A Fourth-Order Moment Method Based on Back Propagation Neural Network for High-Dimensional Nonlinear Reliability Analysis
Source abstract
Abstract
Reliability analysis of complex engineering products often involves high-dimensional nonlinear state functions, with random variable distributions hard to determine due to limited samples, restricting the fourth-order moment method that fails to link moments of variables and state functions. This study proposes a method combining a back propagation (BP) neural network and a fourth-order moment method: a BP neural network surrogates the mapping between the model approximation variables and the state function, generating samples for estimating the first-fourth-order moments of the state function, and thus performing reliability analyses based on the fourth-order moment method. Validation shows the BP model outperforms Kriging in predicting high-dimensional nonlinear functions; it aligns with Monte Carlo simulation (MCS) results in rolling bearing reliability analysis with higher efficiency and applies to time-varying fatigue analysis. This method overcomes limitations of the fourth-order moment method, offers higher accuracy than existing surrogate-based methods, and retains the efficiency of moment methods, suitable for limited-sample and time-varying scenarios.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Probabilistic and Robust Engineering Design · Structural Health Monitoring Techniques · Infrastructure Maintenance and Monitoring
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Beijing Spacecraft, Beijing 100080, China
College of Power and Energy Engineering, Harbin Engineering University, Harbin 150001, China
School of Mechanical Engineering and Automation, Beihang University, Beijing 102206, China
Funding
Key Research and Development Program of Heilongjiang Province · Heilongjiang Provincial Natural Science Foundation · Fundamental Research funds for the Central Universities · Open Project of Key Laboratory of the Ministry of Education
References (33)
Show source-provided references
1. Accelerating reliability analysis of deteriorated simply supported concrete beam with a newly developed approach: MCS, FORM and ANN10.1016/j.istruc.2024.105962 ↗
2. Liu, J., Liu, Y., Wang, G., Lu, N., Cui, J., and Wang, H. (2024). Fatigue Reliability Assessment for Orthotropic Steel Decks: Considering Multicrack Coupling Effects. Metals, 14.10.3390/met14030272 ↗
3. 3D slope reliability analysis based on the intelligent response surface methodology10.1007/s10064-020-01940-6 ↗
4. Reliability-based stability analysis of large rock slopes with different failure mechanisms using response surface methodology10.1007/s12665-022-10624-1 ↗
5. A new computational scheme for structural static stochastic analysis based on Karhunen-Loeve expansion and modified perturbation stochastic finite element method10.1007/s00466-022-02259-7 ↗
6. Huang, J., Yang, Q., Cao, H., and Ma, J. (2024). Structural Reliability Analysis Using Stochastic Finite Element Method Based on Krylov Subspace. Algorithms, 17.10.3390/a17100424 ↗
7. Reliability analysis using bootstrap information criterion for small sample size response functions10.1007/s00158-020-02724-y ↗
8. de la Cruz, R., Salinas, H.S., and Meza, C. (2022). Reliability Estimation for Stress-Strength Model Based on Unit-Half-Normal Distribution. Symmetry, 14.10.3390/sym14040837 ↗
9. A new structural reliability analysis method under non-parameterized probability box variables10.1007/s00158-022-03408-5 ↗
10. An improved high-moment method for reliability analysis10.1007/s00158-017-1715-3 ↗
11. Moment methods for structural reliability10.1016/S0167-4730(00)00027-8 ↗
12. E, S., Wang, Y., Xie, B., and Lu, F. (2024). An Adaptive Kriging-Based Fourth-Moment Reliability Analysis Method for Engineering Structures. Appl. Sci., 14.10.3390/app14083247 ↗
13. Application of first-order reliability method with orthogonal plane sampling for high-dimensional series system reliability analysis10.1016/j.engstruct.2023.115778 ↗
14. A Novel Adaptive Bayesian Model Averaging-Based Multiple Kriging Method for Structural Reliability Analysis10.1109/TR.2024.3389959 ↗
15. Graph Neural Network Surrogate for Seismic Reliability Analysis of Highway Bridge Systems10.1061/JITSE4.ISENG-2264 ↗
16. Adaptive directed support vector machine method for the reliability evaluation of aeroengine structure10.1016/j.ress.2024.110064 ↗
17. Stochastic finite cell method for structural mechanics10.1007/s00466-021-02026-0 ↗
18. Recent advances and applications of surrogate models for finite element method computations: A review10.1007/s00500-022-07362-8 ↗
19. Hands-On Bayesian Neural Networks—A Tutorial for Deep Learning Users10.1109/MCI.2022.3155327 ↗
20. Physics-informed kernel function neural networks for solving partial differential equations10.1016/j.neunet.2024.106098 ↗
21. Zafar, A., Aamir, M., Nawi, N.M., Arshad, A., Riaz, S., Alruban, A., Dutta, A.K., and Almotairi, S. (2022). A Comparison of Pooling Methods for Convolutional Neural Networks. Appl. Sci., 12.10.3390/app12178643 ↗
22. A reliability calculation method based on ISSA-BP neural network10.1108/IJSI-07-2024-0104 ↗
23. Robust optimization design method for structural reliability based on active-learning MPA-BP neural network10.1108/IJSI-10-2022-0129 ↗
24. A novel reliability analysis method combining adaptive relevance vector machine and subset simulation for small failure probability10.1007/s00158-023-03503-1 ↗
25. A Reliability-Based Robust Design Method for the Sealing of Slipper-Swash Plate Friction Pair in Hydraulic Piston Pump10.1109/TR.2018.2805871 ↗
26. Matrix description of differential relations of moment functions in structural reliability sensitivity analysis10.1007/s10483-017-2160-6 ↗
27. Pneumonia Incidence Rate Predictive Model of Nonlinear Time Series Based on Dynamic Learning Rate BP Neural Network
28. Combined relevance vector machine technique and subset simulation importance sampling for structural reliability10.1016/j.apm.2022.09.010 ↗
29. Vibration response-based time-variant reliability and sensitivity analysis of rolling bearings using the first-passage method10.1016/j.ress.2024.110706 ↗
30. An active learning reliability analysis method using adaptive Bayesian compressive sensing and Monte Carlo simulation (ABCS-MCS)10.1016/j.ress.2022.108377 ↗
31. E, S., Wang, Y., Xie, B., and Lu, F. (2023). A Reliability-Based Robust Design Optimization Method for Rolling Bearing Fatigue under Cyclic Load Spectrum. Mathematics, 11.10.3390/math11132843 ↗
32. Time-variant reliability analysis of angular contact ball bearing considering the coupled effect of rolling contact fatigue damage and wear10.1016/j.ress.2023.109667 ↗
33. Adaptive Kriging-based probabilistic subset simulation method for structural reliability problems with small failure probabilities10.1016/j.istruc.2024.107726 ↗