Remaining useful life prediction of time-varying drift kernel filter based on Bayesian framework

PDF(3014 KB)

Journal of Vibration and Shock ›› 2025, Vol. 44 ›› Issue (12) : 249-258.

FAULT DIAGNOSIS ANALYSIS

Remaining useful life prediction of time-varying drift kernel filter based on Bayesian framework

LIANG Yaqin,BAI Jie,SHI Hui*,LI Lijun,LI Zhehao

Author information +

History +

Abstract

In the context of life prediction for components, dynamic environments complicate the degradation process. To ensure the reliability of components during actual operation, a time-varying drift kernel filter based on Bayesian framework is proposed in time-varying operating environment. Firstly, the Wiener model is employed to characterize the degradation process, and the state space equation is constructed utilizing the multi-source mapping function. Next, the Bayesian online mutation point detection is employed, utilizing prior knowledge to predict and update the posterior probability of particles to determine the location of the mutation point. Then, the drift kernel filter is used to adaptively allocate weights and select different kernel functions for particle resampling before and after change points. This approach enhances prediction accuracy. Finally, the effectiveness of the drift kernel filter is verified through the C-MAPSS dataset.

Key words

time-varying drift kernel filter / kernel density estimation / Bayesian mutation point detection / phased resampling

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

LIANG Yaqin, BAI Jie, SHI Hui, LI Lijun, LI Zhehao. Remaining useful life prediction of time-varying drift kernel filter based on Bayesian framework[J]. Journal of Vibration and Shock, 2025, 44(12): 249-258

References

[1] 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(9): 2119-2141.
LI Tian-mei, SI Xiao-sheng, LIU Xiang, et al. Data-model interactive remaining useful life prediction technologies for stochastic degrading devices with big data [J].Acta Automatica Sinica, 2022, 48(9): 2119-2141.
[2] 段俊峰, 李宁, 唐求,等. 基于 CK-GPR 的多应力环境智能电表剩余寿命预测 [J].仪器仪表学报, 2023, (4): 102-110.
DUAN Jun-feng, LI Ning, TANG Qiu, et al. Remaining useful life prediction of smart meter based on CK-GPR in multi-stress environment [J].Chinese Journal of Scientific Instrument, 2023, (4): 102-110.
[3] 李乃鹏, 蔡潇, 雷亚国,等. 一种融合多传感器数据的数模联动机械剩余寿命预测方法 [J].机械工程学报, 2021, 57(20): 29-37, 46.
LI Nai-peng, CAI Xiao, LEI Ya-guo, et al. A model-data-fusion remaining useful life prediction method with multi-sensor fusion for machinery [J].Journal of Mechanical Engineering, 2021, 57(20): 29-37, 46.
[4] 石健, 刘冬, 王少萍. 基于数字孪生的机电液系统 PHM 关键技术综述 [J].机械工程学报, 2024, 60(4): 66-81.
SHI Jian, LIU Dong, WANG Shao-ping. Digital twin for complex electromechanical-hydraulic system PHM: A Review [J].Journal of mechanical engineering, 2024, 60(4): 66-81.
[5] 喻勇, 司小胜, 胡昌华,等. 数据驱动的可靠性评估与寿命预测研究进展: 基于协变量的方法 [J].自动化学报, 2018, 44(2): 216-227.
YU Yong, SI Xiao-sheng, HU Chang-hua, et al. Data driven reliability assessment and life-time prognostics: a review on covariate models [J].Acta Automatica Sinica, 2018, 44(2): 216-227.
[6] 魏云海, 陈民铀, 赖伟,等. 基于IGBT结温波动平滑控制的主动热管理方法综述 [J].电工技术学报, 2022, 37(6): 1415-1430.
WEI Yun-hai, CHEN Min-you, LAI Wei, et al. Review on active thermal control methods based on junction temperature swing smooth control of IGBTs [J].Transactions of China Electrotechnical Society, 2022, 37(6): 1415-1430.
[7] Guo Fei, Wu Xiongwei, Liu Lili, et al. Prediction of remaining useful life and state of health of lithium batteries based on time series feature and Savitzky-Golay filter combined with gated recurrent unit neural network [J]. Energy, 2023, 270: 126880.
[8] He Xinxin, Wang Zhijian, Li Yanfeng, et al. Joint decision-making of parallel machine scheduling restricted in job-machine release time and preventive maintenance with remaining useful life constraints [J]. Reliability Engineering & System Safety, 2022, 222: 108429.
[9] TIAN Q C, CHEN H T, DING SShu Lei, et al. Remaining Useful Life Prediction Method of PEM Fuel Cells Based on a Hybrid Model [J]. Electronics, 2023, 12(18): 3883.
[10] 曾其权, 罗马吉, 杨印龙,等. 基于 LSTM-UPF 混合驱动方法的燃料电池寿命预测 [J].储能科学与技术, 2024, 13(3): 963-970.
ZENG Qi-quan, LUO Ma-ji, YANG Yin-long, et al. Life prediction of fuel cells based on the LSTM-UPF hybrid method [J].Energy Storage Science and Technology, 2024, 13(3): 963-970.
[11] 田成文, 孙丙香, 赵鑫泽,等. 基于数据驱动的锂离子电池快速寿命预测 [J].储能科学与技术, 2024, 13(9): 3103-3111.
TIAN Cheng-wen, SUN Bing-xiang, ZHAO Xin-ze, et al. Accelerated life prediction of lithium-ion batteries using data-driven approaches [J].Energy Storage Science and Technology, 2024, 13(9): 3103-3111.
[12] 朱奕楠, 吕桃林, 赵芝芸,等. 基于并行卡尔曼滤波器的锂离子电池荷电状态估计 [J].储能科学与技术, 2021, 10(6): 2352.
ZHU Yi-nan, LV Tao-lin, ZHAO Zhi-yun, et al. State of charge estimation of lithium ion battery based on parallel Kalman filter [J].Energy Storage Science and Technology, 2021, 10(6): 2352.
[13] 高铭琨, 徐海亮, 吴明铂. 基于等效电路模型的动力电池SOC估计方法综述 [J].电气工程学报, 2021, 16(1): 90-102.
GAO Ming-kun, XU Hai-liang, WU Ming-bo. Review of SOC Estimation Methods for Power Battery Based on Equivalent Circuit Model [J].Journal of Electrical Engineering, 2021, 16(1): 90-102.
[14] Harvey A, Oryshchenko V. Kernel density estimation for time series data [J]. International journal of forecasting, 2012, 28(1): 3-14.
[15] MA M, FU L, ZHAI Z, et al. Transformer based Kalman Filter with EM algorithm for time series prediction and anomaly detection of complex systems [J]. Measurement, 2024, 229: 114378.
[16] 李韶华, 李健玮, 冯桂珍. 基于GA-LSTM自适应卡尔曼滤波的路面不平度识别 [J].振动与冲击, 2024, 43(9): 121-130.
LI Shao-hua, LI Jian-wei, FENG Gui-zhen. Road roughness recognition based on GA-LSTM adaptive Kalman filtering [J].Journal of Vibration and Shock, 2024, 43(9): 121-130.
[17] 安宇宁, 刘祖深, 江丹. 基于粒子滤波算法毫米波误差综合估计 [J].仪器仪表学报, 2023, 44(4): 330-337.
AN Yu-ning, LIU Zu-shen, JIANG Dan. Integrated estimation of millimeter wave errors based on particle filtering algorithms [J].Chinese Journal of Scientific Instrument, 2023, 44(4): 330-337.
[18] LI Y F, XIANG Y Y, PAN B S, et al. A hybrid remaining useful life prediction method for cutting tool considering the wear state [J]. The International Journal of Advanced Manufacturing Technology, 2022, 121(5): 3583-3596.
[19] CUI L L, LI W J, WANG X, et al. Comprehensive remaining useful life prediction for rolling element bearings based on time-varying particle filtering [J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 1-10.
[20] 徐亚洲, 任倩倩, 于明阳,等. 基于粒子滤波算法的风力发电塔地震动力响应预测 [J].振动与冲击, 2022, 41(15): 161-168.
XU Ya-zhou, REN Qian-qian, YU Ming-yang, et al. Seismic dynamic response prediction for a wind turbine tower based on particle filter algorithm [J].Journal of Vibration and Shock, 2022, 41(15): 161-168.
[21] 李冀, 周战洪, 贺红林,等. 基于围猎改进哈里斯鹰优化的粒子滤波方法 [J].电子与信息学报, 2023, 45(6): 2284-2292.
LI Ji, ZHOU Zhan-hong, HE Hong-lin, et al. A particle filter method based on harris hawks optimization improved by encircling strategy [J].Journal of Electronics & Information Technology, 2023, 45(6): 2284-2292.
[22] 王燕, 李想, 齐滨,等. 无源声呐场景中使用辅助粒子滤波的邻近目标检测前跟踪方法 [J].声学学报, 2023, 48(2): 277-290.
WANG Yan, LI Xiang, QI Bin, et al. A track-before-detect method for neighboring targets based on auxiliary particle filter in passive sonar scenarios [J].Acta　Acustica, 2023, 48(2): 277-290.
[23] 张春景, 柳晓鸣. 基于优化遗传重采样的辅助粒子滤波检测前跟踪方法 [J].电光与控制, 2022, 29(1): 23-27.
ZHANG Chun-jing, LIU Xiao-ming. Auxiliary particle filter track-before-detect based on optimized genetic re-sampling [J].Electronics Optics & Control, 2022, 29(1): 23-27.
[24] LI T Z. Particle filter-based fatigue damage prognosis using prognostic-aided model updating [J]. Mechanical Systems and Signal Processing, 2024, 211: 111244.
[25] 杨伟博, 袁慎芳, 邱雷,等. 基于辅助粒子滤波的疲劳裂纹扩展预测研究 [J].振动与冲击, 2018, 37(5): 114-119.
YANG Wei-bo, YUAN Shen-fang, QIU Lei, et al. Prediction of fatigue crack propagation based on auxiliary particle filtering [J].Journal of Vibration and Shock, 2018, 37(5): 114-119.
[26] 郭宇扬, 徐向波, 姬淼鑫. 一种自适应粒子滤波的零速修正方法 [J].西北工业大学学报, 2020, 38(2): 427.
GUO Yu-yang, XU Xiang-bo, JI Miao-xin. A zero－velocity update method for adaptive particle filtering [J].Journal of Northwestern Polytechnical University, 2020, 38(2): 427.
[27] LIN Y H, JIAO X L. Adaptive kernel auxiliary particle filter method for degradation state estimation [J]. Reliability Engineering & System Safety, 2021, 211: 107562.
[28] 卫少萌, 张江民, 石慧,等. 融合多传感器数据的系统相对密度高维核估计剩余寿命预测 [J].计算机集成制造系统: 1-22.
WEI Shao-meng, ZHANG Jiang-min, SHI Hui, et al. Remaining useful life prediction of relative density high-dimensional kernel estimation for systems based on multi-sensor data fusion [J].Computer Integrated Manufacturing Systems: 1-22.
[29] Lin Yuqian, Xu Yang, Zhao Zhan, et al. Assessing effects of pandemic-related policies on individual public transit travel patterns: A Bayesian online changepoint detection based framework [J]. Transportation Research Part A: Policy and Practice, 2024, 181: 104003.
[30] Si Xiao-Sheng, Wang Wenbin, Hu Chang-Hua, et al. A Wiener-process-based degradation model with a recursive filter algorithm for remaining useful life estimation [J]. Mechanical Systems and Signal Processing, 2013, 35(1-2): 219-237.
[31] 郭俊锋, 刘国华, 刘国伟. 基于长序列的航空发动机剩余使用寿命预测方法 [J].北京航空航天大学学报, 2022, 50(3): 774-784.
GUO Jun-feng, LIU Guo-hua, LIU Guowei. Prediction method of remaining useful life of aero-engine based on long sequence [J].Journal of Beijing University of Aeronautics and Astronautics, 2022, 50(3): 774-784.
[32] 李哲昊. 时变环境下的系统漂移核滤波剩余寿命预测 [D].太原科技大学, 2024.
LI Zhe-hao. Remaining useful life prediction based on time-varying system drift kernel filter [J].Taiyuan University of Science and Technology, 2024.
[33] 陈晓锋. AIC 准则及其在计量经济学中的应用研究 [D].Akaike information criterion and its application in econometrics, 2012.
CHEN Xiao-feng. Tianjin University of Finance and Economics [D].天津财经大学, 2012.
[34] ZHANG Y, XIN Y Q, LIU Z W, et al. Health status assessment and remaining useful life prediction of aero-engine based on BiGRU and MMoE [J]. Reliability Engineering & System Safety, 2022, 220: 108263.
[35] ZHANG X Y, XIAO P C, YANG Y Z, et al. Remaining useful life estimation using CNN-XGB with extended time window [J]. IEEE Access, 2019, 7: 154386-154397.
[36] ZHANG J S, JIANG Y C, WU S M, et al. Prediction of remaining useful life based on bidirectional gated recurrent unit with temporal self-attention mechanism [J]. Reliability Engineering & System Safety, 2022, 221: 108297.
[37] Kim Tae San, Sohn So Young. Multitask learning for health condition identification and remaining useful life prediction: deep convolutional neural network approach [J]. Journal of Intelligent Manufacturing, 2021, 32(8): 2169-2179.
[38] Pillai Shanmugasivam, Vadakkepat Prahlad. Two stage deep learning for prognostics using multi-loss encoder and convolutional composite features [J]. Expert Systems with Applications, 2021, 171: 114569.
[39] Kim Gyeongho, Choi Jae Gyeong, Lim Sunghoon. Using transformer and a reweighting technique to develop a remaining useful life estimation method for turbofan engines [J]. Engineering Applications of Artificial Intelligence, 2024, 133: 108475.
[40] Soualhi Moncef, Nguyen Khanh TP, Medjaher Kamal. Explainable RUL estimation of turbofan engines based on prognostic indicators and heterogeneous ensemble machine learning predictors [J]. Engineering Applications of Artificial Intelligence, 2024, 133: 108186.
[41] ZHANG Y D, ZHANG C, WANG S P, et al. Health indicators for remaining useful life prediction of complex systems based on long short-term memory network and improved particle filter [J]. Reliability Engineering & System Safety, 2024, 241: 109666.