Fatigue analysis method and device for connecting bolt of top cover and seat ring of water turbine
By combining Latin hypercube sampling and Kriging surrogate model with finite element simulation, the computational complexity and high cost of traditional bolt fatigue analysis are solved, enabling efficient bolt fatigue life prediction and design optimization.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-14
- Publication Date
- 2026-03-24
AI Technical Summary
Traditional bolt fatigue analysis methods are computationally complex and costly, making it difficult to meet the real-time and accuracy requirements of practical engineering applications, especially in multi-condition and multi-variable analysis, where it is difficult to achieve refined design optimization.
A sample set was generated using Latin hypercube sampling, and a Kriging surrogate model was constructed. Through finite element simulation and dynamic analysis, combined with the Goodman mean stress criterion and SN curve, bolt fatigue life was predicted.
It achieves efficient prediction of bolt fatigue life analysis, reduces computational resource requirements, improves design optimization efficiency, breaks through the computational bottleneck of traditional methods, and provides a reliability analysis tool.
Smart Images
Figure CN121723741A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of equipment testing technology, specifically to a fatigue analysis method and apparatus for the connecting bolts between the top cover and the seat ring of a water turbine. Background Technology With economic development, the hydropower industry has grown increasingly powerful. The bolts connecting the turbine top cover and the seat ring, besides serving as fasteners, also play a crucial role in sealing the water supply, along with the top cover itself. Failure or breakage of these bolts could cause catastrophic accidents to the unit and even the entire plant. In mechanical structures, bolted connections are widely used to link different components, especially under high stress, dynamic loads, and complex operating conditions. These connections often bear significant cyclic loads, making bolt fatigue a critical aspect of structural reliability analysis. The bolts connecting the top cover and the seat ring frequently face uneven loads, temperature variations, and vibrations, potentially leading to fatigue failure during long-term use. Therefore, accurate prediction of bolt fatigue life and the implementation of effective design optimization methods are essential for improving the reliability and safety of mechanical structures.
[0002] Traditional bolt fatigue analysis methods are typically based on finite element analysis and fatigue life prediction models. However, due to computational complexity and high computational cost, especially in multi-condition and multivariate analyses, the computational load is enormous, making it difficult to meet the real-time and accuracy requirements of practical engineering applications. Traditional fatigue analysis methods heavily rely on parametric finite element models for transient dynamic simulations. While the calculation results are accurate, each analysis is extremely time-consuming and computationally expensive. This efficiency bottleneck severely restricts the practical implementation of parameter sensitivity analysis, uncertainty quantification, and design optimization, making it difficult to achieve refined design based on fatigue performance. Summary of the Invention
[0003] To overcome the above-mentioned defects, this invention proposes a fatigue analysis method and apparatus for the connecting bolts between the turbine top cover and the seat ring.
[0004] Firstly, a fatigue analysis method for the connecting bolts between the turbine top cover and the seat ring is provided, the method comprising: Multiple sample sets are generated within the design space of the design variable parameters of the connecting bolts between the turbine top cover and the seat ring based on Latin hypercube sampling. For the multiple sample sets, dynamic simulation was performed on the pre-constructed finite element model of the turbine top cover and seat ring connecting screw to obtain the corresponding training sample library of each sample set and stress response data; A Kriging proxy model is constructed based on the aforementioned training sample library; Based on the Kriging surrogate model, the stress response data corresponding to the design variable parameters are predicted, and fatigue analysis of the connecting bolts between the turbine top cover and the seat ring is performed based on the prediction results.
[0005] Preferably, the design variable parameters include at least one of the following: bolt diameter, bolt elastic modulus, Poisson's ratio yield strength, tensile strength, bolt preload, working water pressure, and unit speed.
[0006] Preferably, the dynamic simulation of the pre-constructed finite element model of the turbine top cover and the seat ring connecting bolt includes: Static water pressure was applied between the top cover and the seat ring to the pre-constructed finite element model of the turbine top cover and seat ring connecting bolts. The magnitude and location of the maximum equivalent stress on the connecting bolts were obtained by structural static simulation calculation using finite element simulation software. Dynamic water pressure pulsation load was applied to the model, and the equivalent stress time history data of the bolts was obtained through transient dynamic simulation calculation.
[0007] Preferably, the stress response data includes: stress amplitude and / or average stress.
[0008] Preferably, in the process of constructing the Kriging surrogate model based on the training sample library, the maximum likelihood estimation method is used to fit the Kriging surrogate model.
[0009] Preferably, the Kriging proxy model is as follows:
[0010] In the above formula, For the stress response Kriging surrogate model with respect to the design variable parameter x, For the regression model of the design variable parameter x, T is the transpose sign. A vector of linear regression coefficients. This is the local deviation term of the model with respect to the design variable parameter x.
[0011] Preferably, in the process of constructing the Kriging surrogate model based on the training sample library, the model prediction performance is verified by calculating the coefficient of determination, maximum absolute error, and / or root mean square error through k-fold cross-validation.
[0012] Preferably, the fatigue analysis of the connecting bolts between the turbine top cover and the seat ring based on the prediction results includes: Stress response data prediction is performed on any set of design variable parameters using the Kriging surrogate model; Based on the equivalent stress calculation model of the modified Goodman mean stress criterion, the symmetrical cyclic stress amplitude of the predicted stress response data is calculated. Using the standard SN curve of the material, the fatigue life value corresponding to the design variable parameter is calculated through the stress-life relationship equation.
[0013] Secondly, a fatigue analysis device for the connecting bolts between the turbine top cover and the seat ring is provided, the device comprising: The generation module is used to generate multiple sample sets within the design space of the design variable parameters of the connecting bolts between the turbine top cover and the seat ring based on Latin hypercube sampling. The first analysis module is used to perform dynamic simulation on the pre-constructed finite element model of the turbine top cover and seat ring connecting screw for the multiple sample sets, and obtain the corresponding training sample library of each sample set and stress response data. The building module is used to construct a Kriging proxy model based on the training sample library; The second analysis module is used to predict the stress response data corresponding to the design variable parameters based on the Kriging surrogate model, and to perform fatigue analysis on the connecting bolts of the turbine top cover and seat ring based on the prediction results.
[0014] Preferably, the design variable parameters include at least one of the following: bolt diameter, bolt elastic modulus, Poisson's ratio yield strength, tensile strength, bolt preload, working water pressure, and unit speed.
[0015] Preferably, the dynamic simulation of the pre-constructed finite element model of the turbine top cover and the seat ring connecting bolt includes: Static water pressure was applied between the top cover and the seat ring to the pre-constructed finite element model of the turbine top cover and seat ring connecting bolts. The magnitude and location of the maximum equivalent stress on the connecting bolts were obtained by structural static simulation calculation using finite element simulation software. Dynamic water pressure pulsation load was applied to the model, and the equivalent stress time history data of the bolts was obtained through transient dynamic simulation calculation.
[0016] Preferably, the stress response data includes: stress amplitude and / or average stress.
[0017] Preferably, in the process of constructing the Kriging surrogate model based on the training sample library, the maximum likelihood estimation method is used to fit the Kriging surrogate model.
[0018] Preferably, the Kriging proxy model is as follows:
[0019] In the above formula, For the stress response Kriging surrogate model with respect to the design variable parameter x, For the regression model of the design variable parameter x, T is the transpose sign. A vector of linear regression coefficients. This is the local deviation term of the model with respect to the design variable parameter x.
[0020] Preferably, in the process of constructing the Kriging surrogate model based on the training sample library, the model prediction performance is verified by calculating the coefficient of determination, maximum absolute error, and / or root mean square error through k-fold cross-validation.
[0021] Preferably, the fatigue analysis of the connecting bolts between the turbine top cover and the seat ring based on the prediction results includes: Stress response data prediction is performed on any set of design variable parameters using the Kriging surrogate model; Based on the equivalent stress calculation model of the modified Goodman mean stress criterion, the symmetrical cyclic stress amplitude of the predicted stress response data is calculated. Using the standard SN curve of the material, the fatigue life value corresponding to the design variable parameter is calculated through the stress-life relationship equation.
[0022] Thirdly, a computer device is provided, comprising: one or more processors; The processor is used to execute one or more programs; When the one or more programs are executed by the one or more processors, the fatigue analysis method for the connecting bolts between the turbine top cover and the seat ring is implemented.
[0023] Fourthly, a computer-readable storage medium is provided, on which a computer program is stored, wherein when the computer program is executed, the fatigue analysis method for the connecting bolts of the turbine top cover and the seat ring is implemented.
[0024] The above-described technical solutions of the present invention have at least one or more of the following beneficial effects: This invention provides a method and apparatus for fatigue analysis of bolts connecting the turbine top cover and seat ring, comprising: generating multiple sample sets within the design space of design variable parameters of the bolts connecting the turbine top cover and seat ring based on Latin hypercube sampling; performing dynamic simulation on a pre-constructed finite element model of the bolts connecting the turbine top cover and seat ring for the multiple sample sets, obtaining a corresponding training sample library of each sample set and stress response data; constructing a Kriging surrogate model based on the training sample library; predicting the stress response data corresponding to the design variable parameters based on the Kriging surrogate model, and performing fatigue analysis of the bolts connecting the turbine top cover and seat ring based on the prediction results. The technical solution provided by this invention, by constructing a surrogate model to approximate the real physical process, can achieve rapid solution of bolt stress response under dynamic loads. Compared with simulating the structural resistance of bolts using CFD simulation tools, it can effectively reduce the workload of numerical simulation and reduce the computational resources required in the optimization process. At the same time, this method, while ensuring prediction accuracy, provides feasibility for solving complex engineering problems such as multi-parameter optimization and reliability analysis, breaking through the bottleneck of traditional methods that cannot conduct in-depth research due to high computational costs. This greatly improves the efficiency of bolt fatigue life analysis and provides an effective tool for reliability optimization design based on fatigue performance. Attached Figure Description
[0025] Figure 1 This is a schematic diagram of the main steps of the fatigue analysis method for the connecting bolts of the turbine top cover and the seat ring according to an embodiment of the present invention. Detailed Implementation
[0026] The specific embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.
[0027] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0028] Example 1 See appendix Figure 1 , Figure 1 This is a schematic flowchart illustrating the main steps of a fatigue analysis method for the connecting bolts between the turbine top cover and the seat ring, according to an embodiment of the present invention. Figure 1 As shown, the fatigue analysis method for the connecting bolts between the turbine top cover and the seat ring in this embodiment of the invention mainly includes the following steps: Step S101: Generate multiple sample sets within the design space of the design variable parameters of the connecting bolts between the turbine top cover and the seat ring based on Latin hypercube sampling; Step S102: For the multiple sample sets, perform dynamic simulation on the pre-constructed finite element model of the turbine top cover and seat ring connecting screw to obtain the corresponding training sample library of each sample set and stress response data; Step S103: Construct a Kriging proxy model based on the training sample library; Step S104: Based on the Kriging surrogate model, predict the stress response data corresponding to the design variable parameters, and perform fatigue analysis on the connecting bolts of the turbine top cover and seat ring based on the prediction results.
[0029] In this embodiment, the design variable parameters include at least one of the following: bolt diameter, bolt elastic modulus, Poisson's ratio yield strength, tensile strength, bolt preload, working water pressure, and unit speed.
[0030] In this embodiment, the dynamic simulation of the pre-constructed finite element model of the turbine top cover and the seat ring connecting bolt includes: Static water pressure was applied between the top cover and the seat ring to the pre-constructed finite element model of the turbine top cover and seat ring connecting bolts. The magnitude and location of the maximum equivalent stress on the connecting bolts were obtained by structural static simulation calculation using finite element simulation software. Dynamic water pressure pulsation load was applied to the model, and the equivalent stress time history data of the bolts was obtained through transient dynamic simulation calculation.
[0031] In this embodiment, the stress response data includes: stress amplitude and / or average stress.
[0032] In one specific implementation, steps S101 and S102 specifically include: Step 1021: Collect the design drawings of the turbine unit, and use 3D visualization modeling software and CFD simulation software to establish 3D geometric models of the turbine's top cover, seat ring and connecting bolts, and assemble them to obtain the overall component assembly model. Step 1022: Obtain the basic technical parameters of the turbine unit and the operating parameters under various typical operating conditions. In the CFD simulation software, mesh the top cover, seat ring, and connecting bolts, and simultaneously refine the mesh on the connecting bolts and the contact surface between the top cover and seat ring. Based on the stress conditions of the turbine top cover-seat ring-connecting bolt system model, set boundary conditions for the model. In addition to bearing the applied bolt preload, the connecting bolts also bear various loads transmitted from the top cover (such as the force transmitted to the top cover from the water guide bearing and movable guide vanes). Add fixed constraints at the bottom of the seat ring, setting frictional contact between the top cover and seat ring, and between the nut and the outer flange of the top cover, while binding constraints exist between the stud and the threaded hole of the seat ring, and between the nut and the stud.
[0033] Step 1023: Based on the study of the stress characteristics of the turbine unit bolts, select n variables as input variables from structural parameters (bolt diameter), material parameters (elastic modulus, Poisson's ratio, yield strength, tensile strength of bolts), load parameters (bolt preload, working water pressure, unit speed), and boundary conditions, and determine the input variable set X = (x1, x2, ..., xn). Step 1024 uses the parametric scripting language Python integrated into the finite element modeling software, which enables the script to automatically read and update the geometric dimensions, mesh generation, load and boundary condition settings of the top cover, seat ring and connecting bolt model for each sample point. Step 1025 defines a reasonable range [ximin, ximax] for each design variable xi based on engineering experience, design specifications, or preliminary sensitivity analysis, ensuring it covers all possible operating conditions. Latin hypercube sampling (LHS) is used to generate N sample points within the design space, ensuring all variables are uniformly distributed within their respective ranges and that projections onto each dimension cover the entire range, avoiding the clustering phenomenon of traditional Monte Carlo sampling. The space-filling criterion is used to evaluate sampling quality, ensuring uniform sample point distribution and providing an input parameter set for subsequent high-fidelity analysis.
[0034] Step 1026: Based on the established parametric finite element simulation model, according to the actual operating conditions, the parametric script automatically reads the design variable values of each sample point xi for each sample point, automatically updates the finite element model in the finite element simulation software, applies static water pressure between the top cover and the seat ring to the finite element model of the turbine top cover-seat ring-connecting bolts according to the design specifications, obtains the magnitude and location of the maximum equivalent stress on the connecting bolts through structural static simulation calculations in the finite element simulation software, applies dynamic water pressure pulsating loads to the model, and obtains the equivalent stress time history data of the bolts through transient dynamic simulation calculations.
[0035] Step 1027 For dynamic load conditions, the script automatically identifies and extracts the stress time history data of the bolt's critical points, performs rainflow counting on the stress time history data of the critical points, and extracts the stress amplitude (Sa) and mean stress (Sm) for fatigue analysis. Step 1028 automatically stores each sample point Xi and its corresponding output response Yi into the database and integrates them into the final training sample library D. The sample library D is an N×(n+m) matrix, where N is the total number of samples, n is the input variable dimension, and m is the output response dimension. Before training the proxy model, a small number of sample points are randomly selected, and the results of the automated script are compared with the results of manually setting the model to ensure the accuracy of the automated process, perform data validation, and check for outliers in the output data.
[0036] Step 1029: To ensure the reliability of the simulation results, a benchmark model should be verified for mesh independence to ensure that the stress solution under the current mesh density has converged. The simulation results of the benchmark model should be compared with theoretical calculations or existing experimental data to verify the accuracy of the finite element model itself.
[0037] In this embodiment, during the process of constructing the Kriging surrogate model based on the training sample library, the maximum likelihood estimation method is used to fit the Kriging surrogate model.
[0038] In this embodiment, the Kriging proxy model is as follows:
[0039] In the above formula, For the stress response Kriging surrogate model with respect to the design variable parameter x, For the regression model of the design variable parameter x, T is the transpose sign. A vector of linear regression coefficients. This is the local deviation term of the model with respect to the design variable parameter x.
[0040] In this embodiment, during the process of constructing the Kriging surrogate model based on the training sample library, the model prediction performance is verified by calculating the coefficient of determination, maximum absolute error, and / or root mean square error through k-fold cross-validation.
[0041] In one implementation, the coefficient of determination is considered to be closer to 1, indicating a higher goodness of fit of the model. This invention requires a coefficient of determination greater than 0.99.
[0042] Root mean square error (RMSE): measures the deviation between the predicted value and the actual value; the smaller the value, the better.
[0043] Maximum absolute error (MAE): measures the prediction error under worst-case conditions.
[0044] In this embodiment, the fatigue analysis of the connecting bolts between the turbine top cover and the seat ring based on the prediction results includes: Stress response data prediction is performed on any set of design variable parameters using the Kriging surrogate model; Based on the equivalent stress calculation model of the modified Goodman mean stress criterion, the symmetrical cyclic stress amplitude of the predicted stress response data is calculated. Using the standard SN curve of the material, the fatigue life value corresponding to the design variable parameter is calculated through the stress-life relationship equation.
[0045] In one implementation, the standard SN curve is determined under symmetrical stress cycling. Since it is difficult to guarantee completely reversed loads in real-world testing, in practical applications, the Goodman method is typically used to correct the alternating stress amplitude to obtain an equivalent alternating stress amplitude. Based on the equivalent stress calculation model using the corrected Goodman mean stress criterion, the symmetrical cyclic stress amplitude of the predicted stress is calculated. Using the material's standard SN curve, the fatigue life value (expressed in cycles) corresponding to the design point is accurately calculated using the stress-life relationship equation. By integrating and coupling the rapid prediction process with the genetic optimization algorithm, with the goal of maximizing fatigue life and constraints such as life requirements, strength, and stiffness, new design parameters are automatically generated and the proxy model is iteratively called for rapid evaluation, forming an automated closed-loop optimization process of "prediction-evaluation-redesign", which ultimately outputs the optimal design scheme that meets all performance requirements efficiently.
[0046] Example 2 Based on the same inventive concept, the present invention also provides a fatigue analysis device for the connecting bolts of the turbine top cover and the seat ring, the fatigue analysis device for the connecting bolts of the turbine top cover and the seat ring comprising: The generation module is used to generate multiple sample sets within the design space of the design variable parameters of the connecting bolts between the turbine top cover and the seat ring based on Latin hypercube sampling. The first analysis module is used to perform dynamic simulation on the pre-constructed finite element model of the turbine top cover and seat ring connecting screw for the multiple sample sets, and obtain the corresponding training sample library of each sample set and stress response data. The building module is used to construct a Kriging proxy model based on the training sample library; The second analysis module is used to predict the stress response data corresponding to the design variable parameters based on the Kriging surrogate model, and to perform fatigue analysis on the connecting bolts of the turbine top cover and seat ring based on the prediction results.
[0047] Preferably, the design variable parameters include at least one of the following: bolt diameter, bolt elastic modulus, Poisson's ratio yield strength, tensile strength, bolt preload, working water pressure, and unit speed.
[0048] Preferably, the dynamic simulation of the pre-constructed finite element model of the turbine top cover and the seat ring connecting bolt includes: Static water pressure was applied between the top cover and the seat ring to the pre-constructed finite element model of the turbine top cover and seat ring connecting bolts. The magnitude and location of the maximum equivalent stress on the connecting bolts were obtained by structural static simulation calculation using finite element simulation software. Dynamic water pressure pulsation load was applied to the model, and the equivalent stress time history data of the bolts was obtained through transient dynamic simulation calculation.
[0049] Preferably, the stress response data includes: stress amplitude and / or average stress.
[0050] Preferably, in the process of constructing the Kriging surrogate model based on the training sample library, the maximum likelihood estimation method is used to fit the Kriging surrogate model.
[0051] Preferably, the Kriging proxy model is as follows:
[0052] In the above formula, For the stress response Kriging surrogate model with respect to the design variable parameter x, For the regression model of the design variable parameter x, T is the transpose sign. A vector of linear regression coefficients. This is the local deviation term of the model with respect to the design variable parameter x.
[0053] Preferably, in the process of constructing the Kriging surrogate model based on the training sample library, the model prediction performance is verified by calculating the coefficient of determination, maximum absolute error, and / or root mean square error through k-fold cross-validation.
[0054] Preferably, the fatigue analysis of the connecting bolts between the turbine top cover and the seat ring based on the prediction results includes: Stress response data prediction is performed on any set of design variable parameters using the Kriging surrogate model; Based on the equivalent stress calculation model of the modified Goodman mean stress criterion, the symmetrical cyclic stress amplitude of the predicted stress response data is calculated. Using the standard SN curve of the material, the fatigue life value corresponding to the design variable parameter is calculated through the stress-life relationship equation.
[0055] Example 3 Based on the same inventive concept, this invention also provides a computer device, which includes a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in the computer storage medium to achieve corresponding method flows or corresponding functions, thereby implementing the steps of the fatigue analysis method for the connecting bolts of the turbine top cover and seat ring in the above embodiments.
[0056] Example 4 Based on the same inventive concept, this invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and extended storage media supported by the computer device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, this storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the steps of the fatigue analysis method for the turbine top cover and seat ring connecting bolts in the above embodiments.
[0057] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0058] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0059] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0060] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0061] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.
Claims
1. A fatigue analysis method for the connecting bolts between the turbine top cover and the seat ring, characterized in that, The method includes: Multiple sample sets are generated within the design space of the design variable parameters of the connecting bolts between the turbine top cover and the seat ring based on Latin hypercube sampling. For the multiple sample sets, dynamic simulation was performed on the pre-constructed finite element model of the turbine top cover and seat ring connecting screw to obtain the corresponding training sample library of each sample set and stress response data; A Kriging proxy model is constructed based on the aforementioned training sample library; Based on the Kriging surrogate model, the stress response data corresponding to the design variable parameters are predicted, and fatigue analysis of the connecting bolts between the turbine top cover and the seat ring is performed based on the prediction results.
2. The method as described in claim 1, characterized in that, The design variable parameters include at least one of the following: bolt diameter, bolt elastic modulus, Poisson's ratio yield strength, tensile strength, bolt preload, working water pressure, and unit speed.
3. The method as described in claim 1, characterized in that, The dynamic simulation of the pre-constructed finite element model of the turbine top cover and the seat ring connecting bolt includes: Static water pressure was applied between the top cover and the seat ring to the pre-constructed finite element model of the turbine top cover and seat ring connecting bolts. The magnitude and location of the maximum equivalent stress on the connecting bolts were obtained by structural static simulation calculation using finite element simulation software. Dynamic water pressure pulsation load was applied to the model, and the equivalent stress time history data of the bolts was obtained through transient dynamic simulation calculation.
4. The method as described in claim 1, characterized in that, The stress response data includes: stress amplitude and / or average stress.
5. The method as described in claim 1, characterized in that, In the process of constructing the Kriging surrogate model based on the training sample library, the maximum likelihood estimation method is used to fit the Kriging surrogate model.
6. The method as described in claim 1, characterized in that, The Kriging proxy model is as follows: In the above formula, For the stress response Kriging surrogate model with respect to the design variable parameter x, For the regression model of the design variable parameter x, T is the transpose sign. A vector of linear regression coefficients. This is the local deviation term of the model with respect to the design variable parameter x.
7. The method as described in claim 1, characterized in that, In the process of constructing the Kriging surrogate model based on the training sample library, the model prediction performance is verified by calculating the coefficient of determination, maximum absolute error, and / or root mean square error.
8. The method as described in claim 1, characterized in that, The fatigue analysis of the connecting bolts between the turbine top cover and the seat ring based on the prediction results includes: Stress response data prediction is performed on any set of design variable parameters using the Kriging surrogate model; Based on the equivalent stress calculation model of the modified Goodman mean stress criterion, the symmetrical cyclic stress amplitude of the predicted stress response data is calculated. Using the standard SN curve of the material, the fatigue life value corresponding to the design variable parameter is calculated through the stress-life relationship equation.
9. A fatigue analysis device for the connecting bolts between the turbine top cover and the seat ring, characterized in that, The device includes: The generation module is used to generate multiple sample sets within the design space of the design variable parameters of the connecting bolts between the turbine top cover and the seat ring based on Latin hypercube sampling. The first analysis module is used to perform dynamic simulation on the pre-constructed finite element model of the turbine top cover and seat ring connecting screw for the multiple sample sets, and obtain the corresponding training sample library of each sample set and stress response data. The building module is used to construct a Kriging proxy model based on the training sample library; The second analysis module is used to predict the stress response data corresponding to the design variable parameters based on the Kriging surrogate model, and to perform fatigue analysis on the connecting bolts of the turbine top cover and seat ring based on the prediction results.
10. The apparatus as claimed in claim 9, characterized in that, The design variable parameters include at least one of the following: bolt diameter, bolt elastic modulus, Poisson's ratio yield strength, tensile strength, bolt preload, working water pressure, and unit speed.
11. The apparatus as claimed in claim 9, characterized in that, The dynamic simulation of the pre-constructed finite element model of the turbine top cover and the seat ring connecting bolt includes: Static water pressure was applied between the top cover and the seat ring to the pre-constructed finite element model of the turbine top cover and seat ring connecting bolts. The magnitude and location of the maximum equivalent stress on the connecting bolts were obtained by structural static simulation calculation using finite element simulation software. Dynamic water pressure pulsation load was applied to the model, and the equivalent stress time history data of the bolts was obtained through transient dynamic simulation calculation.
12. The apparatus as claimed in claim 9, characterized in that, The stress response data includes: stress amplitude and / or average stress.
13. The apparatus as claimed in claim 9, characterized in that, In the process of constructing the Kriging surrogate model based on the training sample library, the maximum likelihood estimation method is used to fit the Kriging surrogate model.
14. The apparatus as claimed in claim 9, characterized in that, The Kriging proxy model is as follows: In the above formula, For the stress response Kriging surrogate model with respect to the design variable parameter x, For the regression model of the design variable parameter x, T is the transpose sign. A vector of linear regression coefficients. This is the local deviation term of the model with respect to the design variable parameter x.
15. The apparatus as claimed in claim 9, characterized in that, In the process of constructing the Kriging surrogate model based on the training sample library, the model prediction performance is verified by calculating the coefficient of determination, maximum absolute error, and / or root mean square error.
16. The apparatus as claimed in claim 9, characterized in that, The fatigue analysis of the connecting bolts between the turbine top cover and the seat ring based on the prediction results includes: Stress response data prediction is performed on any set of design variable parameters using the Kriging surrogate model; Based on the equivalent stress calculation model of the modified Goodman mean stress criterion, the symmetrical cyclic stress amplitude of the predicted stress response data is calculated. Using the standard SN curve of the material, the fatigue life value corresponding to the design variable parameter is calculated through the stress-life relationship equation.
17. A computer device, characterized in that, include: One or more processors; The processor is used to execute one or more programs; When the one or more programs are executed by the one or more processors, the fatigue analysis method for the connecting bolts between the turbine top cover and the seat ring as described in any one of claims 1 to 8 is implemented.
18. A computer-readable storage medium, characterized in that, It contains a computer program, which, when executed, implements the fatigue analysis method for the connecting bolts between the turbine top cover and the seat ring as described in any one of claims 1 to 8.