed range under the influence of uncertainty parameters.

[0011] Furthermore, the uncertainty parameters include dimensional parameters, material parameters, and load parameters.

[0012] Furthermore, the steps for determining the theoretical fracture strain value of the target disk material include:

[0013] Several tensile specimens were made from raw materials from different production batches of the target wheel. Material property tests were conducted on each tensile specimen. Based on the measured values ​​of engineering stress and engineering strain obtained from the tests, the material engineering stress-engineering strain curve of the target wheel was plotted.

[0014] The material's engineering stress-engineering strain curve is converted into a true stress-true strain curve, and the theoretical fracture strain value of the target wheel material is read from the true stress-true strain curve.

[0015] Furthermore, the steps for determining the material parameters of the target wheel include:

[0016] The Poisson's ratio and elastic modulus of each tensile specimen were tested using a universal testing machine. The maximum and minimum values ​​of the Poisson's ratio and elastic modulus were then used as the range of Poisson's ratio and elastic modulus of the target disc, respectively. At the same time, the density of each tensile specimen was measured, and the maximum and minimum values ​​of the density were used as the range of density of the target disc.

[0017] Based on the engineering stress and engineering strain measurements obtained from the material property tests of each tensile specimen, the true stress and true strain of each tensile specimen are obtained. Then, the data are input into the material plasticity data function to obtain the material plasticity data of each tensile specimen. The average value of the material plasticity data of all tensile specimens is calculated and used as the theoretical value of the material plasticity data of the target wheel. The maximum and minimum values ​​of the material plasticity data of all tensile specimens are statistically analyzed to determine the range of values ​​for the material plasticity data of the target wheel.

[0018] Furthermore, the expression for the material plasticity data function is as follows:

[0019] ;

[0020] in, This refers to material plasticity data; The measured engineering stress value of the tensile specimen; This represents the true strain of the tensile specimen.

[0021] Furthermore, methods for obtaining a well-trained strain prediction surrogate model include:

[0022] Using the key parameters of the training sample points and the initial sample points as input, and the maximum strain analysis value corresponding to the training sample points and the initial sample points as output, a strain prediction surrogate model is reconstructed using the Kriging model. Then, the key parameters of the training sample points are input into the reconstructed strain prediction surrogate model to obtain the maximum strain prediction value corresponding to the training sample points. The root mean square error between the maximum strain prediction value and the maximum strain analysis value of the training sample points is then calculated. If the root mean square error is less than a preset error threshold, the prediction accuracy of the reconstructed strain prediction surrogate model is considered to meet the preset accuracy requirement, and a trained strain prediction surrogate model is obtained. Otherwise, the sequence of points is repeated to regenerate a training sample point until a trained strain prediction surrogate model is obtained.

[0023] Furthermore, the steps of using the strain prediction surrogate model to predict the fracture speed of the disk and obtain the theoretical fracture speed and the fracture speed range under the influence of uncertainty parameters include:

[0024] The theoretical values ​​of the target wheel's key geometric parameters, elastic modulus, Poisson's ratio, and material plasticity data are input into the trained strain prediction proxy model. A first initial test speed and a second initial test speed are also input. These initial test speeds are then analyzed within the trained strain prediction proxy model to obtain the first and second maximum strain prediction values ​​for the target wheel. The difference between the minimum of the first and second maximum strain prediction values ​​and the theoretical fracture strain of the target wheel is calculated. If the difference is less than a preset range, the corresponding test speed is used as the predicted theoretical fracture speed of the target wheel. Otherwise, a bisection method is used to adjust and update the test speed to obtain the theoretical fracture speed of the target wheel.

[0025] Furthermore, the step of using the strain prediction surrogate model to predict the fracture speed of the disk and obtain the theoretical fracture speed and the fracture speed range under the influence of uncertainty parameters also includes:

[0026] The Monte Carlo sampling method is used to sample within the design space of the key dimensional parameters, elastic modulus, and Poisson's ratio, generating several sample points. Each sample point and the maximum strain prediction value corresponding to the theoretical fracture speed are input into the trained strain prediction surrogate model for analysis. The fracture speed corresponding to each sample point and the maximum strain prediction value is calculated. Then, the maximum and minimum values ​​of the fracture speed are statistically determined. Based on the maximum and minimum values, the fracture speed range of the target disk when considering the uncertainty parameters is determined. The theoretical fracture speed and fracture speed range of the target disk are output as the prediction results.

[0027] Compared with the prior art, the beneficial effects of this invention are:

[0028] This invention utilizes a strain prediction surrogate model for analysis and calculation, improving the accuracy and efficiency of predicting the fracture speed of a wheel disk. By replacing the traditional finite element method with a strain prediction surrogate model, this invention eliminates the need for extensive simulation models of wheel disk over-rotation fracture. Only a small number of sample points require finite element calculations to quickly output strain prediction results under any operating condition, resulting in high computational efficiency, low computational cost, and the ability to meet real-time computational requirements. Furthermore, this invention considers the influence of uncertain parameters on the wheel disk's fracture behavior, predicting the fracture speed range under the influence of these uncertain parameters. This improves the accuracy and reliability of fracture speed prediction, providing a more scientific basis for the design and optimization of the wheel disk. Attached Figure Description

[0029] Figure 1 This is a flowchart of the wheel over-rotation fracture speed prediction method based on the surrogate model in the embodiment. Detailed Implementation

[0030] The present invention will now be described in further detail with reference to the embodiments and accompanying drawings. However, this should not be construed as limiting the scope of the above-described subject matter of the present invention to the following embodiments; all technologies implemented based on the content of the present invention fall within the scope of the present invention.

[0031] Example 1

[0032] See Figure 1 A method for predicting the over-rotation fracture speed of a chariot based on a surrogate model, comprising:

[0033] The theoretical fracture strain value and material parameters of the target wheel material are determined, and a finite element analysis model of the wheel is established; the material parameters include the density, Poisson's ratio, elastic modulus and material plasticity data of the target wheel.

[0034] Uncertainty parameters affecting the maximum strain value of the wheel are obtained, and key parameters are screened from these uncertainty parameters through sensitivity analysis. The key parameters include key dimensional parameters, elastic modulus, Poisson's ratio, material plasticity data, and rotational speed.

[0035] Based on the key parameters, an optimized Latin hypercube sampling method is used to generate several initial sample points in the design space; each initial sample point is input into the finite element analysis model for simulation to obtain the maximum strain analysis value of the disk at the corresponding rotational speed for each initial sample point; with the key parameters of all initial sample points as input and the maximum strain analysis value corresponding to each initial sample point as output, the Kriging model is used to construct the initial strain prediction proxy model of the disk.

[0036] The Latin hypercube sampling method is used to perform sequential point addition, generating training sample points within the design space of the key parameters. The training sample points are then input into the finite element analysis model for simulation to obtain the maximum strain analysis value corresponding to the training sample points. The initial strain prediction surrogate model is trained and reconstructed using the training sample points and the initial sample points. The accuracy of the reconstructed strain prediction surrogate model is then verified. If the reconstructed strain prediction surrogate model meets the accuracy requirements, a trained strain prediction surrogate model is obtained; otherwise, sequential point addition is performed again until a trained strain prediction surrogate model is obtained.

[0037] The trained strain prediction surrogate model is corrected, and then the strain prediction surrogate model is used to predict the fracture speed of the disk, so as to obtain the theoretical fracture speed of the disk and the fracture speed range under the influence of uncertainty parameters.

[0038] This invention utilizes a strain prediction surrogate model for analysis and calculation, improving the accuracy and efficiency of predicting the fracture speed of a wheel disk. By replacing the traditional finite element method with a strain prediction surrogate model, this invention eliminates the need for extensive simulation models of wheel disk over-rotation fracture. Only a small number of sample points require finite element calculations to quickly output strain prediction results under any operating condition, resulting in high computational efficiency, low computational cost, and the ability to meet real-time computational requirements. Furthermore, this invention considers the influence of uncertain parameters on the wheel disk's fracture behavior, predicting the fracture speed range under the influence of these uncertain parameters. This improves the accuracy and reliability of fracture speed prediction, providing a more scientific basis for the design and optimization of the wheel disk.

[0039] Example 2

[0040] To illustrate this invention in detail, a certain type of roulette wheel is used as the target roulette wheel. To predict the fracture speed of the target roulette wheel, the following are the specific steps of the roulette wheel over-rotation fracture speed prediction method based on a surrogate model according to this invention, including:

[0041] Step 1: Determine the theoretical fracture strain value and material parameters of the target wheel material; and establish a finite element analysis model of the target wheel based on the theoretical values ​​of its geometric dimensions and material parameters; the material parameters include the density, Poisson's ratio, elastic modulus, and material plasticity data of the target wheel.

[0042] Specifically, firstly, several tensile specimens are made using raw materials from different production batches of the target wheel. Material property tests are conducted on each specimen to obtain the engineering stress and strain measurements. Then, the average engineering stress and strain measurements are calculated, and the material's engineering stress-strain curve for the target wheel is plotted. The engineering stress-strain curve is then converted into a true stress-true strain curve using the following formula:

[0043] ;

[0044] in, To be truly adaptable; The length of the sample at a certain moment; This is the original gauge length of the sample; For engineering contingency;

[0045] ;

[0046] in, For engineering stress, This is the true stress.

[0047] By reading the strain value at the time of fracture from the true stress-true strain curve of the target wheel material, the theoretical fracture strain value of the target wheel material can be obtained.

[0048] The Poisson's ratio and elastic modulus of each tensile specimen were tested using a universal testing machine. The maximum and minimum values ​​of the Poisson's ratio and elastic modulus were then used as the range of Poisson's ratio and elastic modulus of the target disc, respectively. At the same time, the density of each tensile specimen was measured, and the maximum and minimum values ​​of the density were used as the range of density of the target disc.

[0049] Then, based on the measured engineering stress and strain values ​​obtained for each tensile specimen, the true stress and true strain of each tensile specimen are obtained. These are then input into a material plasticity data function to obtain the material plasticity data for each tensile specimen. The expression is as follows:

[0050] ;

[0051] in, This refers to material plasticity data; The measured engineering stress value of the tensile specimen; This represents the true strain of the tensile specimen. Calculate the material plasticity data for all tensile specimens. The average value was taken as the theoretical value of the material plasticity data of the target wheel, and the material plasticity data of all tensile specimens were statistically analyzed. The maximum and minimum values ​​in the data are used as the plasticity data of the target wheel material. The upper and lower limits of the value are used to determine the range of values ​​for the plasticity data of the target wheel material.

[0052] Finally, based on the design drawings and other relevant design data of the target roulette wheel, the theoretical values ​​of its geometric dimensions and material parameters are obtained. A finite element analysis model of the target roulette wheel is then established based on these theoretical values. It should be noted that the theoretical geometric dimensions are the basic dimensions in the design drawings without considering tolerances, and the theoretical material parameters are the Poisson's ratio and elastic modulus of the target roulette wheel's material, obtained by looking up tables.

[0053] Step 2: Obtain the uncertainty parameters that affect the maximum strain value of the wheel, and use the uncertainty parameters as key parameters through sensitivity analysis. The uncertainty parameters include size parameters, material parameters and load parameters. The key parameters include key size parameters, elastic modulus, Poisson's ratio, material plasticity data and rotational speed.

[0054] Specifically, traditional methods for analyzing the structural performance of wheel disks typically assume that the material properties and geometric parameters of the disk are deterministic constants, meaning they do not change with time or conditions throughout the analysis process. However, during the design and manufacturing stages of the wheel disk, the material itself inevitably exhibits a certain degree of non-uniformity; for example, material parameters such as elastic modulus and density fluctuate between different batches. Furthermore, due to limitations in current manufacturing processes, it is difficult to achieve consistent replication of all wheel disks. Even wheel disks from the same production batch exhibit a certain range of random distribution in their structural dimensions and material parameters. These multi-source uncertainties significantly affect the fracture behavior characteristics of the wheel disk, causing the critical fracture speed to exhibit obvious dispersion and fluctuation range, rather than a single deterministic value. Therefore, this invention considers the uncertainties of the wheel disk when predicting its fracture speed, systematically reflecting the impact of uncertainties on the structural response and over-rotation fracture behavior of the wheel disk. The specific steps are as follows:

[0055] Step 2.1: Obtain the uncertainty parameters affecting the maximum strain value of the target wheel. These uncertainty parameters include the dimensional parameters, material parameters, and load parameters of the target wheel. This embodiment considers the geometric uncertainty of the wheel from the perspective of its dimensional tolerance. First, a 3D scan is performed on each tensile specimen. Based on the 3D scan data, the values ​​of each dimensional parameter on different tensile specimens are statistically analyzed, and the maximum and minimum values ​​are determined. This yields the numerical fluctuation range of each dimensional parameter of the target wheel. Dimensional parameters with fluctuation ranges greater than a preset threshold are then selected. The statistically obtained numerical fluctuation range is used as the range of values ​​for the selected dimensional parameters. For example, based on the 3D scan data, after statistical filtering, the following values ​​are obtained: C 1. C 2. C 3. C 4. C 5. C 6. C 7. C 8 These are 8 size parameters whose fluctuation range exceeds a preset threshold, which is set based on experience.

[0056] Meanwhile, this embodiment will determine the density of the target roulette wheel. ρ Elastic modulus E Poisson's ratio B、 Material plasticity data k Material parameters, including rotational speed, are included as uncertain parameters. S The load parameter is one of the uncertain parameters. Among them, the rotational speed... S The range of values ​​is set manually based on experience and needs to cover the design operating speed and estimated fracture speed of the target wheel. The estimated fracture speed can be determined based on experience or experiments.

[0057] Step 2.2: Perform sensitivity analysis using a global sensitivity analysis method to select key parameters from the uncertainty parameters whose sensitivity to the maximum strain value of the target wheel is greater than a preset sensitivity threshold. Specifically, use an optimized Latin hypercube sampling method to randomly generate 200 sensitivity analysis sample points within the design space. Each sensitivity analysis sample point consists of a set of the aforementioned uncertainty parameters, i.e., each sensitivity analysis sample point includes a set of { C 1, C 2, C 3, C 4, C 5, C 6, C 7, C 8, ρ , B , E , SThe design space is the range of values ​​for each uncertainty parameter, and the same applies below. Then, the uncertainty parameter of each sensitivity analysis sample point is used as input, and the finite element analysis model is used for analysis to obtain the rotational speed of the target wheel at each sample point. S The maximum strain value is obtained for each sensitivity analysis sample point. A high-precision mapping relationship between the uncertainty parameters and the maximum strain value of the wheel is then constructed using the Kriging surrogate model. The main effect sensitivity index of each uncertainty parameter is evaluated using the Sobol variance decomposition method combined with Monte Carlo sampling technology. Finally, uncertainty parameters whose main effect sensitivity index exceeds a preset sensitivity threshold are selected as key parameters. The key parameters in this embodiment include { C 2, C 3, C 7, C 8, B , E , k , S},in{ C 2, C 3, C 7, C 8} represents the key dimensional parameters selected. It should be noted that the uncertainty parameters of the sensitivity analysis sample points are input into the finite element analysis model for analysis to obtain the target disk at the corresponding rotational speed. S The maximum strain value in the strain field is the maximum strain analysis value.

[0058] Step 3: Based on the selected key parameters, an optimized Latin hypercube sampling method is used to generate several initial sample points within the design space. Each initial sample point includes a set of key parameters { C 2, C 3, C 7, C 8, B , E , k , S Each initial sample point is input into the finite element analysis model for simulation to obtain the value of each initial sample point at the corresponding rotational speed. S The maximum strain analysis value of the target wheel is obtained. Using the key parameters of all initial sample points as input and the maximum strain analysis value corresponding to each initial sample point as output, the Kriging model is used to construct the initial strain prediction surrogate model of the target wheel.

[0059] Step 4: Using the Latin hypercube sampling method, sequential point addition is performed to generate training sample points within the design space of the key parameters. These training sample points are then input into the finite element analysis model for simulation to obtain the maximum strain analysis value corresponding to each training sample point. The initial strain prediction surrogate model is then trained and reconstructed using the training sample points and the initial sample points. The accuracy of the reconstructed strain prediction surrogate model is then verified. If the reconstructed strain prediction surrogate model meets the accuracy requirements, a trained strain prediction surrogate model is obtained; otherwise, sequential point addition is performed again until a trained strain prediction surrogate model is obtained. Specifically, this includes the following steps:

[0060] Step 4.1: Use the Latin hypercube sampling method to generate a training sample point in the design space of the key parameters, input the key parameters contained in the training sample point into the finite element analysis model for simulation, and obtain the maximum strain analysis value corresponding to the training sample point.

[0061] Step 4.2: Using the key parameters of the training sample points and the initial sample points as input, and the maximum strain analysis value corresponding to the training sample points and the initial sample points as output, reconstruct the strain prediction proxy model using the Kriging model. Then, input the key parameters of the training sample points into the reconstructed strain prediction proxy model to obtain the maximum strain prediction value corresponding to the training sample points. Next, calculate the root mean square error between the maximum strain prediction value and the maximum strain analysis value of the training sample points. If the root mean square error is less than a preset error threshold, the prediction accuracy of the reconstructed strain prediction proxy model is considered to meet the preset accuracy requirement, and a trained strain prediction proxy model is obtained. Otherwise, repeat step 4.1 to add points sequentially and regenerate a training sample point until a trained strain prediction proxy model is obtained.

[0062] It should be noted that the strain field of the target compressor integral bladed disk output by the finite element analysis model in this invention at the corresponding rotational speed is used to extract the maximum strain value as the maximum strain analysis value. Similarly, the strain prediction proxy model in this invention also outputs the strain field of the target compressor integral bladed disk at the corresponding rotational speed, and extracts the maximum strain value as the maximum strain prediction value.

[0063] Step 5: Correct the trained strain prediction surrogate model.

[0064] The strain prediction proxy model is modified. Specifically, the theoretical values ​​of the target wheel's key geometric parameters, elastic modulus, Poisson's ratio, material plasticity data, and multiple different test speeds are input into the trained strain prediction proxy model to obtain the strain field of the target wheel at each test speed. Several test points are selected on the target wheel, and the predicted strain value corresponding to each test point is read from the strain field. Then, an over-rotation test is performed on the test points on a tensile specimen to obtain the measured strain value, i.e., the true strain value, at each test point. Calculate the correction factor for each test point. ,in, For the tensile specimen, the first Correction coefficients for each test point For the tensile specimen, the first The true strain value at each test point For the tensile specimen, the first The strain prediction values ​​for each test point are calculated. Finally, the average of the correction factors for all test points is calculated. And used as a correction coefficient for the target roulette wheel. Then, the strain prediction surrogate model is compared with the correction coefficient. Multiplying these results yields the corrected strain prediction surrogate model. Through these correction methods, the prediction results of the strain prediction surrogate model can be systematically adjusted, thus getting closer to the actual experimental values ​​and reducing prediction errors.

[0065] Step Six: Utilize the strain prediction surrogate model to predict the fracture speed of the target disk, obtaining the predicted fracture speed result. Specifically, this includes:

[0066] Step 6.1: Input the theoretical values ​​of the target wheel's key geometric parameters, elastic modulus, Poisson's ratio, and material plasticity data into the trained strain prediction proxy model, and input the first and second initial test speeds. Both the first and second initial test speeds are within the range of rotational speeds. S Within the range of values, the first initial test speed must be less than the predicted fracture speed of the target wheel based on experience, and the second initial test speed must be greater than the predicted fracture speed of the target wheel based on experience. Then, the first and second initial test speeds are input into the trained strain prediction proxy model for analysis to obtain the first and second maximum strain prediction values ​​of the target wheel, respectively. The difference between the minimum of the first and second maximum strain prediction values ​​and the theoretical fracture strain of the target wheel is calculated. If the difference is less than a preset difference range, the corresponding test speed is taken as the predicted theoretical fracture speed of the target wheel; otherwise, the test speed is adjusted and updated using a bisection method to obtain the theoretical fracture speed of the target wheel.

[0067] Step 6.2: Use the Monte Carlo sampling method to measure the key dimensional parameters and elastic modulus. E Poisson's ratio B Sampling was conducted within the design space to generate 1000 sample points. Each sample point includes a set of key dimensional parameters, elastic modulus, and Poisson's ratio, i.e., { C 2, C 3, C 7, C 8, B , E The maximum strain prediction value corresponding to each sample point and the theoretical fracture speed is input into the trained strain prediction proxy model for analysis. The fracture speed corresponding to each sample point and the maximum strain prediction value is calculated. Then, the maximum and minimum values ​​of the fracture speed are statistically determined. Based on the maximum and minimum values, the fracture speed range of the target disk when considering the uncertainty parameters is determined. The theoretical fracture speed and fracture speed range of the target disk are output as the prediction results.

[0068] This invention predicts the theoretical fracture speed based on the theoretical values ​​of relevant parameters of the target wheel, and also considers the influence of uncertain parameters on the wheel's fracture behavior. By introducing uncertain parameters such as key dimensional parameters, elastic modulus, and Poisson's ratio, it predicts the fracture speed range under the influence of these uncertain parameters. Compared with traditional prediction methods based solely on deterministic parameters, this invention can more comprehensively and realistically reflect the fracture speed that the target wheel may experience in actual operation, improving the accuracy and reliability of fracture speed prediction, and providing a more scientific and reasonable basis for the design, operation, and maintenance of the wheel.

[0069] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for predicting the over-rotation fracture speed of a chariot based on a surrogate model, characterized in that, include: The theoretical fracture strain value and material parameters of the target wheel material are determined, and a finite element analysis model of the wheel is established; the material parameters include the density, Poisson's ratio, elastic modulus and material plasticity data of the target wheel. Uncertainty parameters affecting the maximum strain value of the wheel are obtained, and key parameters are screened from these uncertainty parameters through sensitivity analysis. The key parameters include key dimensional parameters, elastic modulus, Poisson's ratio, material plasticity data, and rotational speed. Based on the key parameters, an optimized Latin hypercube sampling method is used to generate several initial sample points in the design space. Each initial sample point is input into the finite element analysis model for simulation to obtain the maximum strain analysis value of the disk at the corresponding rotation speed for each initial sample point. Using the key parameters of all initial sample points as input and the maximum strain analysis value corresponding to each initial sample point as output, the Kriging model is used to construct the initial strain prediction surrogate model for the wheel. The Latin hypercube sampling method is used to perform sequential point addition, generating training sample points within the design space of the key parameters. The training sample points are then input into the finite element analysis model for simulation to obtain the maximum strain analysis value corresponding to the training sample points. The initial strain prediction surrogate model is trained and reconstructed using the training sample points and the initial sample points. The accuracy of the reconstructed strain prediction surrogate model is then verified. If the reconstructed strain prediction surrogate model meets the accuracy requirements, a trained strain prediction surrogate model is obtained; otherwise, sequential point addition is performed again until a trained strain prediction surrogate model is obtained. The trained strain prediction surrogate model is corrected, and then the strain prediction surrogate model is used to predict the fracture speed of the disk, so as to obtain the theoretical fracture speed of the disk and the fracture speed range under the influence of uncertainty parameters.

2. The method for predicting the over-rotation fracture speed of a wheel according to claim 1, characterized in that, The uncertainty parameters include dimensional parameters, material parameters, and load parameters.

3. The method for predicting the over-rotation fracture speed of a wheel according to claim 2, characterized in that, The steps for determining the theoretical fracture strain value of the target wheel material include: Several tensile specimens were made from raw materials from different production batches of the target wheel. Material property tests were conducted on each tensile specimen. Based on the measured values ​​of engineering stress and engineering strain obtained from the tests, the material engineering stress-engineering strain curve of the target wheel was plotted. The material's engineering stress-engineering strain curve is converted into a true stress-true strain curve, and the theoretical fracture strain value of the target wheel material is read from the true stress-true strain curve.

4. The method for predicting the over-rotation fracture speed of a wheel according to claim 3, characterized in that, The steps for determining the material parameters of the target wheel include: The Poisson's ratio and elastic modulus of each tensile specimen were tested using a universal testing machine. The maximum and minimum values ​​of the Poisson's ratio and elastic modulus were then used as the range of Poisson's ratio and elastic modulus of the target disc, respectively. At the same time, the density of each tensile specimen was measured, and the maximum and minimum values ​​of the density were used as the range of density of the target disc. Based on the engineering stress and engineering strain measurements obtained from the material property tests of each tensile specimen, the true stress and true strain of each tensile specimen are obtained. Then, the data are input into the material plasticity data function to obtain the material plasticity data of each tensile specimen. The average value of the material plasticity data of all tensile specimens is calculated and used as the theoretical value of the material plasticity data of the target wheel. The maximum and minimum values ​​of the material plasticity data of all tensile specimens are statistically analyzed to determine the range of values ​​for the material plasticity data of the target wheel.

5. The method for predicting the over-rotation fracture speed of a wheel according to claim 4, characterized in that, The expression for the material plasticity data function is: ； in, This refers to material plasticity data; The measured engineering stress value of the tensile specimen; This represents the true strain of the tensile specimen.

6. The method for predicting the over-rotation fracture speed of a wheel according to claim 5, characterized in that, Using the key parameters of the training sample points and the initial sample points as input, and the maximum strain analysis value corresponding to the training sample points and the initial sample points as output, a strain prediction surrogate model is reconstructed using the Kriging model. Then, the key parameters of the training sample points are input into the reconstructed strain prediction surrogate model to obtain the maximum strain prediction value corresponding to the training sample points. The root mean square error between the maximum strain prediction value and the maximum strain analysis value of the training sample points is then calculated. If the root mean square error is less than a preset error threshold, the prediction accuracy of the reconstructed strain prediction surrogate model is considered to meet the preset accuracy requirement, and a trained strain prediction surrogate model is obtained. Otherwise, the sequence of points is repeated to regenerate a training sample point until a trained strain prediction surrogate model is obtained.

7. The method for predicting the over-rotation fracture speed of a wheel according to claim 6, characterized in that, The steps for predicting the fracture speed of the disk using the strain prediction surrogate model, and obtaining the theoretical fracture speed and the fracture speed range under the influence of uncertainty parameters, include: The theoretical values ​​of the target wheel's key geometric parameters, elastic modulus, Poisson's ratio, and material plasticity data are input into the trained strain prediction proxy model. A first initial test speed and a second initial test speed are also input. These initial test speeds are then analyzed within the trained strain prediction proxy model to obtain the first and second maximum strain prediction values ​​for the target wheel. The difference between the minimum of the first and second maximum strain prediction values ​​and the theoretical fracture strain of the target wheel is calculated. If the difference is less than a preset range, the corresponding test speed is used as the predicted theoretical fracture speed of the target wheel. Otherwise, a bisection method is used to adjust and update the test speed to obtain the theoretical fracture speed of the target wheel.

8. The method for predicting the over-rotation fracture speed of a wheel according to claim 7, characterized in that, The step of using the strain prediction surrogate model to predict the fracture speed of the disk and obtain the theoretical fracture speed and the fracture speed range under the influence of uncertainty parameters further includes: The Monte Carlo sampling method is used to sample within the design space of the key dimensional parameters, elastic modulus, and Poisson's ratio, generating several sample points. Each sample point and the maximum strain prediction value corresponding to the theoretical fracture speed are input into the trained strain prediction surrogate model for analysis. The fracture speed corresponding to each sample point and the maximum strain prediction value is calculated. Then, the maximum and minimum values ​​of the fracture speed are statistically determined. Based on the maximum and minimum values, the fracture speed range of the target disk when considering the uncertainty parameters is determined. The theoretical fracture speed and fracture speed range of the target disk are output as the prediction results.

Images