RESEARCH PAPER
Artificial neural network supported monotonic stochastic processes for reliability analysis considering multi-uncertainties
More details
Hide details
1
Beihang University, China
Submission date: 2024-08-31
Final revision date: 2024-09-25
Acceptance date: 2024-12-08
Online publication date: 2024-12-14
Publication date: 2024-12-14
Corresponding author
Di Liu
Beihang University, China
Eksploatacja i Niezawodność – Maintenance and Reliability 2025;27(3):197051
HIGHLIGHTS
- Process, mean function and parameter uncertainties are considered simultaneously.
- IG and Gamma processes are cooperated with ANN.
- BMA method is introduced to estimate the model parameters and probabilities.
KEYWORDS
TOPICS
ABSTRACT
Focusing on nonmonotonic degradation processes, we have cooperated artificial neural network (ANN) with Wiener process to utilize its powerful ability on curve fitting. While, the degradation processes of some actual products are determined as monotonic. Furthermore, the process uncertainty issue is also neglected, which is inevitable in engineering practice. Hence, focusing on monotonic degradation dataset, this research introduces ANN-based stochastic process for reliability analysis under multiple uncertainties, including random effects, process uncertainty and mean function uncertainty. The ANN-supported inverse Gaussian and Gamma process models subject to random effects are built. The related parameter estimation and updating methods are also constructed by utilizing moment estimation (ME), Akaike information criterion (AIC) and fully Bayesian inference methods. According to the simulation experiment and actual case study, the proposed method provides higher accuracies on population degradation modeling and monitoring individual degradation prediction.
ACKNOWLEDGEMENTS
This study was co-supported by the National Natural Science Foundation of China (52105045, 52475046), the Aviation Science Foundation (2022Z027051001), Ningbo Key R&D Program (2023Z010), Beijing Natural Science Foundation (L221008) and the Foundation of Tianmushan Laboratory (TK-2023-C-006).
REFERENCES (39)
1.
Ma ZH, Nie SL, Liao HT. A load spectra design method for multi-stress accelerated testing. Journal of Risk and Reliability 2022; 236(6): 994-1006.
https://doi.org/10.1177/174800....
2.
He R, Chen GM, Shen XY, et al. Reliability assessment of repairable closed-loop process systems under uncertainties. ISA Transactions 2020; 104: 222-232.
https://doi.org/10.1016/j.isat....
3.
Li ZL, Zheng ZX and Rachid O. A prognostic methodology for power MOSFETs under thermal stress using echo state network and particle filter. Microelectronics Reliability 2018; 88: 350-354.
https://doi.org/10.1016/j.micr....
4.
Ma R, Yang T, Breaz E, et al. Data-driven proton exchange membrane fuel cell degradation predication through deep learning method. Applied Energy 2018; 231: 102-115.
https://doi.org/10.1016/j.apen....
5.
Chen X, Liu Z, Wang J, et al. An adaptive prediction model for the remaining life of an Li-ion battery based on the fusion of the two-phase wiener process and an extreme learning machine. Electronics 2021; 10: 540.
https://doi.org/10.3390/electr....
6.
Hong W, Wang SP, Tomovic MM, et al. A novel indicator for mechanical failure and life prediction based on debris monitoring. IEEE Trans Reliab 2016; 66: 161-169.
https://doi.org/10.1109/TR.201....
7.
Nie SL, Song YX, Ma ZH, Yin FL, Ji H. Reliability assessment of PEEK/17-4PH stainless steel tribopair under seawater lubrication. Journal of Risk and Reliability 2023; 237(1): 29-39.
https://doi.org/10.1177/174800....
8.
Yang CY, Ma J, Wang XD, et al. A novel based-performance degradation indicator 456 RUL prediction model and its application in rolling bearing. ISA Transactions 2021; 121: 349-364.
https://doi.org/10.1016/j.isat....
10.
Pan DH, Wei YT, Fang HZ, et al. A reliability estimation approach via Wiener degradation model with measurement errors. Applied Mathematics and Computation 2018; 320: 131-141.
https://doi.org/10.1016/j.amc.....
11.
Dong QL, Cui LR and Si SB. Reliability and availability analysis of stochastic degradation systems based on bivariate wiener processes. Applied Mathematical Modelling 2019; 79: 414-433.
https://doi.org/10.1016/j.apm.....
12.
Park C and Padgett WJ. Accelerated degradation models for failure based on geometric Brownian motion and gamma processes. Lifetime Data Analysis 2005; 11: 511-527.
https://doi.org/10.1007/s10985....
14.
Ye ZS, Chen LP, Tang LC, et al. Accelerated degradation test planning using the inverse gaussian process. IEEE Transactions on Reliability 2014; 63: 750-763.
https://doi.org/10.1109/TR.201....
15.
Peng CY. Inverse Gaussian processes with random effects and explanatory variables for degradation data. Technometrics 2015; 57: 100-111.
https://doi.org/10.1080/004017....
16.
Jiang PH, Wang BX, Wang XF, et al. Inverse Gaussian process based reliability analysis for constant-stress accelerated degradation data. Applied Mathematical Modelling 2022; 105: 137-148.
https://doi.org/10.1016/j.apm.....
17.
Tseng ST, Balakrishnan N and Tsai CC. Optimal step-stress accelerated degradation test plan for gamma degradation processes. IEEE Transactions on Reliability 2009; 58: 611-618.
https://doi.org/10.1109/TR.200....
18.
Wu B, Cui LR and Yin J. Reliability and maintenance of systems subject to Gamma degradation and shocks in dynamic environments. Applied Mathematical Modelling 2021; 96: 367-381.
https://doi.org/10.1016/j.apm.....
20.
Sugiura N. Further analysis of the data by Akaike's information criterion and the finite corrections. Commun Stat Theory Methods 1978; 7: 13-26.
https://doi.org/10.1080/036109....
23.
Liu D, Wang SP, Zhang C, et al. Bayesian model averaging based reliability analysis method for monotonic degradation dataset based on inverse Gaussian process and Gamma process. Reliability Engineering & System Safety 2018; 180: 25-38.
https://doi.org/10.1016/j.ress....
24.
Liu D, Wang SP and Tomovic MM. Degradation modeling method for rotary lip seal based on failure mechanism analysis and stochastic process. Eksploatacja i Niezawodnosc-Maintenance and Reliability 2020; 22: 381-390. DOI:
https://doi.org/10.17531/ein.2....
25.
Peng WW, Li YF, Yang YJ, et al. Leveraging Degradation testing and condition monitoring for field reliability analysis with time-varying operating missions. IEEE Transactions on Reliability 2015; 64: 1367-1382.
https://doi.org/10.1109/TR.201....
26.
Peng WW, Li YF, Yang YJ, et al. Bayesian degradation analysis with inverse gaussian process models under time-varying degradation rates. IEEE Transactions on Reliability 2017; 66: 84-96.
https://doi.org/10.1109/TR.201....
27.
Liu K, Zou TJ, Dang W, et al. Misspecification analysis of two phase gamma liner degradation models. Quality and Reliability Engineering International 2020; 36: 2066-2084.
https://doi.org/10.1002/qre.26....
28.
Kong D, Balakrishnan N and Cui LR. Two-phase degradation process model with abrupt jump at change point governed by Wiener process. IEEE Trans Reliab 2017: 66: 1345-1360.
https://doi.org/10.1109/TR.201....
29.
Zhang JX, Si XS, Du DB, et al. Lifetime estimation for multi-phase deteriorating process with random abrupt jumps. Sensors 2019; 19: 1472.
https://doi.org/10.3390/s19061....
30.
Liu D, Wang SP and Cui XY. An artificial neural network supported Wiener process based reliability estimation method considering individual difference and measurement error. Reliability Engineering & System Safety 2021; 218: 108162.
https://doi.org/10.1016/j.ress....
31.
Rodríguez-Picón LA, Rodríguez-Picón AP, Méndez-González LC, et al. Degradation modeling based on gamma process models with random effects. Commun Stat-Simul Comput 2018; 47: 1796-1810.
https://doi.org/10.1080/036109....
32.
Li XY, Wu JP, Ma HG, et al. A random fuzzy accelerated degradation model and statistical analysis. IEEE Transactions on Fuzzy Systems 2018; 26: 1638-1650.
https://doi.org/10.1109/TFUZZ.....
33.
Liu D and Wang SP. A degradation modeling and reliability estimation method based on Wiener process and evidential variable. Reliability Engineering & System Safety 2020; 202: 106957.
https://doi.org/10.1016/j.ress....
34.
Peng WW, Huang HZ, Xie M, et al. A Bayesian approach for system reliability analysis with multilevel pass-fail. lifetime and degradation data sets. IEEE Transactions on Reliability 2013; 62: 689-699.
https://doi.org/10.1109/TR.201....
35.
Peng WW, Li YF, Yang YJ, et al. Inverse Gaussian process models for degradation analysis: a Bayesian perspective. Reliab Eng Syst Saf 2014; 13: 175-89.
https://doi.org/10.1016/j.ress....
36.
Guan Q, Tang YC and Xu AC. Objective Bayesian analysis accelerated degradation test based on Wiener process models. Applied Mathematical Modelling 2016; 40: 2743-55.
https://doi.org/10.1016/j.apm.....
37.
Jia X. Reliability analysis for Weibull distribution with homogeneous heavily censored data based on Bayesian and least-squares methods. Applied Mathematical Modelling 2020; 83: 169-188.
https://doi.org/10.1016/j.apm.....
38.
Guo JY, Li YF, Peng WW, et al. Bayesian information fusion method for reliability analysis with failure‐time data and degradation data. Quality and Reliability Engineering International 2022; 38: 1944-1956.
https://doi.org/10.1002/qre.30....
39.
Liu D, Wang SP. An artificial neural network supported stochastic process for degradation modeling and prediction. Reliability Engineering & System Safety 2021; 214 (5):107738.
https://doi.org/10.1016/j.ress....