考虑多部件间随机相关性的多阶段退化系统剩余寿命预测方法

PDF(2409 KB)

振动与冲击 ›› 2025, Vol. 44 ›› Issue (10) : 311-322.

故障诊断分析

考虑多部件间随机相关性的多阶段退化系统剩余寿命预测方法

朱彦军，李可，吴斌，石慧*

作者信息 +

Remaining useful life prediction method of multi-stage degradation system considering random correlation among multiple components

ZHU Yanjun, LI Ke, WU Bin, SHI Hui*

Author information +

文章历史 +

摘要

多部件系统中部件之间退化可能存在不同程度的相互影响，使得多部件系统常常具有多阶段的退化特征。针对上述问题，本文考虑多部件系统各部件之间相互作用对退化模式的影响，提出一种基于维纳过程的连续退化双向随机相关影响的多阶段系统退化建模与剩余寿命预测方法。首先利用突变点检测建立考虑双向随机相关影响的多阶段维纳过程退化模型，用来描述部件间随机相互影响对多部件系统退化过程产生的影响。其次为了反应各部件退化异质性，并考虑部件的退化速率是由自身固有的退化速率和与其相关的部件产生的退化率相互作用两部分组成，将系统各阶段的漂移系数和扩散系数定义为随机参数，运用期望最大化算法估计未知参数。最后采用贝叶斯算法更新后验参数分布，预测突变点位置，根据首达时间推导考虑各部件之间退化随机相关性的多阶段退化系统剩余寿命的表达式，并通过数值模拟和C-MAPSS数据集验证了该方法的有效性。

Abstract

Degradation between components in multi-component systems may have different degrees of mutual influence, which makes multi-component systems often have multi-stage degradation characteristics. In view of the above problems, this paper considers the influence of the interaction between the components of the multi-component system on the degradation mode, and proposes a multi-stage system degradation modeling and remaining useful life prediction method based on Wiener process with continuous degradation bidirectional random correlation effect. Firstly, a multi-stage Wiener process degradation model considering the influence of bidirectional random correlation is established by using the mutation point detection to describe the influence of random interaction between components on the degradation process of multi-component system. Secondly, to reflect the degradation heterogeneity of each component, and consider that the degradation rate of the component is composed of two parts: its own inherent degradation rate and the degradation rate generated by its related components. The drift coefficient and diffusion coefficient of each stage of the system are defined as random parameters, and the expectation maximization algorithm is used to estimate the unknown parameters. Finally, the Bayesian algorithm is used to update the posterior parameter distribution, predict the location of the mutation point, and derive the expression of the remaining life of the multi-stage degradation system considering the random correlation of degradation among the components according to the first passage time. The effectiveness of the method is verified by numerical simulation and C-MAPSS dataset.

关键词

多部件 / 多阶段 / 剩余寿命预测 / 随机相关性 / 贝叶斯算法

引用本文

EndNote

Ris (Procite)

Bibtex

导出引用

朱彦军, 李可, 吴斌, 石慧. 考虑多部件间随机相关性的多阶段退化系统剩余寿命预测方法[J]. 振动与冲击, 2025, 44(10): 311-322

ZHU Yanjun, LI Ke, WU Bin, SHI Hui. Remaining useful life prediction method of multi-stage degradation system considering random correlation among multiple components[J]. Journal of Vibration and Shock, 2025, 44(10): 311-322

参考文献

[1] Zhang J X, Zhang J L, Zhang Z X, et al. Remaining useful life prediction for stochastic degrading devices incorporating quantization[J]. Reliability Engineering & System Safety, 2024: 110223.
[2] Wu B, Zeng J, Shi H, et al. Multi-sensor information fusion-based prediction of remaining useful life of nonlinear Wiener process[J]. Measurement Science and Technology, 2022, 33(10): 105106.
[3] 李天梅，司小胜，刘翔，等. 大数据下数模联动的随机退化设备剩余寿命预测技术[J].自动化学报, 2022, 48(09): 2119-2141.
Li Tian-Mei, Si Xiao-Sheng, Liu Xiang, Pei Hong. Data-model interactive remaining useful life prediction technologies for stochastic degrading devices with big data[J]. Acta Automatica Sinica, 2022, 48(9): 2119−2141
[4] Dong S. J., Xiao J. F., et al. Deep transfer learning based on Bi-LSTM and attention for remaining useful life prediction of rolling bearing[J]. Reliability Engineering & System Safety, 2023, 230: 108914.
[5] Niu H, Zeng J, Shi H, et al. Degradation modeling and remaining useful life prediction for a multi-component system with stochastic dependence[J]. Computers & Industrial Engineering, 2023, 175: 108889.
[6] Kong X. F., Yang J., et al. Reliability analysis for multi-component systems considering stochastic dependency based on factor analysis[J]. Mechanical Systems and Signal Processing, 2022, 169: 108754.
[7] Fang G, Pan R, Hong Y. Copula-based reliability analysis of degrading systems with dependent failures[J]. Reliability Engineering & System Safety, 2020, 193: 106618.
[8] Bian L. K. and Gebraeel N. Stochastic modeling and real-time prognostics for multi-component systems with degradation rate interactions[J]. IIE Transactions, 2014, 46(5): 470-482.
[9] Bian L. K. and Gebraeel N. Stochastic Framework for Partially Degradation Systems with Continuous Component Degradation-Rate-Interactions[J]. Naval Research Logistics, 2014, 61(4): 286-303.
[10] Tamssaouet F., Nguyen K. T. P., et al. Online joint estimation and prediction for system-level prognostics under component interactions and mission profile effects[J]. ISA Trans, 2021, 113: 52-63.
[11] Shahraki A. F., Yadav O. P., et al. Selective maintenance optimization for multi-state systems considering stochastically dependent components and stochastic imperfect maintenance actions[J]. Reliability Engineering & System Safety, 2020, 196: 106738.
[12] Wang P. P., Tang Y. C., et al. Bayesian analysis of two-phase degradation data based on change-point Wiener process[J]. Reliability Engineering & System Safety, 2018, 170: 244-256.
[13] Chen Z., Li Y. P., et al. Two-phase degradation data analysis with change-point detection based on Gaussian process degradation model[J]. Reliability Engineering & System Safety, 2021, 216: 107916.
[14] Zhang J. X., Hu C. H., et al. A novel lifetime estimation method for two-phase degrading systems[J]. IEEE Transactions on Reliability, 2018, 68(2): 689-709.
[15] Liao G. B., Yin H. P., et al. Remaining useful life prediction for multi-phase deteriorating process based on Wiener process[J]. Reliability Engineering & System Safety, 2021, 207: 107361.
[16] Wen Y. X., Wu J. G., et al. Degradation modeling and RUL prediction using Wiener process subject to multiple change points and unit heterogeneity[J]. Reliability Engineering & System Safety, 2018, 176: 113-124.
[17] Liu W., Yang W. A., et al. Three-Stage Wiener-Process-Based Model for Remaining Useful Life Prediction of a Cutting Tool in High-Speed Milling[J]. Sensors (Basel), 2022, 22(13): 4763.
[18] Ma J., Cai L., et al. A multi-phase Wiener process-based degradation model with imperfect maintenance activities[J]. Reliability Engineering & System Safety, 2023, 232: 109075.
[19] Lin W, Chai Y, Fan L, et al. Remaining useful life prediction using nonlinear multi-phase Wiener process and variational Bayesian approach[J]. Reliability Engineering & System Safety, 2024, 242: 109800.
[20] Wang Z., Ta Y., et al. Research on a remaining useful life prediction method for degradation angle identification two-stage degradation process[J]. Mechanical Systems Signal Processing, 2023, 184: 109747.
[21] Wu B, Shi H, Zeng J, et al. Remaining useful life prediction for complex systems with multiple indicators of stochastic correlation considering random shocks[J]. Mechanical Systems and Signal Processing, 2023, 204: 110767.
[22] Zhang C., Lim P., et al. Multiobjective Deep Belief Networks Ensemble for Remaining Useful Life Estimation in Prognostics[J]. IEEE Trans Neural Netw Learn Syst, 2017, 28(10): 2306-2318.
[23] Singh S. K., Kumar S., et al. A novel soft computing method for engine RUL prediction[J]. Multimedia Tools and Applications, 2019, 78(4): 4065-4087.
[24] Wen P, Zhao S, Chen S, et al. A generalized remaining useful life prediction method for complex systems based on composite health indicator[J]. Reliability Engineering & System Safety, 2021, 205: 107241.
[25] Wang S, Liu M, Dong Z. Remaining useful life prediction based on multi-stage Wiener process and Bayesian information criterion[J]. Computers & Industrial Engineering, 2024, 196: 110496.
[26] 石慧, 康辉, 任谦力等. 随机相关性影响的多部件系统剩余寿命预测[J]. 振动与冲击, 2022, 41(21): 299-307.
Shi H, Kang H, Ren Q L. Remaining useful life prediction of multi-component system affected by stochastic dependence, Journal of Vibration and Shock[J], 2022,41(21):299-307.