Abstract
To predict reliability for highly non-linear and complex model efficiently and accurately, an artificial neural network (ANN) based Monte Carlo method (MCM) is proposed. In this method, ANN trained by backpropagation (BP) algorithm is developed to establish the relationship between inputs and outputs. The trained ANN model is then connected to MCM to predict reliability and reliability sensitivity of structure. To examine the accuracy and efficiency of the proposed method, results obtained by polynomial-FOSM (first-order second moment) method and ANN-AFOSM (advanced first-order second moment) method are provided. Compared with the traditional Monte Carlo method, the time consumed by ANN-MCM, polynomial-FOSM and ANN-AFOSM methods only accounts for 0.14% of the traditional MCM. The reliability analysis and reliability sensitivity analysis results of ANN-MCM method are very close to traditional MCM, polynomial-FOSM method yields large errors, ANN-AFOSM is in between. It shows that the proposed method is of high accuracy and efficiency.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Gobet E, Turkedjiev P (2016) Adaptive importance sampling in least-squares Monte Carlo algorithms for backward stochastic differential equations. Stoch Processes Appl 127(4):1171–1203
Papaioannou I, Papadimitriou C, Straub D (2016) Sequential importance sampling for structural reliability analysis. Struct Saf 62:66–75
Alvarez DA, Uribe F, Hurtado JE (2018) Estimation of the lower and upper bounds on the probability of failure using subset simulation and random set theory. Mech Syst Signal Process 100:782–801
Eijnden APVD, Hicks MA (2017) Efficient subset simulation for evaluating the modes of improbable slope failure. Comput Geotech 88:267–280
Quaranta G (2011) Finite element analysis with uncertain probabilities. Comput Methods Appl Mech Eng 200(1–4):114–129
Sudret B, Kiureghian AD (2002) Comparison of finite element reliability methods. Probab Eng Mech 17(4):337–348
Mohanraj M, Jayaraj S, Muraleedharan C (2015) Applications of artificial neural networks for thermal analysis of heat exchangers—a review. Int J Therm Sci 90(4):150–172
Chojaczyk AA, Teixeira AP, Neves LC et al (2015) Review and application of artificial neural networks models in reliability analysis of steel structures. Struct Saf 52(3):78–89
Lv Z, Song S, Li H et al (2009) Reliability and reliability sensitivity analysis for structure. Science Press, Beijing (in Chinese)
Jensen JJ (2015) Fatigue damage estimation in non-linear systems using a combination of Monte Carlo simulation and the first order reliability method. Mar Struct 44:203–210
Zhang Z, Jian C, Han X, Dean Hu, Yu S (2014) A response surface approach for structural reliability analysis using evidence theory. Adv Eng Softw 69:37–45
Díaz J, Pereira F, Romera L et al (2012) Probabilistic assessment of the structural failure of single-lap bonded joints. Int J Adhes Adhes 37(9):70–78
Hu Y, Liu S, Ding S, Liao Y (2015) Application of response surface method for contact fatigue reliability analysis of spur gear with consideration of EHL. J Central South Univ 22(7):2549–2556
Hu Y, Liu S, Chang J, Zhang J (2015) An intelligent method for contact fatigue reliability analysis of spur gear under EHL. J Central South Univ 22(9):3389–3396
Nawi MN, Khan et al (2013) A new Levenberg Marquardt based back propagation algorithm trained with cuckoo search. In: The 4th international conference on electrical engineering and informatics (ICEEI 2013), pp 18–23
Cheng J, Li QS, Xiao R (2008) A new artificial neural network-based response surface method for structural reliability analysis. Probab Eng Mech 23(1):51–63
Duan W, Wang Z (2007) Probability strength design of steam turbine blade and sensitivity analysis with respect to random parameters based on response surface method. Proc CSEE 27(5):99–104 (in Chinese)
Li C, Han X (2011) Analysis of reliability sensitivity for gear engagement based on response surface methods. J Aerosp Power 26(3):711–715 (in Chinese)
Schön TB, Svensson A, Murray L et al (2018) Probabilistic learning of nonlinear dynamical systems using sequential Monte Carlo. Mech Syst Signal Process 104:866–883
Li S, Anisetti A (2017) A tribo-dynamic contact fatigue model for spur gear pairs. Int J Fatigue 98:81–91
Wei J, Zhang A, Gao P (2016) A study of spur gear pitting under EHL conditions: theoretical analysis and experiments. Tribol Int 94:146–154
Fajdiga G (2015) Computational fatigue analysis of contacting mechanical elements. Tehnicki Vjesnik 22(1):169–175
Martini A, Escoffier B, Wang Q et al (2006) Prediction of subsurface stress in elastic perfectly plastic rough components. Tribol Lett 23(3):243–251
Dubi A (1999) Monte Carlo applications in systems engineering. Wiley, New York (in Chinese)
Acknowledgements
The work presented in this paper was supported by National Natural Science Foundation of China (Grant no. 51705229).
Author information
Authors and Affiliations
Corresponding author
Additional information
Technical Editor: Marcelo A. Trindade.
Rights and permissions
About this article
Cite this article
Hu, Y., Xiao, Cd. & Shi, Yy. Reliability analysis for highly non-linear and complex model using ANN-MCM simulation. J Braz. Soc. Mech. Sci. Eng. 40, 251 (2018). https://doi.org/10.1007/s40430-018-1163-z
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s40430-018-1163-z