Structural Engineering and Mechanics

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

A general active-learning method for surrogate-based structural reliability analysis

  • Zha, Congyi (School of Mechanical Engineering and Automation, Northeastern University) ;
  • Sun, Zhili (School of Mechanical Engineering and Automation, Northeastern University) ;
  • Wang, Jian (School of Mechanical Engineering and Automation, Northeastern University) ;
  • Pan, Chenrong (Department of General Education, Anhui Xinhua University) ;
  • Liu, Zhendong (School of Mechanical Engineering and Automation, Northeastern University) ;
  • Dong, Pengfei (School of Mechanical Engineering and Automation, Northeastern University)
  • Received : 2021.12.16
  • Accepted : 2022.04.28
  • Published : 2022.07.25
⟨ Previous Next ⟩

Abstract

Surrogate models aim to approximate the performance function with an active-learning design of experiments (DoE) to obtain a sufficiently accurate prediction of the performance function's sign for an inexpensive computational demand in reliability analysis. Nevertheless, many existing active-learning methods are limited to the Kriging model, while the uncertainties of the Kriging itself affect the reliability analysis results. Moreover, the existing general active-learning methods may not achieve a fully satisfactory balance between accuracy and efficiency. Therefore, a novel active-learning method GLM-CM is constructed to yield the issues, which conciliates several merits of existing methods. To demonstrate the performance of the proposed method, four examples, concerning both mathematical and engineering problems, were selected. By benchmarking obtained results with literature findings, various surrogate models combined with the proposed method not only provide an accurate reliability evaluation while highly alleviating the computational burden, but also provides a satisfactory balance between accuracy and efficiency compared to the other reliability methods.

Keywords

Acknowledgement

The research described in this paper was financially supported by the National Natural Science Foundation of China (Grant NO. 51775097, 51875095) and the Fundamental Research Funds for the Central Universities (Grant NO. N180303031). The financial supports are gratefully acknowledged.

References

  1. Ameryan, A., Ghalehnovi, M. and Rashki, M. (2022), "AK-SESC: a novel reliability procedure based on the integration of active learning kriging and sequential space conversion method", Reliab. Eng. Syst. Saf., 217, 108036. https://doi.org/10.1016/j.ress.2021.108036.
  2. Bichon, B.J., Eldred, M.S., Swiler, L.P., Mahadevan, S. and McFarland, J.M. (2008), "Efficient global reliability analysis for nonlinear implicit performance functions", Aiaa J., 46(10), 2459-2468. https://doi.org/10.2514/1.34321.
  3. Cao, R., Sun, Z., Wang, J. and Guo, F. (2021), "An efficient reliability analysis strategy for low failure probability problems", Struct. Eng. Mech., 78(2), 209-218. https://doi.org/10.12989/sem.2021.78.2.209.
  4. Cao, R., Sun, Z., Wang, J. and Zhang, Y. (2020), "An efficient and time-saving reliability analysis strategy for complex mechanical structure", IEEE Access, 8, 171281-171291. https://doi.org/10.1109/access.2020.3020314.
  5. Cheng, K. and Lu, Z.Z. (2020), "Structural reliability analysis based on ensemble learning of surrogate models", Struct. Saf., 83, 101905. https://doi.org/10.1016/j.strusafe.2019.101905.
  6. Cheng, K., Lu, Z., Ling, C. and Zhou, S. (2020), "Surrogate-assisted global sensitivity analysis: an overview", Struct. Multidisc. Optim., 61(3), 1187-1213. https://doi.org/10.1007/s00158-019-02413-5.
  7. Echard, B., Gayton, N. and Lemaire, M. (2011), "AK-MCS: An active learning reliability method combining Kriging and Monte Carlo Simulation", Struct. Saf., 33(2), 145-154. https://doi.org/10.1016/j.strusafe.2011.01.002.
  8. Guimaraes, H., Matos, J.C. and Henriques, A.A. (2018), "An innovative adaptive sparse response surface method for structural reliability analysis", Struct. Saf., 73, 12-28. https://doi.org/10.1016/j.strusafe.2018.02.001.
  9. Hong, L., Li, H. and Peng, K. (2021), "A combined radial basis function and adaptive sequential sampling method for structural reliability analysis", Appl. Math. Model., 90, 375-393. https://doi.org/10.1016/j.apm.2020.08.042.
  10. Jiang, C., Qiu, H., Yang, Z., Chen, L., Gao, L. and Li, P. (2019), "A general failure-pursuing sampling framework for surrogate-based reliability analysis", Reliab. Eng. Syst. Saf., 183, 47-59. https://doi.org/10.1016/j.ress.2018.11.002.
  11. Jing, Z., Chen, J. and Li, X. (2019), "RBF-GA: An adaptive radial basis function metamodeling with genetic algorithm for structural reliability analysis", Reliab. Eng. Syst. Saf., 189, 42-57. https://doi.org/10.1016/j.ress.2019.03.005.
  12. Keshtegar, B. (2018), "Conjugate finite-step length method for efficient and robust structural reliability analysis", Struct. Eng. Mech., 65(4), 415-422. https://doi.org/10.12989/sem.2018.65.4.415.
  13. Keshtegar, B. and Chakraborty, S. (2018), "A hybrid self-adaptive conjugate first order reliability method for robust structural reliability analysis", Appl. Math. Model., 53, 319-332. https://doi.org/10.1016/j.apm.2017.09.017.
  14. Keshtegar, B. and Hao, P. (2017), "A hybrid self-adjusted mean value method for reliability-based design optimization using sufficient descent condition", Appl Math. Model., 41, 257-270. https://doi.org/10.1016/j.apm.2016.08.031.
  15. Keshtegar, B. and Kisi, O. (2017), "M5 model tree and Monte Carlo simulation for efficient structural reliability analysis", Appl. Math. Model., 48, 899-910. https://doi.org/https://doi.org/10.1016/j.apm.2017.02.047.
  16. Keshtegar, B. and Kisi, O. (2018), "RM5Tree: Radial basis M5 model tree for accurate structural reliability analysis", Reliab. Eng. Syst. Saf., 180, 49-61. https://doi.org/https://doi.org/10.1016/j.ress.2018.06.027.
  17. Keshtegar, B., Meng, D., Ben Seghier, M.E.A., Xiao, M., Trung, N.T. and Bui, D.T. (2021), "A hybrid sufficient performance measure approach to improve robustness and efficiency of reliability-based design optimization", Eng. Comput., 37(3), 1695-1708. https://doi.org/10.1007/s00366-019-00907-w.
  18. Kolahchi, R., Tian, K., Keshtegar, B., Li, Z., Trung, N.T. and Thai, D.K. (2020), "AK-GWO: a novel hybrid optimization method for accurate optimum hierarchical stiffened shells", Eng. Comput., 1-13. https://doi.org/10.1007/s00366-020-01124-6.
  19. Lee, C.H. and Kim, Y. (2019), "Probabilistic flaw assessment of a surface crack in a mooring chain using the first- and second-order reliability method", Marine Struct., 63, 1-15. https://doi.org/10.1016/j.marstruc.2018.09.003.
  20. Li, X., Gong, C., Gu, L., Gao, W., Jing, Z. and Su, H. (2018), "A sequential surrogate method for reliability analysis based on radial basis function", Struct. Saf., 73, 42-53. https://doi.org/10.1016/j.strusafe.2018.02.005.
  21. Luo, C., Keshtegar, B., Zhu, S.P., Taylan, O. and Niu, X.P. (2022), "Hybrid enhanced Monte Carlo simulation coupled with advanced machine learning approach for accurate and efficient structural reliability analysis", Comput. Meth. Appl. Mech. Eng., 388, 114218. https://doi.org/https://doi.org/10.1016/j.cma.2021.114218.
  22. Moustapha, M. and Sudret, B. (2019), "Surrogate-assisted reliability-based design optimization: a survey and a unified modular framework", Struct. Multidisc. Optim., 60(5), 2157-2176. https://doi.org/10.1007/s00158-019-02290-y.
  23. Papaioannou, I. and Straub, D. (2021), "Combination line sampling for structural reliability analysis", Struct. Saf., 88, 102025. https://doi.org/10.1016/j.strusafe.2020.102025.
  24. Shi, L., Sun, B. and Ibrahim, D.S. (2019), "An active learning reliability method with multiple kernel functions based on radial basis function", Struct. Multidisc. Optim., 60(1), 211-229. https://doi.org/10.1007/s00158-019-02210-0.
  25. Shi, Y., Lu, Z., He, R., Zhou, Y. and Chen, S. (2020), "A novel learning function based on Kriging for reliability analysis", Reliab. Eng. Syst Saf., 198, 106857. https://doi.org/10.1016/j.ress.2020.106857.
  26. Sun, Z., Wang, J., Li, R. and Tong, C. (2017), "LIF: A new Kriging based learning function and its application to structural reliability analysis", Reliab. Eng. Syst. Saf., 157, 152-165. https://doi.org/10.1016/j.ress.2016.09.003.
  27. Teixeira, R., Nogal, M. and O'Connor, A. (2021), "Adaptive approaches in metamodel-based reliability analysis: A review", Struct. Saf., 89. 102019. https://doi.org/10.1016/j.strusafe.2020.102019.
  28. Vahedi, J., Ghasemi, M.R. and Miri, M. (2018), "Structural reliability assessment using an enhanced adaptive Kriging method", Struct. Eng. Mech., 66(6), 677-691. https://doi.org/10.12989/sem.2018.66.6.677.
  29. Wang, J. and Sun, Z.L. (2018), "The stepwise accuracy-improvement strategy based on the Kriging model for structural reliability analysis", Struct. Multidisc. Optim., 58(2), 595-612. https://doi.org/10.1007/s00158-018-1911-9.
  30. Wang, J., Sun, Z., Cao, R. and Yan, Y. (2020), "An efficient and robust adaptive Kriging for structural reliability analysis", Struct. Multidisc. Optim., 62(6), 3189-3204. https://doi.org/10.1007/s00158-020-02666-5.
  31. Wang, Z.Y. and Shafieezadeh, A. (2021), "Metamodel-based subset simulation adaptable to target computational capacities: the case for high-dimensional and rare event reliability analysis", Struct. Multidisc. Optim., 64(2), 649-675. https://doi.org/10.1007/s00158-021-02864-9.
  32. Wen, Z., Pei, H., Liu, H. and Yue, Z. (2016), "A Sequential Kriging reliability analysis method with characteristics of adaptive sampling regions and parallelizability", Relia. Eng. Syst. Saf., 153, 170-179. https://doi.org/10.1016/j.ress.2016.05.002.
  33. Xiao, N.C., Zuo, M.J. and Guo, W. (2018), "Efficient reliability analysis based on adaptive sequential sampling design and cross-validation", Appl. Math. Model., 58, 404-420. https://doi.org/10.1016/j.apm.2018.02.012.
  34. Xiao, N.C., Zuo, M.J. and Zhou, C.N. (2018), "A new adaptive sequential sampling method to construct surrogate models for efficient reliability analysis", Reliab. Eng. Syst. Saf., 169, 330-338. https://doi.org/10.1016/j.ress.2017.09.008.
  35. Xu, C., Chen, W., Ma, J., Shi, Y. and Lu, S. (2020), "AK-MSS: An adaptation of the AK-MCS method for small failure probabilities", Struct. Saf., 86, 101971. https://doi.org/10.1016/j.strusafe.2020.101971.
  36. Yang, X., Liu, Y. and Ma, P. (2017), "Structural reliability analysis under evidence theory using the active learning kriging model", Eng. Optim., 49(11), 1922-1938. https://doi.org/10.1080/0305215x.2016.1277063.
  37. Yi, J., Zhou, Q., Cheng, Y. and Liu, J. (2020), "Efficient adaptive Kriging-based reliability analysis combining new learning function and error-based stopping criterion", Struct. Multidisc. Optim., 62(5), 2517-2536. https://doi.org/10.1007/s00158-020-02622-3.
  38. Zhang, J.H., Xiao, M. and Gao, L. (2019), "An active learning reliability method combining Kriging constructed with exploration and exploitation of failure region and subset simulation", Reliab. Eng. Syst Saf., 188, 90-102. https://doi.org/10.1016/j.ress.2019.03.002.
  39. Zhang, W.T. and Xiao, Y.Q. (2020), "Decomposable polynomial response surface method and its adaptive order revision around most probable point", Struct. Eng. Mech., 76(6), 675-685. https://doi.org/10.12989/sem.2020.76.6.675.
  40. Zhang, X., Pandey, M.D., Yu, R. and Wu, Z. (2021), "HALK: A hybrid active-learning Kriging approach and its applications for structural reliability analysis", Eng. Comput., 1-17. https://doi.org/10.1007/s00366-021-01308-8.
  41. Zhang, X.B., Lu, Z.Z. and Cheng, K. (2021), "AK-DS: An adaptive Kriging-based directional sampling method for reliability analysis", Mech. Syst. Signal Pr., 156, 107610. https://doi.org/10.1016/j.ymssp.2021.107610.
  42. Zhang, X.F., Wang, L. and Sorensen, J.D. (2019), "REIF: A novel active-learning function toward adaptive Kriging surrogate models for structural reliability analysis", Reliab. Eng. Syst Saf., 185, 440-454. https://doi.org/10.1016/j.ress.2019.01.014.
  43. Zhang, Y., Sun, Z., Yan, Y., Yu, Z. and Wang, J. (2020), "A novel reliability analysis method based on Gaussian process classification for structures with discontinuous response", Struct. Eng. Mech., 75(6), 771-784. https://doi.org/10.12989/sem.2020.75.6.771.
  44. Zhou, Y.C., Lu, Z.Z. and Yun, W.Y. (2020), "Active sparse polynomial chaos expansion for system reliability analysis", Reliab. Eng. Syst. Saf., 202, 107025. https://doi.org/10.1016/j.ress.2020.107025.
  45. Zhu, S.P., Keshtegar, B., Seghier, M.E.A.B., Zio, E. and Taylan, O. (2022), "Hybrid and enhanced PSO: Novel first order reliability method-based hybrid intelligent approaches", Comput. Meth. Appl. Mech. Eng., 393, 114730. https://doi.org/https://doi.org/10.1016/j.cma.2022.114730.