Search for Author, Title, Keyword
RESEARCH PAPER
Degradation generation and prediction based on machine learning methods: A comparative study
,
 
,
 
Jian Shi 1,2
 
 
 
More details
Hide details
1
Academy of Mathematics and Systems Science, Chinese Academy of Sciences, China
 
2
School of Mathematical Sciences, University of Chinese Academy of Sciences, China
 
 
Submission date: 2024-04-27
 
 
Final revision date: 2024-06-24
 
 
Acceptance date: 2024-08-08
 
 
Online publication date: 2024-08-09
 
 
Publication date: 2024-08-09
 
 
Corresponding author
Jian Shi   

Academy of Mathematics and Systems Sciences, Chinese Academy of Sciences, Beijing, China
 
 
Eksploatacja i Niezawodność – Maintenance and Reliability 2025;27(1):192168
 
HIGHLIGHTS
  • The degradation trajectories are generated based on TimeGAN, SVAE, diffusion model, and the segmented sampling method, respectively.
  • The diffusion model is used to synthesize the degradation process.
  • Based on several generative models and predictive networks, evaluation and comparison of both numerical simulations and case studies are realized.
KEYWORDS
TOPICS
ABSTRACT
In engineering practice, degradation analysis often suffers from the small-sample problem. To this end, several generative models are developed to expand the degradation data, based on which both the original data and the synthetic data are used to train neural networks for degradation prediction. However, these methods are rarely compared with each other, and the performances of competitive candidates are not explored. Given this, this paper reviews some machine learning-based methods and performs a comparison among them. Particularly, a segmented sampling method is proposed and the diffusion model is introduced for degradation generation. Results of both numerical simulations and case studies show that none of these methods can perform best in all cases, yet making use of synthetic data improves the predictive performance. Overall, the time-series generative adversarial network and the segmented sampling method are recommended for degradation generation, and the gated recurrent unit network is recommended for prediction.
ACKNOWLEDGEMENTS
We would like to thank the reviewers for their insightful comments and suggestions, which have significantly improved the quality of this paper.
REFERENCES (45)
1.
Ye Z, Xie M. Stochastic modelling and analysis of degradation for highly reliable products. Appl Stoch Models Bus & Ind 2015;31:16–32. https://doi.org/10.1002/asmb.2....
 
2.
Meeker WQ, Escobar LA, Pascual FG. Statistical methods for reliability data. Second edition. Hoboken, NJ: Wiley; 2022.
 
3.
Weerahandi S. Generalized Confidence Intervals. Exact Statistical Methods for Data Analysis, New York, NY: Springer New York; 1995, p. 143–68. https://doi.org/10.1007/978-1-....
 
4.
Chen P, Ye Z, Xiao X. Pairwise model discrimination with applications in lifetime distributions and degradation processes. Naval Research Logistics 2019;66:675–86. https://doi.org/10.1002/nav.21....
 
5.
Wang X, Wang BX, Wu W, Hong Y. Reliability analysis for accelerated degradation data based on the Wiener process with random effects. Quality & Reliability Eng 2020;36:1969–81. https://doi.org/10.1002/qre.26....
 
6.
Song K, Cui L. Fiducial inference-based failure mechanism consistency analysis for accelerated life and degradation tests. Applied Mathematical Modelling 2022;105:340–54. https://doi.org/10.1016/j.apm.....
 
7.
Chen P, Ye Z-S. Uncertainty quantification for monotone stochastic degradation models. Journal of Quality Technology 2018;50:207–19. https://doi.org/10.1080/002240....
 
8.
Lu Y, Shen M, Wang H, Wang X, van Rechem C, Fu T, et al. Machine Learning for Synthetic Data Generation: A Review 2024.
 
9.
De S, Bermudez-Edo M, Xu H, Cai Z. Deep Generative Models in the Industrial Internet of Things: A Survey. IEEE Trans Ind Inf 2022;18:5728–37. https://doi.org/10.1109/TII.20....
 
10.
Goodfellow IJ, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, et al. Generative adversarial nets. Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 2, Cambridge, MA, USA: MIT Press; 2014, p. 2672–80.
 
11.
Kingma DP, Welling M. An Introduction to Variational Autoencoders. Found Trends Mach Learn 2019;12:307–92. https://doi.org/10.1561/220000....
 
12.
Liu J, Qu F, Hong X, Zhang H. A Small-Sample Wind Turbine Fault Detection Method With Synthetic Fault Data Using Generative Adversarial Nets. IEEE Transactions on Industrial Informatics 2019;15:3877–88. https://doi.org/10.1109/TII.20....
 
13.
Liu C, Antypenko R, Sushko I, Zakharchenko O. Intrusion Detection System After Data Augmentation Schemes Based on the VAE and CVAE. IEEE Transactions on Reliability 2022;71:1000–10. https://doi.org/10.1109/TR.202....
 
14.
Booyse W, Wilke DN, Heyns S. Deep digital twins for detection, diagnostics and prognostics. Mechanical Systems and Signal Processing 2020;140:106612. https://doi.org/10.1016/j.ymss....
 
15.
Yu H, Wang QF, Shi JY. Data Augmentation Generated by Generative Adversarial Network for Small Sample Datasets Clustering. Neural Process Lett 2023;55:8365–84. https://doi.org/10.1007/s11063....
 
16.
Zhang W, Li Z, Li G, Zhuang P, Hou G, Zhang Q, et al. GACNet: Generate Adversarial-Driven Cross-Aware Network for Hyperspectral Wheat Variety Identification. IEEE Trans Geosci Remote Sensing 2024;62:1–14. https://doi.org/10.1109/TGRS.2....
 
17.
Zhang W, Zhao W, Li J, Zhuang P, Sun H, Xu Y, et al. CVANet: Cascaded visual attention network for single image super-resolution. Neural Netw 2024;170:622–34. https://doi.org/10.1016/j.neun....
 
18.
Shangguan A, Xie G, Fei R, Mu L, Hei X. Train wheel degradation generation and prediction based on the time series generation adversarial network. Reliability Engineering & System Safety 2023;229:108816. https://doi.org/10.1016/j.ress....
 
19.
Yoon J, Jarrett D, van der Schaar M. Time-series generative adversarial networks. Proceedings of the 33rd International Conference on Neural Information Processing Systems, Red Hook, NY, USA: Curran Associates Inc.; 2019.
 
20.
Shangguan A, Feng N, Mu L, Fei R, Hei X, Xie G. SVAE‐GRU‐based degradation generation and prediction for small samples. Quality & Reliability Eng 2023;39:2851–68. https://doi.org/10.1002/qre.33....
 
21.
Ho J, Jain A, Abbeel P. Denoising diffusion probabilistic models. Proceedings of the 34th International Conference on Neural Information Processing Systems, Red Hook, NY, USA: Curran Associates Inc.; 2020.
 
22.
Ke W, Guo Y, Liu Q, Chen W, Wang P, Luo H, et al. MDM: Meta diffusion model for hard-constrained text generation. Knowledge-Based Systems 2024;283:111147. https://doi.org/10.1016/j.knos....
 
23.
Zeng J, Liu X, Li Z. Radio Anomaly Detection Based on Improved Denoising Diffusion Probabilistic Models. IEEE Communications Letters 2023;27:1979–83. https://doi.org/10.1109/LCOMM.....
 
24.
Dhariwal P, Nichol A. Diffusion Models Beat GANs on Image Synthesis. In: Ranzato M, Beygelzimer A, Dauphin Y, Liang PS, Vaughan JW, editors. Advances in Neural Information Processing Systems, vol. 34, Curran Associates, Inc.; 2021, p. 8780–94.
 
25.
Gupta P, Hayat M, Dhall A, Do T-T. Conditional Distribution Modelling for Few-Shot Image Synthesis with Diffusion Models. ArXiv 2024;abs/2404.16556.
 
26.
Wang Z, Zhang H. Customized Load Profiles Synthesis for Electricity Customers Based on Conditional Diffusion Models. IEEE Trans Smart Grid 2024:1–1. https://doi.org/10.1109/TSG.20....
 
27.
Liu Y, Shen R, Shen X. Novel Uncertainty Quantification through Perturbation-Assisted Sample Synthesis. IEEE Transactions on Pattern Analysis and Machine Intelligence 2024:1–12. https://doi.org/10.1109/TPAMI.....
 
28.
Shen X, Liu Y, Shen R. Boosting Data Analytics with Synthetic Volume Expansion n.d.
 
29.
Efron B, Tibshirani RJ. An Introduction to the Bootstrap. 0 ed. Chapman and Hall/CRC; 1994. https://doi.org/10.1201/978042....
 
30.
Zhou S, Xu A. Exponential Dispersion Process for Degradation Analysis. IEEE Transactions on Reliability 2019;68:398–409. https://doi.org/10.1109/TR.201....
 
31.
Guo J, Wang C, Cabrera J, Elsayed EA. Improved inverse Gaussian process and bootstrap: Degradation and reliability metrics. Reliability Engineering & System Safety 2018;178:269–77. https://doi.org/10.1016/j.ress....
 
32.
Hochreiter S, Schmidhuber J. Long Short-Term Memory. Neural Computation 1997;9:1735–80. https://doi.org/10.1162/neco.1....
 
33.
Cho K, Merrienboer B van, Gülçehre Ç, Bahdanau D, Bougares F, Schwenk H, et al. Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation. Conference on Empirical Methods in Natural Language Processing, 2014. https://doi.org/10.3115/v1/D14....
 
34.
Yang K, Wang Y, Yao Y, Fan S. Remaining useful life prediction via long-short time memory neural network with novel partial least squares and genetic algorithm. Quality and Reliability Engineering International 2021;37:1080–98. https://doi.org/10.1002/qre.27....
 
35.
Ungurean L, Micea MV, Cârstoiu G. Online state of health prediction method for lithium-ion batteries, based on gated recurrent unit neural networks. International Journal of Energy Research 2020;44:6767–77. https://doi.org/10.1002/er.541....
 
36.
Lin M, You Y, Wang W, Wu J. Battery health prognosis with gated recurrent unit neural networks and hidden Markov model considering uncertainty quantification. Reliability Engineering & System Safety 2023;230:108978. https://doi.org/10.1016/j.ress....
 
37.
Sun R, Yang Z, Yang L, Qiao B, Chen X, Gryllias KC. Planetary gearbox spectral modeling based on the hybrid method of dynamics and LSTM. Mechanical Systems and Signal Processing 2020;138:106611. https://doi.org/10.1016/j.ymss....
 
38.
Gu L, Zheng R, Zhou Y, Zhang Z, Zhao K. Remaining useful life prediction using composite health index and hybrid LSTM-SVR model. Quality and Reliability Engineering International 2022;38:3559–78. https://doi.org/10.1002/qre.31....
 
39.
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, et al. Attention is all you need. Proceedings of the 31st International Conference on Neural Information Processing Systems, Red Hook, NY, USA: Curran Associates Inc.; 2017, p. 6000–10.
 
40.
Wen Q, Zhou T, Zhang C, Chen W, Ma Z, Yan J, et al. Transformers in Time Series: A Survey. International Joint Conference on Artificial Intelligence, 2022. https://doi.org/10.24963/ijcai....
 
41.
Lee S, Hong J, Liu L, Choi W. TS-Fastformer: Fast Transformer for Time-series Forecasting. ACM Trans Intell Syst Technol 2024;15. https://doi.org/10.1145/363063....
 
42.
Song K, Cui L. A common random effect induced bivariate gamma degradation process with application to remaining useful life prediction. Reliability Engineering & System Safety 2022;219:108200. https://doi.org/10.1016/j.ress....
 
43.
Freitas MA, de Toledo MLG, Colosimo EA, Pires MC. Using degradation data to assess reliability: a case study on train wheel degradation. Quality and Reliability Engineering International 2009;25:607–29. https://doi.org/10.1002/qre.99....
 
44.
Peng C-Y, Cheng Y-S. Student-t Processes for Degradation Analysis. Technometrics 2020;62:223–35. https://doi.org/10.1080/004017....
 
45.
Gretton A, Borgwardt KM, Rasch MJ, Scholkopf B, Smola A. A Kernel Two-Sample Test. Journal of Machine Learning Research 2012;13:723–73.
 
 
CITATIONS (1):
1.
Intelligent Systems in Production Engineering and Maintenance IV
Ziółkowski Jarosław, Grzybowski Bartłomiej
 
eISSN:2956-3860
ISSN:1507-2711
Journals System - logo
Scroll to top