Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content

Advertisement

Springer Nature Link
Log in

Time-dependent reliability prediction using transfer learning

  • Research Paper
  • Published:
Structural and Multidisciplinary Optimization Aims and scope Submit manuscript

Abstract

One of the key challenges in reliability estimation is the acquisition of failure information especially under real-life scenarios or computationally expensive long-run simulations. Due to the lack of failure information, it becomes a challenging task to estimate time-dependent reliability of a structure or component. In this paper, a preliminary study of time-dependent reliability prediction using transfer learning is given by utilizing only current time performance function information. Transfer learning, specifically domain adaptation, is used in this work in order to find a representation in latent space where the statistical properties of nonstationary stochastic processes such as variance are preserved and their distribution parameters at different times are made close to each other. Correlated random samples of the stochastic processes are generated in present and future time intervals in order to find common latent space using domain adaptation via transfer component analysis (TCA). Due to the excellent computational efficiency, a Kriging surrogate model is built in the present interval only using an adaptive sampling strategy. The reliability in the future is predicted using the same surrogate model without retraining it using future performance function information. Monte Carlo simulation (MCS) is used to validate the results of the proposed method. The results show that the proposed method can predict the failure probability of time-dependent problems efficiently with significant accuracy.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

References

  • Andrieu-Renaud C, Sudret B, Lemaire M (2004) The PHI2 method: a way to compute time-variant reliability. Reliab Eng SystSaf 84:75–86

    Article  Google Scholar 

  • das Chagas Moura M, Zio E, Lins ID, Droguett E (2011) Failure and reliability prediction by support vector machines regression of time series data. Reliab Eng Syst Saf 96:1527–1534

    Article  Google Scholar 

  • Echard B, Gayton N, Lemaire M (2011) AK-MCS: an active learning reliability method combining Kriging and Monte Carlo simulation. Struct Saf 33:145–154

    Article  Google Scholar 

  • Gaspar B, Teixeira A, Soares CG (2017) Adaptive surrogate model with active refinement combining Kriging and a trust region method. Reliab Eng Syst Saf 165:277–291

    Article  Google Scholar 

  • Gretton A, Borgwardt K, Rasch M, Schölkopf B, Smola AJ a kernel method for the two-sample-problem, In: Advances in neural information processing systems, 2007. pp 513–520

  • Hawchar L, El Soueidy C-P, Schoefs F (2018) Global Kriging surrogate modeling for general time-variant reliability-based design optimization problems. Struct Multidiscip Optim 58:955–968

    Article  MathSciNet  Google Scholar 

  • Hu Z, Du X (2013a) A sampling approach to extreme value distribution for time-dependent reliability analysis. J Mech Des 135:071003

    Article  Google Scholar 

  • Hu Z, Du X (2013b) Time-dependent reliability analysis with joint up-crossing rates. Struct Multidiscip Optim 48:893–907

    Article  MathSciNet  Google Scholar 

  • Hu Z, Du X (2015a) First order reliability method for time-variant problems using series expansions. Struct Multidiscip Optim 51:1–21

    Article  MathSciNet  Google Scholar 

  • Hu Z, Du X (2015b) Mixed efficient global optimization for time-dependent reliability analysis. J Mech Des 137:051401

    Article  Google Scholar 

  • Hu Z, Mahadevan S (2016) A single-loop kriging surrogate modeling for time-dependent reliability analysis. J Mech Des 138:061406

    Article  Google Scholar 

  • Hu Z, Li H, Du X, Chandrashekhara K (2013) Simulation-based time-dependent reliability analysis for composite hydrokinetic turbine blades. Struct Multidiscip Optim 47:765–781

    Article  Google Scholar 

  • Jiang M, Huang Z, Qiu L, Huang W, Yen GG (2017) Transfer learning-based dynamic multiobjective optimization algorithms. IEEE Trans Evol Comput 22:501–514

    Article  Google Scholar 

  • Kaymaz I, McMahon CA (2005) A response surface method based on weighted regression for structural reliability analysis. Probabilistic Eng Mech 20:11–17

    Article  Google Scholar 

  • Li C-C, Der Kiureghian A (1993) Optimal discretization of random fields. J Eng Mech 119:1136–1154

    Article  Google Scholar 

  • Li M, Wang Z (2018) Confidence-driven design optimization using Gaussian process Metamodeling with insufficient data. J Mech Des 140:121405

    Article  Google Scholar 

  • Lu J, Behbood V, Hao P, Zuo H, Xue S, Zhang G (2015) Transfer learning using computational intelligence: a survey. Knowl-Based Syst 80:14–23

    Article  Google Scholar 

  • Lutes LD, Sarkani S (2004) Random vibrations: analysis of structural and mechanical systems, Butterworth-Heinemann

  • Matasci G, Volpi M, Kanevski M, Bruzzone L, Tuia D (2015) Semisupervised transfer component analysis for domain adaptation in remote sensing image classification. IEEE Trans Geosci Remote Sens 53:3550–3564

    Article  Google Scholar 

  • Matsubara T, Norinaga Y, Ozawa Y, Cui Y (2018) Policy Transfer from Simulations to Real World by Transfer Component Analysis. In: 2018 IEEE 14th International Conference on Automation Science and Engineering (CASE). IEEE, pp 264–269

  • Min ATW, Sagarna R, Gupta A, Ong Y-S, Goh CK (2017) Knowledge transfer through machine learning in aircraft design. IEEE Comput Intell Mag 12:48–60

    Article  Google Scholar 

  • Mourelatos ZP, Majcher M, Pandey V, Baseski I (2015) Time-dependent reliability analysis using the total probability theorem. J Mech Des 137:031405

    Article  Google Scholar 

  • Pan SJ, Yang Q (2009) A survey on transfer learning. IEEE Trans Knowl Data Eng 22:1345–1359

    Article  Google Scholar 

  • Pan SJ, Tsang IW, Kwok JT, Yang Q (2010) Domain adaptation via transfer component analysis. IEEE Trans Neural Netw 22:199–210

    Article  Google Scholar 

  • Rice SO (1944) Mathematical analysis of random noise. Bell System Technical Journal 23:282–332

    Article  MathSciNet  Google Scholar 

  • Schölkopf B, Smola A, Müller K-R (1998) Nonlinear component analysis as a kernel eigenvalue problem. Neural Comput 10:1299–1319

    Article  Google Scholar 

  • Shawe-Taylor J, Cristianini N (2004) Kernel methods for pattern analysis. Cambridge university press

  • Sheu S-H, Yeh RH, Lin Y-B, Juang M-G (2001) A Bayesian approach to an adaptive preventive maintenance model. Reliab Eng Syst Saf 71:33–44

    Article  Google Scholar 

  • Smola A, Gretton A, Song L, Schölkopf B A (2007) Hilbert space embedding for distributions. In: International Conference on Algorithmic Learning Theory, Springer, pp 13–31

  • Stein M (1987) Large sample properties of simulations using Latin hypercube sampling. Technometrics 29:143–151

    Article  MathSciNet  Google Scholar 

  • Tee KF, Khan LR, Li H (2014) Application of subset simulation in reliability estimation of underground pipelines reliability. Eng Syst Saf 130:125–131

    Article  Google Scholar 

  • Vennell R (2011) Estimating the power potential of tidal currents and the impact of power extraction on flow speeds. Renew Energy 36:3558–3565

    Article  Google Scholar 

  • Wang Z, Chen W (2017) Confidence-based adaptive extreme response surface for time-variant reliability analysis under random excitation. Struct Saf 64:76–86

    Article  Google Scholar 

  • Wang Z, Wang P (2012) A nested extreme response surface approach for time-dependent reliability-based design optimization. J Mech Des 134:121007

    Google Scholar 

  • Wang Z, Wang Z, Yu S, Zhang K (2019) Time-dependent mechanism reliability analysis based on envelope function and vine-copula function. Mech Mach Theory 134:667–684

    Article  Google Scholar 

  • Wang Z, Liu J, Yu S (2019a) Time-variant reliability prediction for dynamic systems using partial information. Reliab Eng Syst Saf. https://doi.org/10.1016/j.ress.2019.106756

  • Wang Z, Wang Z, Yu S, Cheng X (2019b) Time-dependent concurrent reliability-based design optimization integrating the time-variant B-distance index. J Mech Des 141(9):091403.1–091403.8

    Google Scholar 

  • Wei P, Wang Y, Tang C (2017) Time-variant global reliability sensitivity analysis of structures with both input random variables and stochastic processes. Struct Multidiscip Optim 55:1883–1898

    Article  MathSciNet  Google Scholar 

  • Weiss K, Khoshgoftaar TM, Wang D (2016) A survey of transfer learning. Journal of Big data 3:9

    Article  Google Scholar 

  • Wu X, Kozlowski T, Meidani H (2018) Kriging-based inverse uncertainty quantification of nuclear fuel performance code BISON fission gas release model using time series measurement data. Reliab Eng Syst Saf 169:422–436

    Article  Google Scholar 

  • Xiao N-C, Zuo MJ, Zhou C (2018) A new adaptive sequential sampling method to construct surrogate models for efficient reliability analysis. Reliab Eng Syst Saf 169:330–338

    Article  Google Scholar 

  • Yang HZ, Zheng W (2011) Metamodel approach for reliability-based design optimization of a steel catenary riser. J Mar Sci Technol 16:202–213

    Article  Google Scholar 

  • Yang X, Liu Y, Mi C, Wang X (2018) Active learning Kriging model combining with kernel-density-estimation-based importance sampling method for the estimation of low failure probability. J Mech Des 140:051402

    Article  Google Scholar 

  • Yu S, Wang Z (2018) A novel time-variant reliability analysis method based on failure processes decomposition for dynamic uncertain structures. J Mech Des 140:051401

    Article  Google Scholar 

  • Yu S, Wang Z (2019) A general decoupling approach for time- and space-variant system reliability-based design optimization. Comput Methods Appl Mech Eng 357:112608.1–112608.11260823

  • Yu S, Wang Z, Meng D (2018) Time-variant reliability assessment for multiple failure modes and temporal parameters. Struct Multidiscip Optim 58:1705–1717

    Article  MathSciNet  Google Scholar 

  • Zhang D, Han X, Jiang C, Liu J, Li Q (2017) Time-dependent reliability analysis through response surface method. J Mech Des 139:041404

    Google Scholar 

Download references

Funding

This material is based upon the work supported by the National Natural Science Foundation of China under the Contract No. 11472075 and the Fundamental Research Funds for Central Universities under Contract No. ZYGX2019J043.

Author information

Authors and Affiliations

  1. School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China, Chengdu, 611731, People’s Republic of China

    Tayyab Zafar & Zhonglai Wang

  2. National University of Sciences and Technology, Islamabad, Pakistan

    Tayyab Zafar

Authors
  1. Tayyab Zafar
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zhonglai Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Zhonglai Wang.

Ethics declarations

Conflict of interest

The authors declared that they have no conflicts of interest in this work. We declare that we do not have any commercial or associative interest that represents a conflict of interest in connection with the work submitted.

Replication of results

The results presented in this work are based on the flowchart in Fig. 1. In order to replicate the results, a series of Matlab code is provided as supplementary material. The series of codes of the proposed approach are attached in the Supplementary Material. The attached Matlab file named as “Main.m” and other function files can be utilized to compute the time-dependent reliability in case 4.2. For replication of the results of other cases in the proposed work, information of input variables and random process can be modified in the corresponding source codes. It should be noted that the results presented in the paper are average of 20 individual runs.

Additional information

Responsible Editor: Byeng D Youn

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zafar, T., Wang, Z. Time-dependent reliability prediction using transfer learning. Struct Multidisc Optim 62, 147–158 (2020). https://doi.org/10.1007/s00158-019-02475-5

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00158-019-02475-5

Keywords

Search

Navigation