High-temperature component reliability interval evaluation method, device, equipment, medium and product

Abstract

The invention discloses a high-temperature component reliability interval assessment method, device, equipment, medium and product, and relates to the technical field of reliability assessment, the method comprises the following steps: carrying out probability damage assessment on a high-temperature component to obtain stress and strain probability distribution of a dangerous point of the high-temperature component; constructing and training a plurality of physical information neural network models by taking the creep fatigue test conditions of the high-temperature part as input and the test life as output; according to the life prediction result of each physical information neural network model, constructing a life prediction interval and basic trust distribution of each model; carrying out fusion through a Dempster method to obtain a fusion life prediction interval; according to the fused life prediction interval and the stress and strain probability distribution, a reliability interval evaluation result of the life of the high-temperature component is obtained, the model uncertainty brought by the selected model is considered, and the method has the advantages of being high in prediction precision, high in engineering applicability and good in physical interpretation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of reliability evaluation, in particular to a high-temperature component reliability interval evaluation method, device, equipment, medium and product. BACKGROUND

[0002] With the complication and extremization of long-term service conditions of high-temperature rotating mechanical components such as steam turbines and gas turbines, accurate evaluation of the reliability of high-temperature rotating mechanical components has become a key problem to ensure safe and reliable operation of equipment. In the reliability evaluation process, the traditional method often only relies on a single model to give point estimates, ignoring the uncertainty differences between different models, which can easily lead to distorted results. How to effectively characterize and fuse model uncertainty and construct a more robust reliability evaluation method to provide reliable basis for safety analysis and maintenance strategy optimization of high-temperature rotating mechanical components is an important problem to be solved at present.

[0003] In creep-fatigue life prediction, the traditional physical method is simple and easy to use, and has strong generalization ability, but the fitting and prediction accuracy is not high; the data model has high prediction accuracy, but is highly dependent on the quality of the data set, and may appear in the prediction process. The prediction of the anti-physical law. Physical-data model has high accuracy and good generalization ability, and has physical interpretability. However, no matter which kind of model can only give point estimates of life prediction, and cannot reflect the uncertainty of the prediction value, and is easily affected by extreme data, which further limits the accuracy of reliability evaluation. SUMMARY

[0004] The purpose of the present application is to provide a high-temperature component reliability interval evaluation method, device, equipment, medium and product, which can better realize the reliability evaluation of high-temperature rotating mechanical components, and has the advantages of high prediction accuracy, strong engineering applicability and good physical interpretability.

[0005] To achieve the above-mentioned purpose, the present application provides the following solutions: In a first aspect, the present application provides a high-temperature component reliability interval evaluation method, comprising: Performing probability damage assessment on the high-temperature component to obtain the stress and strain probability distribution of the dangerous point of the high-temperature component.

[0006] Constructing and training a plurality of physical information neural network models with the creep-fatigue test conditions of the high-temperature component as input and the test life as output; the physical information neural network model includes a fatigue life prediction model and a creep life prediction model.

[0007] According to the life prediction results of each physical information neural network model, the life prediction interval and basic trust distribution of each model are constructed.

[0008] Based on the lifetime prediction intervals and basic trust assignments of each model, the Dempster method is used to fuse them to obtain the fused lifetime prediction interval.

[0009] Based on the fusion life prediction range and the stress and strain probability distribution, the reliability range assessment results of the high-temperature component life are obtained.

[0010] Secondly, this application provides a high-temperature component reliability interval assessment device, including: a probabilistic damage assessment module, a model training module, an interval construction and trust allocation module, a fusion module, and a reliability interval assessment module.

[0011] The probabilistic damage assessment module is used to perform probabilistic damage assessment on high-temperature components and obtain the stress and strain probability distribution at the critical points of the high-temperature components.

[0012] The model training module is used to construct and train multiple physical information neural network models with the creep fatigue test conditions of high-temperature components as input and the test life as output; the physical information neural network models include fatigue life prediction models and creep life prediction models.

[0013] The interval construction and trust allocation module is used to construct the lifetime prediction interval and basic trust allocation for each model based on the lifetime prediction results of each physical information neural network model.

[0014] The fusion module is used to fuse the lifetime prediction intervals and basic trust assignments of each model using the Dempster method to obtain the fused lifetime prediction interval.

[0015] The reliability range assessment module is used to obtain the reliability range assessment results of the high-temperature component life based on the fusion life prediction range and the stress and strain probability distribution.

[0016] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the high-temperature component reliability range assessment method described in any one of the above.

[0017] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the high-temperature component reliability range assessment method described above.

[0018] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the high-temperature component reliability range assessment method described above.

[0019] According to the specific embodiments provided in this application, the following technical effects are disclosed: This application provides a method, apparatus, equipment, medium, and product for assessing the reliability range of high-temperature components. By obtaining the stress and strain probability distributions at critical points of high-temperature components instead of single, deterministic values, the engineering practicality and decision robustness of the assessment method are significantly improved. Multiple physical information neural network models are constructed and trained, taking into account the cognitive uncertainty caused by different models, to conduct a comprehensive reliability analysis. Based on the lifetime prediction ranges and basic trust assignments of each model, they are fused using the Dempster method to obtain a fused lifetime prediction range. Cognitive uncertainty is quantified using Dempster's evidence theory. Based on the fused lifetime prediction range and the stress and strain probability distributions, the reliability range assessment result for the lifetime of the high-temperature component is obtained. The obtained reliability range assessment result covers the real situation better than traditional point estimation, reducing the risk of misjudgment due to ignoring cognitive uncertainty, making the assessment result more comprehensive and realistic. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 A flowchart illustrating a method for evaluating the reliability range of a high-temperature component, provided in an embodiment of this application; Figure 2 A detailed flowchart illustrating a high-temperature component reliability range assessment method provided in an embodiment of this application; Figure 3 A schematic diagram of the finite element model mesh generation of a steam turbine rotor provided in an embodiment of this application; Figure 4 This is a finite element displacement cloud diagram of a steam turbine rotor provided in an embodiment of this application; Figure 5 The following is a scatter plot of a material creep fatigue test dataset provided in an embodiment of this application; wherein, (a) is the scatter plot distribution of the strain range, (b) is the scatter plot distribution of the plastic strain range, (c) is the scatter plot distribution of the stress range, (d) is the scatter plot distribution of the average stress, (e) is the scatter plot distribution of the strain rate, (f) is the scatter plot distribution of the tensile holding time, and (g) is the scatter plot distribution of the compressive holding time. Figure 6 This is a schematic diagram of the interval reliability assessment results provided in an embodiment of this application; Figure 7 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0022] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0023] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0024] First, the technical terms involved in the embodiments of this application will be introduced.

[0025] The input to life prediction models in related technologies is generally test conditions or operating conditions, and the output is generally the predicted life. However, creep fatigue life has a very high degree of dispersion; even under the same test conditions or operating conditions, the actual life can vary greatly. Therefore, the predicted single-value life cannot be completely accurate, and there is a certain degree of uncertainty between it and the actual life. This application mainly uses a combination of physical information neural networks and evidence theory to reflect this uncertainty. Among them, physical information neural networks are a data-physical driven life prediction method, while evidence theory is a means of quantifying cognitive uncertainty.

[0026] In one exemplary embodiment, such as Figure 1 As shown, a method for evaluating the reliability range of high-temperature components is provided, including the following steps 201 to 205. Wherein: Step 201: Perform probabilistic damage assessment on the high-temperature component to obtain the stress and strain probability distribution at the critical points of the high-temperature component.

[0027] Step 202: Using the creep fatigue test conditions of high-temperature components as input and the test life as output, construct and train multiple physical information neural network models; the physical information neural network models include fatigue life prediction models and creep life prediction models.

[0028] To avoid high testing costs, the creep fatigue test conditions in this application are based on high-temperature components at the material level. The stress and strain at the critical point are calculated based on the finite element model. The area around the critical point is treated as a continuous medium, and a material-level life prediction model is applied for prediction.

[0029] Step 203: Based on the lifetime prediction results of each physical information neural network model, construct the lifetime prediction range and basic trust allocation for each model.

[0030] Step 204: Based on the lifetime prediction intervals and basic trust assignments of each model, the models are fused using the Dempster method to obtain the fused lifetime prediction interval.

[0031] Step 205: Based on the fusion life prediction range and the stress and strain probability distribution, obtain the reliability range assessment results of the high-temperature component life.

[0032] By implementing steps 201 to 205 above, the engineering practicality and decision robustness of the assessment method are significantly improved by obtaining the stress and strain probability distributions at the critical points of high-temperature components instead of single, definite values. Multiple physical information neural network models are constructed and trained, taking into account the cognitive uncertainty caused by different models, to conduct a comprehensive reliability analysis. Based on the life prediction intervals and basic trust assignments of each model, they are fused using the Dempster method to obtain a fused life prediction interval. Cognitive uncertainty is quantified using Dempster's evidence theory. Based on the fused life prediction interval and the stress and strain probability distributions, the reliability interval assessment result for the life of the high-temperature component is obtained. The obtained reliability interval assessment result covers the real situation better than traditional point estimation, reducing the risk of misjudgment due to ignoring cognitive uncertainty, making the assessment result more comprehensive and realistic.

[0033] In another exemplary embodiment of this application, step 201 is replaced by steps 301 to 305: Step 301: Establish a three-dimensional finite element model based on the structural characteristics of the high-temperature component.

[0034] Step 302: Latin hypercube sampling is used to extract multiple sets of parameter combinations from the model parameters of the three-dimensional finite element model, and finite element simulations are performed on each combination to obtain the stress and strain response of the high-temperature component at the critical point under different parameter combinations.

[0035] Step 303: Using the parameter combination of the finite element simulation as input and the stress and strain response of the danger point as output, train the surrogate model to obtain the trained surrogate model.

[0036] Step 304: Obtain multiple combinations of random parameters through Latin hypercube sampling.

[0037] Step 305: Using Monte Carlo simulation based on the trained surrogate model, calculate the stress and strain response of the critical point under multiple random parameter combinations obtained by Latin hypercube sampling, and obtain the stress and strain probability distribution of the critical point.

[0038] The probabilistic damage assessment of high-temperature components (specifically, high-temperature rotating machinery components, such as steam turbine components) in this application includes: S11: Establish a high-fidelity finite element model, assuming that the model parameters follow a probability distribution, obtain different combinations of model parameters through Latin hypercube sampling, and perform finite element simulation.

[0039] Optionally, the finite element model in this application is generally a thermo-mechanical coupling model of the component established using ABAQUS software. The parameters of the (finite element) model include, but are not limited to: material property parameters, temperature, rotational speed, geometric dimensions, and external load.

[0040] S12: Based on the finite element simulation results, a surrogate model is trained, which can quickly calculate the stress / strain response at the critical point using the model's parameters.

[0041] Optionally, the surrogate model refers to a general interpolation regression method, including but not limited to: neural network models, support vector machine regression, and Gaussian process regression.

[0042] S13: Through Monte Carlo simulation, the stress / strain of the system under a large number of random combinations of model parameters is calculated, and the stress / strain probability distribution of the critical point under this working condition is obtained.

[0043] The training of the physical information neural network model in this application includes: S21: Data preprocessing, physical equation parameter prefitting, construction of physical loss function, and initialization of model hyperparameters.

[0044] The data preprocessing mainly involves dividing the data into training and testing sets, which are used for training and verification of the physical information neural network, respectively. The processed data consists of stress and strain responses output from finite element simulations (e.g., stress, strain, plastic strain, temperature, etc.).

[0045] Model hyperparameters include, but are not limited to: learning rate, Dropout probability, regularization weights, physical loss weights, and Adamw optimizer weights.

[0046] The physical equations refer to the fatigue life equation and the creep life equation. The fatigue life equation includes, but is not limited to, the Manson-Coffin equation, the Morrow equation, and the Ostergren equation. The creep life equation includes, but is not limited to, the time fraction method and the ductile exhaustion method.

[0047] S22: The neural network propagates forward to calculate the data loss and physical loss, and then propagates backward until convergence.

[0048] The physical loss function is expressed as follows: .

[0049] .

[0050] in, For physical loss, For the sample size, To predict creep fatigue life using neural networks, Predicting creep fatigue life using physical equations and These represent creep damage and fatigue damage calculated from the physical equations, respectively.

[0051] The total loss of the physical information neural network model is: .

[0052] in, The total loss of the physical information neural network model is... For data loss function, For physical loss function, These are the weights of the physical loss function.

[0053] S23: Bayesian optimization until the maximum number of iterations is reached, and output the optimal model parameters (i.e., the optimal model hyperparameters obtained according to the optimization objective function).

[0054] The Bayesian optimization objective function is: .

[0055] in, To optimize the objective function using Bayesian methods, The coefficient of determination for the test set. The coefficient of determination for the training set is denoted by , and the objective function takes values ​​of [-1, 1]. A larger value indicates better generalization ability of the model.

[0056] The evidence-based lifespan assessment in this application includes: S31: Construct lifetime prediction intervals and basic trust assignments based on the results of cross-validation of the physical information neural network model.

[0057] The cross-validation described above is the model evaluation process, and the results of cross-validation are used here. For each physical information neural network with different physical constraints trained, a five-fold cross-validation result can be obtained. Based on this result, a model can be constructed to predict the lifetime prediction interval and basic confidence assignment for each input condition. The model used for cross-validation here is the model with the best model hyperparameters, that is, the best model obtained through training.

[0058] S32: Fuse the prediction results of two models using Dempster's rule, and then continue to fuse new model prediction results using the fused model prediction results until all model prediction results are fused. S33: Based on the stress and strain at the critical point obtained by finite element method, the life range of the component under this working condition is evaluated.

[0059] In another exemplary embodiment of this application, the calculation formula for the lifetime prediction interval is: in, For the first The lifetime prediction range of each model. For the first The lower bound of the lifetime prediction range for each model. For the first The upper limit of the lifetime prediction range for each model. for Quantiles For 1- Quantiles For confidence quantile parameters, These are the input parameters for the physical information neural network model. Number the model. For cross-validation folds, The total number of folds for cross-validation. For the first The model has input parameters On The set of prediction results from cross-validation.

[0060] This application uses a given confidence quantile parameter (or confidence level). Obtain quantiles; calculate the upper limit of the lifespan prediction interval. and the lower limit of the life prediction range The lifespan prediction range is obtained. (or model prediction interval).

[0061] In another exemplary embodiment of this application, the calculation formula for the basic trust allocation is: .

[0062] in, For the first i The basic trust assignment function of the model, For the first The lifetime prediction range of each model. For the first The credibility weights of each model For the first The model score of each model. Number the model. For the first The dimensionless error index of the model To control the parameters of the model score discrimination, For the first The model error index of each model. and They are respectively j The minimum and maximum error indices in each model.

[0063] This application is based on the dimensionless model error index. Convert to model score , score the model Normalized to model confidence weights Based on the model's credibility weights Constructing the basic trust allocation for each model .

[0064] In another exemplary embodiment of this application, step 204 is replaced by steps 401 to 404: Step 401: Calculate the conflict factor based on the basic trust allocation. The formula for calculating the conflict factor is as follows: .

[0065] in, As a conflict factor, To identify a subset of the frame, i.e., the model a Lifespan prediction range , For another subset of the identification framework, namely the model b Lifespan prediction range , For the model a Basic trust allocation, For the model b The basic trust allocation.

[0066] Step 402: According to Dempster's rule, the basic trust assignments of each model are merged one by one until all models are merged, resulting in the merged basic trust assignments. The calculation formula for the merged basic trust assignments is as follows: .

[0067] in, For the allocation of basic trust after integration, For the first The basic trust allocation of each model =1, 2, ..., , To identify any subset within the frame, This is the Dempster fusion operator.

[0068] Step 403: Perform a Pignistic transformation on the fused basic trust allocation to obtain the Pignistic probability distribution of the predicted lifetime. The formula for calculating the Pignistic probability distribution of the predicted lifetime is as follows: .

[0069] in, For the Pignistic probability, For the interval [ c 1 ,c 2], The lower bound of the interval, The upper bound of the interval is... For set M The basic trust allocation.

[0070] Step 404: Based on the preset confidence level, determine the fusion lifetime prediction interval from the Pignistic probability distribution.

[0071] This application allocates basic trust based on each model. Basic trust allocation for the two models and Obtain conflict factor According to Dempster's rule, the basic trust distribution of the two models is merged sequentially. The basic trust assignments of each model are obtained, resulting in a fused basic trust assignment. A pignistic transformation is then performed on the fused basic trust assignment to obtain the probability distribution for predicting lifetimes under a set of experimental conditions. Quantiles are then selected. (i.e., the preset confidence level), calculate the minimum width that satisfies this interval: .in, This is the confidence probability based on the Pignistic probability. This represents the confidence interval for predicting lifespan.

[0072] In another exemplary embodiment of this application, step 205 is replaced by steps 501 to 505: Step 501: Based on the fused lifetime prediction interval, obtain the conditional probability density function of lifetime.

[0073] Step 502: The stress and strain probability distributions are used as prior probability density functions.

[0074] Step 503: Calculate the marginal probability density function of the lifetime based on the conditional probability density function and the prior probability density function. The calculation formula is as follows: .

[0075] in, For predicted equipment lifespan T Exceeding time t The marginal probability density function, Given input parameters under Piginistic probability x Predicted equipment lifespan T Exceeding time t The conditional probability density function, For input parameters The prior probability density function.

[0076] Step 504: Calculate the conditional reliability function based on the conditional probability density function. The calculation formula is as follows: .

[0077] .

[0078] in, Given input parameters x Predicted devices in t The conditional reliability function at time t. For probability operators, For time, Let lifespan be a random variable. Given output parameters x The lifespan random variable at that time.

[0079] Step 505: Based on the conditional reliability function and the prior probability density function, obtain the overall predicted reliability function for lifetime and the reliability interval evaluation curve. The calculation formula is: .

[0080] in, Let be the overall predicted reliability function for lifetime at time t.

[0081] .

[0082] .

[0083] in, for t The lower bound reliability function of the lifetime at time t. Given input parameters x exist t The lower bound conditional reliability function at time t. for t The upper limit of the lifetime at any given time is determined by the reliability function. Given input parameters x exist t The upper limit conditional reliability function at time t.

[0084] This application refers to models that have already been fused. Given input parameters The predicted lifespan interval is a random variable and follows a distribution: (in, Given output parameters x The lifespan random variable at that time, Given input parameters under Piginistic probability x Predicted equipment lifespan T The conditional probability density function at that time); if the input parameters Then the marginal distribution of lifetimes is obtained. From this, the conditional survival function (or conditional reliability function) can be obtained. The predicted reliability of the lifetime is obtained after synthesis. Thus, the interval reliability is obtained. , This allows us to obtain the final interval reliability curve (or reliability interval evaluation curve). .

[0085] This invention provides a reliability interval assessment method for high-temperature rotating machinery components considering model uncertainties. Based on a constructed physical information neural network, it utilizes evidence theory to extend point estimation of lifespan to interval estimation, further achieving interval estimation of reliability. The upper limit of the reliability interval reflects the most economical reliability assessment but carries potential risks, while the lower limit reflects the most conservative reliability assessment but may involve over-maintenance. Interval reliability assessment provides more decision-making basis for the operation and maintenance management of high-temperature rotating machinery components, helping factories find the optimal balance between economy and safety based on actual operating conditions, and better plan equipment maintenance and downtime. This reliability interval assessment method has advantages such as high computational efficiency, accurate prediction, and good engineering applicability.

[0086] The following uses a steam turbine rotor as an example to illustrate the reliability range assessment method for high-temperature components in this application.

[0087] In this embodiment, 12Cr1MoV alloy is used as the rotor material, and its operating temperature is 600℃. Figure 2As shown, this invention provides a reliability interval assessment method for high-temperature rotating mechanical components considering model uncertainties, comprising the following steps: Probabilistic damage assessment of high-temperature rotating mechanical components: establishing a high-fidelity finite element model, identifying critical points of the high-temperature rotating mechanical components, accumulating multiple sets of finite element simulation results, training a surrogate model, and obtaining the stress-strain probability distribution of critical points of the component through Monte Carlo simulation; Establishment of a material-level physical information neural network model: training the neural network with experimental conditions as input variables and lifetime as the output variable, constructing multiple physical loss functions based on the linear damage accumulation rule, training multiple physical information neural network models, and constraining the training gradient with dynamic physical loss weights to ensure a stable training process; Reliability interval estimation based on evidence theory: calculating the error index of cross-validation of each physical information neural network, constructing a lifetime prediction interval and basic trust allocation based on this, fusing the prediction results of each model one by one using Dempster's rule to obtain a lifetime interval estimate, further incorporating the influence of random uncertainty, and completing the reliability interval assessment. Traditional reliability assessment methods for high-temperature rotating mechanical components often focus on the random uncertainties brought about by model parameters, while ignoring the cognitive uncertainty caused by different model selections, resulting in an incomplete reliability analysis of high-temperature rotating mechanical components. The reliability interval assessment method for high-temperature rotating mechanical components considering model uncertainties of this invention, in addition to considering the random uncertainties caused by loads and material parameters, also considers the model uncertainties caused by the selected physical model. This method can reflect the uncertainty and confidence interval of the predicted values, providing a more comprehensive basis and information for reliability assessment required in engineering. This reliability assessment method has fast calculation speed, good robustness, and good engineering applicability.

[0088] like Figure 3 As shown, a three-dimensional finite element model was established based on the structural characteristics of the turbine rotor, and the physical properties, elasticity, and plasticity of the 12Cr1MoV material as a function of temperature were set. Temperature field and centrifugal force field were applied to address the creep fatigue interaction experienced by the turbine rotor during actual service.

[0089] like Figure 4 As shown, the most dangerous position of the turbine rotor and the stress and strain values ​​at that position are determined through finite element simulation.

[0090] Assume that the parameters in the finite element simulation follow a normal distribution with a coefficient of variation of 0.05. These parameters include: Young's modulus. Fatigue strength factor Fatigue ductility factor Ostergren model parameters Ostergren model parameters Stress relaxation equation parameters Stress relaxation equation parameters Maximum stress ,temperature Fifty sets of parameter combinations were obtained through Latin hypercube sampling, and finite element simulations were performed sequentially.

[0091] Using 50 sets of parameter combinations from finite element simulations as input variables and the stress and strain values ​​at critical points as output variables, a surrogate model was trained. Model selection included neural networks, support vector machine regression, Gaussian process regression, response surface methodology, and random forest regression. Comparison showed that the neural network model had the smallest error and the strongest generalization ability, thus it was chosen as the surrogate model.

[0092] The neural network architecture is set to 32-16-8, with Young's modulus as the input variable. Fatigue strength factor Fatigue ductility factor Ostergren model parameters Ostergren model parameters Stress relaxation equation parameters Stress relaxation equation parameters Maximum stress ,temperature The output variable is the stress at the critical point. ,strain Displacement Because the magnitudes of the input variables differ too much, the data needs to be normalized before training begins. The ratio of training set to test set is 4:1. The activation function is ReLU, the optimizer is AdamW, L2 regularization is used, the training epochs are set to 500, and the model loss function is MSE.

[0093] After the surrogate model is trained, 10,000 parameter combinations are obtained through Latin hypercube sampling. Monte Carlo simulations are then performed using the surrogate model to obtain the stress and strain probability distributions at critical points. The stress follows... The unit is MPa, and the strain follows The unit is %.

[0094] like Figure 5 As shown, this embodiment collected 127 sets of creep fatigue test data for 12Cr1MoV material at a test temperature of 600℃. The data includes strain range, plastic strain range, stress range, average stress, strain rate, tensile holding time, compressive holding time, and fatigue life.

[0095] The physical information neural network was trained using this dataset. The network structure was set to 16-8-4. The input variables were strain range, plastic strain range, stress range, strain rate, tensile holding time, and compressive holding time. The output variable was life. The ratio of training set to test set was 4:1. The activation function was ReLU, the optimizer was AdamW, and L2 regularization was used. The training epochs were set to 500.

[0096] The model's total loss function is set as follows: .

[0097] in, The total loss of the physical information neural network model is... For data loss function, For physical loss function, These are the weights for the physical loss function. The total loss function participates in the forward and backward propagation of the model.

[0098] The physical loss function is expressed as follows: .

[0099] .

[0100] in, For physical loss, For the sample size, To predict creep fatigue life using neural networks, Predict creep fatigue life using physical equations.

[0101] The available fatigue life prediction models are the Manson-Coffin model (MC), the Morrow model (MO), and the Ostergren model (OS); the available creep life prediction models are the Time-Fractional model (TF) and the Ductile Exhaustion model (DE). The damage expressions for the above five damage models are as follows: .

[0102] .

[0103] .

[0104] .

[0105] .

[0106] in, For the total strain amplitude, The fatigue strength index. The fatigue ductility index, It is the fatigue strength coefficient (or fatigue strength factor). It is the elastic modulus (or Young's modulus) of the material. It is the fatigue ductility coefficient (or fatigue ductility factor). This refers to fatigue life or failure cycles. For single-cycle fatigue damage, For the total strain range, For average stress, These are material constants (or Ostergren model parameters). Plastic strain energy density for each cycle, These are material constants (or Ostergren model parameters). Creep damage calculated using the time fraction method. For relaxation rate parameters, To ensure the load time, For material constants, Peak stress, These are the parameters of the stress relaxation equation. For time, For material constants, For creep damage calculated using the ductile exhaustion method, For material constants, is a material constant.

[0107] The model parameters of any of the above fatigue damage models (or fatigue life prediction models) and creep damage models (or creep life prediction models) (there are 6 combinations in total) need to be pre-fitted before training begins, and the specific values ​​are shown in Table 1.

[0108] Table 1: Parameters of the Physical Loss Equation

[0109] Creep fatigue life can be calculated using the linear damage accumulation rule: .

[0110] in, and These represent creep damage and fatigue damage calculated from the physical equations, respectively.

[0111] The model selects the learning rate, Dropout probability, regularization weight, physical loss weight, and optimizer weight as hyperparameters, and performs 200 rounds of hyperparameter search using Bayesian optimization. The optimization objective is: .

[0112] in, The coefficient of determination for the test set. The coefficient of determination for the training set is denoted by , and the objective function takes values ​​in the range [-1, 1]. A larger value indicates better generalization ability of the model. To ensure the robustness of the model, the average of the model scores obtained through 10-fold cross-validation during training is used as the model score.

[0113] The range of hyperparameter search is shown in Table 2: Table 2: Hyperparameter Search Range

[0114] During training, a dynamic physical loss weight is used to control the speed of gradient descent. When the norm of the gradient exceeds 1, the physical loss weight is multiplied by a coefficient less than 1 to avoid the gradient being too large and causing training failure.

[0115] After each model is trained, it is subjected to 10-fold cross-validation with the optimal hyperparameters. The model error metrics are shown in Table 3. The error metrics include: mean square error, root mean square error, mean absolute error, mean absolute percentage error, coefficient of determination, and double error band precision.

[0116] Table 3: Error Indicators of Physical Information Neural Network Models

[0117] Compared to ordinary neural network models that do not contain physical information, physical information neural networks that incorporate physical equations show higher accuracy and better overall fit in predicting creep fatigue life.

[0118] After ten-fold cross-validation, 10 predicted lifetimes were obtained for each of the 6 models under each experimental condition, for a total of 60 data points. Based on this data, lifetime prediction intervals and basic confidence assignments were constructed.

[0119] For each model, 10 predicted lifetime data points are provided, along with a confidence quantile parameter. To obtain the quantiles: in, For the first The lower bound of the lifetime prediction range for each model. For the first The upper limit of the lifetime prediction range for each model. for Quantiles For 1- Quantiles For confidence quantile parameters, These are the input parameters for the physical information neural network model. Number the model. For cross-validation folds, The total number of folds for cross-validation. For the first The model has input parameters On The set of prediction results from cross-validation.

[0120] Then the model prediction interval can be obtained: .

[0121] The basic trust allocation method is as follows: First, the dimensionless model error index is used. in, For the first The dimensionless error index of the model For the first The model error metric for each model is the mean absolute error (MAE). and They are respectively j The minimum and maximum error indices for each model. It is important to note that the errors selected here are the model errors specific to a set of experimental conditions and lifetimes, not the overall model error index. These are then converted into model scores: .

[0122] in, The parameter used to control the model score discrimination is set to 0.3 here. Normalized to the model confidence weights: in, For the first The credibility weights of each model For the first The model score of each model.

[0123] Constructing the basic trust allocation for each model: .

[0124] in, For the first i The basic trust assignment function of the model, For the first The lifetime prediction range of each model.

[0125] Basic trust allocation for the two models and Its conflict factor is: .

[0126] in, As a conflict factor, To identify a subset of the frame, i.e., the model a Lifespan prediction range , For another subset of the identification framework, namely the model b Lifespan prediction range .

[0127] According to Dempster's rule, the basic trust allocation of the two models is as follows: in, To identify any subset within the frame, This is the Dempster fusion operator.

[0128] By sequentially integrating the basic trust allocation of the six models, we obtain: .

[0129] in, Assigning basic trust after integration.

[0130] A Pignistic transformation of this basic trust assignment yields the probability distribution for predicting lifetimes under a set of experimental conditions: .

[0131] in, For the Pignistic probability, For the interval [ , ], The lower bound of the interval, The upper bound of the interval is... For set The basic trust allocation.

[0132] Selecting quantiles Calculate the minimum width that satisfies this interval: .

[0133] in, This is the confidence probability based on the Pignistic probability. This represents the confidence interval for predicting lifespan.

[0134] Calculations show that the interval width required to achieve a 95% interval coverage rate is 238.

[0135] For models that have already been merged Given input stress and strain The predicted lifespan intervals follow a distribution: .

[0136] in, Given input stress and strain The lifespan random variable at that time, Let be the conditional probability density function of lifetime under Piginistic probability.

[0137] The stress follows the parameters obtained from the aforementioned Monte Carlo simulation. The unit is MPa, and the strain follows If the unit is %, then the marginal distribution of lifetime is: .

[0138] in, For predicted equipment lifespan T Exceeding time t The marginal probability density function of lifetime. Given input parameters under Piginistic probability x Predicted equipment lifespan T The conditional probability density function at time , For input parameters The prior probability density function.

[0139] From this, we can obtain the conditional survival function (or conditional reliability function): .

[0140] in, Given input parameters x Predicted devices in t The conditional reliability function at time t. For probability operators, For time, For lifespan random variables.

[0141] The overall lifetime prediction reliability is obtained as follows: .

[0142] in, for t The overall predictive reliability function for lifetime at time point.

[0143] Interval reliability is obtained: .

[0144] .

[0145] in, for t The lower bound reliability function of the lifetime at time t. Given input parameters x exist t The lower bound conditional reliability function at time t. for t The upper limit of the lifetime at any given time is determined by the reliability function. Given input parameters x exist t The upper limit conditional reliability function at time t.

[0146] like Figure 6 As shown, the final interval reliability curve (or reliability interval evaluation curve) is obtained. .

[0147] Based on the same inventive concept, this application also provides a high-temperature component reliability range assessment device for implementing the high-temperature component reliability range assessment method described above. The solution provided by this device is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more embodiments of the high-temperature component reliability range assessment device provided below can be found in the limitations of the high-temperature component reliability range assessment method described above, and will not be repeated here.

[0148] In one exemplary embodiment, a high-temperature component reliability range assessment device is provided, including: a probabilistic damage assessment module, a model training module, a range construction and trust allocation module, a fusion module, and a reliability range assessment module.

[0149] The probabilistic damage assessment module is used to perform probabilistic damage assessment on high-temperature components and obtain the stress and strain probability distribution at the critical points of the high-temperature components.

[0150] The model training module is used to construct and train multiple physical information neural network models with the creep fatigue test conditions of high-temperature components as input and the test life as output; the physical information neural network models include fatigue life prediction models and creep life prediction models.

[0151] The interval construction and trust allocation module is used to construct the lifetime prediction interval and basic trust allocation for each model based on the lifetime prediction results of each physical information neural network model.

[0152] The fusion module is used to fuse the lifetime prediction intervals and basic trust assignments of each model using the Dempster method to obtain the fused lifetime prediction interval.

[0153] The reliability range assessment module is used to obtain the reliability range assessment results of the high-temperature component life based on the fusion life prediction range and the stress and strain probability distribution.

[0154] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 7 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores high-temperature component reliability range assessment data. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a high-temperature component reliability range assessment method.

[0155] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0156] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0157] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0158] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0159] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0160] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0161] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0162] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0163] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for evaluating the reliability range of high-temperature components, characterized in that, include: Probabilistic damage assessment is performed on high-temperature components to obtain the stress and strain probability distribution at critical points of the high-temperature components; Using the creep fatigue test conditions of high-temperature components as input and the test life as output, multiple physical information neural network models are constructed and trained; the physical information neural network models include fatigue life prediction models and creep life prediction models. Based on the lifetime prediction results of each physical information neural network model, the lifetime prediction range and basic trust allocation of each model are constructed. Based on the lifetime prediction intervals and basic confidence assignments of each model, the Dempster method is used to fuse them to obtain the fused lifetime prediction interval. Based on the fusion life prediction range and the stress and strain probability distribution, the reliability range assessment results of the high-temperature component life are obtained.

2. The method for evaluating the reliability range of high-temperature components according to claim 1, characterized in that, The formula for calculating the lifetime prediction range is: in, For the first The lifetime prediction range of each model. For the first The lower bound of the lifetime prediction range for each model. For the first The upper limit of the lifetime prediction range for each model. for Quantiles For 1- Quantiles For confidence quantile parameters, These are the input parameters for the physical information neural network model. Number the model. For cross-validation folds, The total number of folds for cross-validation. For the first The model has input parameters On The set of prediction results from cross-validation.

3. The method for evaluating the reliability range of high-temperature components according to claim 1, characterized in that, The formula for calculating the basic trust allocation is as follows: ； in, For the first i The basic trust assignment function of the model, For the first The lifetime prediction range of each model. For the first The credibility weights of each model For the first The model score of each model. Number the model. For the first The dimensionless error index of the model To control the parameters of the model score discrimination, For the first The model error index of each model. and They are respectively j The minimum and maximum error indices in each model.

4. The method for evaluating the reliability range of high-temperature components according to claim 1, characterized in that, Based on the lifetime prediction intervals and basic confidence assignments of each model, the Dempster method is used to fuse them to obtain the fused lifetime prediction interval, which specifically includes: The conflict factor is calculated based on the basic trust allocation, and the formula for calculating the conflict factor is as follows: ； in, As a conflict factor, To identify a subset of the frame, i.e., the model a Lifetime prediction range , For another subset of the identification framework, namely the model b Lifespan prediction range , For the model a Basic trust allocation, For the model b Basic trust allocation; According to Dempster's rule, the basic trust assignments of each model are merged one by one until all models are merged, resulting in the merged basic trust assignment. The formula for calculating the merged basic trust assignment is as follows: ； in, Assigning basic trust after integration, For the first The basic trust allocation of each model =1, 2, ..., , To identify any subset within the frame, For Dempster fusion operator; The fused basic trust allocation is subjected to a Pignistic transformation to obtain the Pignistic probability distribution of predicted lifetime. The formula for calculating the Pignistic probability distribution of predicted lifetime is as follows: ； in, For the Pignistic probability, For the interval [ , ], The lower bound of the interval, The upper bound of the interval is... For set M Basic trust allocation; Based on a preset confidence level, the fusion lifetime prediction interval is determined from the Pignistic probability distribution.

5. The method for evaluating the reliability range of high-temperature components according to claim 1, characterized in that, Based on the fusion life prediction range and the stress and strain probability distribution, the reliability range assessment results of the high-temperature component life are obtained, specifically including: Based on the fusion lifetime prediction interval, the conditional probability density function of lifetime is obtained; The probability distributions of stress and strain are used as prior probability density functions; Based on the conditional probability density function and the prior probability density function, the marginal probability density function of the lifetime is calculated using the following formula: ； in, For predicted equipment lifespan T Exceeding time t The marginal probability density function, Given input parameters under Piginistic probability x Predicted equipment lifespan T Exceeding time t The conditional probability density function, For input parameters The prior probability density function; The conditional reliability function is calculated based on the conditional probability density function, and the formula is as follows: ； ； in, Given input parameters x Predicted devices in t The conditional reliability function at time t. For probability operators, For time, Let lifespan be a random variable. For given output parameters x The lifespan random variable at that time; Based on the conditional reliability function and the prior probability density function, the overall predicted reliability function for lifetime and the reliability interval assessment curve are obtained. The calculation formula is: ； in, for t The overall predictive reliability function for lifetime at any given time; ； ； in, for t The lower bound reliability function of the lifetime at any given time. Given input parameters x exist t The lower bound conditional reliability function at time t. for t The upper limit of the lifetime at any given time is determined by the reliability function. Given input parameters x exist t The upper limit conditional reliability function at time t.

6. The method for evaluating the reliability range of high-temperature components according to claim 1, characterized in that, Probabilistic damage assessment is performed on high-temperature components to obtain the stress and strain probability distribution at critical points of the components, specifically including: A three-dimensional finite element model was established based on the structural characteristics of the high-temperature component. Latin hypercube sampling was used to extract multiple sets of parameter combinations from the model parameters of the three-dimensional finite element model, and finite element simulations were performed to obtain the stress and strain response of the high-temperature component at the critical point under different parameter combinations. Using the parameter combination of finite element simulation as input and the stress and strain response at the critical point as output, a surrogate model is trained to obtain a well-trained surrogate model. Multiple combinations of random parameters were obtained through Latin hypercube sampling; Monte Carlo simulation, based on a trained surrogate model, is used to calculate the stress and strain responses of critical points under multiple random parameter combinations obtained by Latin hypercube sampling, and the stress and strain probability distributions of critical points are obtained.

7. A high-temperature component reliability range assessment device, characterized in that, include: The probabilistic damage assessment module is used to perform probabilistic damage assessment on high-temperature components and obtain the stress and strain probability distribution at the critical points of the high-temperature components. The model training module is used to construct and train multiple physical information neural network models with the creep fatigue test conditions of high-temperature components as input and the test life as output; the physical information neural network models include fatigue life prediction models and creep life prediction models. The interval construction and trust allocation module is used to construct the lifetime prediction interval and basic trust allocation for each model based on the lifetime prediction results of each physical information neural network model. The fusion module is used to fuse the lifetime prediction intervals and basic trust assignments of each model using the Dempster method to obtain the fused lifetime prediction interval. The reliability range assessment module is used to obtain the reliability range assessment results of the high-temperature component life based on the fusion life prediction range and the stress and strain probability distribution.

8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the high-temperature component reliability range assessment method according to any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the high-temperature component reliability range assessment method as described in any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the high-temperature component reliability range assessment method as described in any one of claims 1-6.

Images