基于机器学习的设备剩余寿命预测方法综述

doi:10.3901/JME.2019.08.001

摘要/Abstract

摘要： 随着科学技术的发展和生产工艺的进步，当代设备日益朝着大型化、复杂化、自动化以及智能化方向发展。为保障设备安全性与可靠性，剩余寿命（Remaining useful life，RUL）预测技术受到了普遍关注，同时得到了广泛应用。传统的统计数据驱动方法受模型的选择影响明显，而机器学习具有强大的数据处理能力，并且无需确切的物理模型和专家先验知识，因而机器学习在剩余寿命预测领域表现出了广阔的应用前景。鉴于此，详细分析和阐述了基于机器学习的设备剩余寿命预测方法。根据机器学习模型结构的深度，将其分为基于浅层机器学习的方法和基于深度学习的方法。同时疏理了每类方法的发展分支与研究现状，并且总结了相应的优势和缺点，最后探讨了基于机器学习的剩余寿命预测方法的未来研究方向。

关键词: 机器学习, 深度学习, 神经网络, 剩余寿命预测, 支持向量机

Abstract: With the development of science and technology as well as the advancement of production technology, contemporary equipment is increasingly developing towards large-scale, complex, automated and intelligent direction. In order to ensure the safety and reliability of equipment, the remaining useful life (RUL) prediction technology has received widespread attention and been widely used. Traditional statistical data-driven methods are obviously influenced by the choice of models. Machine learning has powerful data processing ability, and does not need exact physical models and prior knowledge of experts. Therefore, machine learning has a broad application prospect in the field of RUL prediction. In view of this, the RUL prediction methods based on machine learning are analyzed and expounded in detail. According to the depth of machine learning model structure, it is divided into shallow machine learning methods and deep learning methods. At the same time, the development branches and research status of each method are sorted out, and the corresponding advantages and disadvantages are summarized. Finally, the future research directions of RUL prediction methods based on machine learning are discussed.

Key words: deep learning, machine learning, neural network, remaining useful life prediction, support vector machine

中图分类号:

V448

裴洪, 胡昌华, 司小胜, 张建勋, 庞哲楠, 张鹏. 基于机器学习的设备剩余寿命预测方法综述[J]. 机械工程学报, 2019, 55(8): 1-13.

PEI Hong, HU Changhua, SI Xiaosheng, ZHANG Jianxun, PANG Zhenan, ZHANG Peng. Review of Machine Learning Based Remaining Useful Life Prediction Methods for Equipment[J]. Journal of Mechanical Engineering, 2019, 55(8): 1-13.

参考文献

[1] MOGHADDASS R,ZUO M J. An integrated framework for online diagnostic and prognostic health monitoring using a multistate deterioration process[J]. Reliability Engineering and System Safety,2014,124:92-104.
[2] QIAO W,ZHANG P,CHOW M Y. Condition monitoring,diagnosis,prognosis,and health management for wind energy conversion systems[J]. IEEE Transactions on Industrial Electronics,2015,62(10):6533-6535.
[3] PECHT M,JAAI R. A prognostics and health management roadmap for information and electronics-rich systems[J]. Microelectronics Reliability,2010,50(3):317-323.
[4] LAU D,FONG B. Special issue on prognostics and health management[J]. Microelectronics Reliability,2011,51(2):253-254.
[5] ZHAO Z,QUAN Q,CAI KY. A profust reliability based approach to prognostics and health management[J]. IEEE Transactions on Reliability,2014,63(1):26-41.
[6] SMITH G,SCHROEDER J B,NAVARRO S,et al. Development of a prognostics and health management capability for the Joint Strike Fighter[C]//1997 IEEE Autotestcon Proceedings AUTOTESTCON,2002:676-682.
[7] PECHT M. Prognostics and health management of electronics[M]. Hoboken:John Wiley and Sons,Ltd,2008.
[8] YE Z S,XIE M. Stochastic modelling and analysis of degradation for highly reliable products[J]. Applied Stochastic Models in Business and Industry,2015,31(1):16-32.
[9] GEBRAEEL N,ELWANY A,PAN J. Residual life predictions in the absence of prior degradation knowledge[J]. IEEE Transactions on Reliability,2009,58(1):106-117.
[10] SI X S,WANG W,HU C H,et al. A Wiener-process-based degradation model with a recursive filter algorithm for remaining useful life estimation[J]. Mechanical Systems & Signal Processing,2013,35(1-2):219-237.
[11] WANG X,BALAKRISHNAN N,GUO B. Residual life estimation based on nonlinear-multivariate Wiener processes[J]. Journal of Statistical Computation and Simulation,2015,85(9):1742-1764.
[12] ZIO E,MAIO F D. A data-driven fuzzy approach for predicting the remaining useful life in dynamic failure scenarios of a nuclear system[J]. Reliability Engineering & System Safety,2013,95(1):49-57.
[13] GEBRAEEL N,PAN J. Prognostic degradation models for computing and updating residual life distributions in a time-varying environment[J]. IEEE Transactions on Reliability,2008,57(4):539-550.
[14] HENG A,ZHANG S,TAN A C C,et al. Rotating machinery prognostics:State of the art,challenges and opportunities[J]. Mechanical Systems & Signal Processing,2009,23(3):724-739.
[15] LIU D T,WANG H,PENG Y,et al. Satellite lithium-ion battery remaining cycle life prediction with novel indirect health indicator extraction[J]. Energies,2013,6(8):3654-3668.
[16] ZHANG J X,HU C H,HE X,et al. Lifetime prognostics for deteriorating systems with time-varying random jumps[J]. Reliability Engineering and System Safety,2017,167:338-350.
[17] LI C J,LEE H. Gear fatigue crack prognosis using embedded model,gear dynamic model and fracture mechanics[J]. Mechanical Systems and Signal Processing,2005,19(4):836-846.
[18] FAN J J,YUNG K C,PECHT M. Physics-of-failure-based prognostics and health management for high-power white light-emitting diode lighting[J]. IEEE Transactions on Device and Materials Reliability,2011,11(3):407-416.
[19] CHENG S,PECHT M. A fusion prognostics method for remaining useful life prediction of electronic products[C]//IEEE International Conference on Automation Science and Engineering,2009:102-107.
[20] SI X S,WANG W B,HU C H,et al. Remaining useful life estimation:A review on the statistical data driven approaches[J]. European Journal of Operational Research,2011,213(1):1-14.
[21] LIAO L,KÖTTIG F. Review of hybrid prognostics approaches for remaining useful life prediction of engineered systems,and an application to battery life prediction[J]. IEEE Transactions on Reliability,2014,63(1):191-207.
[22] NOORTWIJK J M V. A survey of the application of gamma processes in maintenance[J]. Reliability Engineering & System Safety,2009,94(1):2-21.
[23] ZHANG Z X,SI X S,HU C H,et al. Degradation data analysis and remaining useful life estimation:A review on Wiener-Process-Based methods[J]. European Journal of Operational Research,2018.
[24] MITCHELL T M,CARBONELL J G,MICHALSKI R S. machine learning[M]. Beijing:China Machine Press,2003.
[25] BENGIO S,DENG L,LAROCHELLE H,et al. Guest editors' introduction:Special section on learning deep architectures[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(8):1795-1797.
[26] YU D,HINTON G,MORGAN N,et al. Introduction to the special section on deep learning for speech and language processing[J]. IEEE Transactions on Audio Speech & Language Processing,2012,20(1):4-6.
[27] LECUN Y,BENGIO Y,HINTON G. Deep learning[J]. Nature,2015,521(7553):436-444.
[28] SIMON H. Neural network:A comprehensive foundation[M]. New Jersey:Prentice Hall PTR,1994.
[29] BYINGTON C S,WATSON M,EDWARDS D. Data-driven neural network methodology to remaining life predictions for aircraft actuator components[C]//IEEE Aerospace Conference Proceedings,2004:3581-3589.
[30] SHAO Y,NEZU K. Prognosis of remaining bearing life using neural networks[J]. Proceedings of the Institution of Mechanical Engineers-Part I,2000,214(3):217-230.
[31] GEBRAEEL N,LAWLEY M,LIU R,et al. Residual life predictions from vibration-based degradation signals:A neural network approach[J]. IEEE Transactions on Industrial Electronics,2004,51(3):694-700.
[32] 张慰,李晓阳,姜同敏,等. 基于BP神经网络的多应力加速寿命试验预测方法[J]. 航空学报,2009,30(9):1691-1696. ZHANG Wei,LI Xiaoyang,JIANG Tongmin,et al. Life-prediction of multi-stress accelerated life testing based on BP algorithm of artificial neural network[J]. Acta Aeronautica et Astronautica Sinica,2009,30(9):1691-1696.
[33] WANG L X,WU Z H,FU Y D,et al. Remaining life predictions of fan based on time series analysis and BP neural networks[C]//Information Technology,Networking,Electronic and Automation Control Conference,IEEE. 2016:607-611.
[34] ZHANG Z,LI L,ZHAO W. Tool life prediction model based on GA-BP neural network[J]. Materials Science Forum,2016,836-837:256-262.
[35] SANTHOSH T V,GOPIKA V,GHOSH A K,et al. An approach for reliability prediction of instrumentation and control cables by artificial neural networks and weibull theory for probabilistic safety assessment of NPPs[J]. Reliability Engineering and System Safety,2018,170:31-44.
[36] TIAN Z G,WONG L,SAFAEI N. A neural network approach for remaining useful life prediction utilizing both failure and suspension histories[J]. Mechanical Systems & Signal Processing,2010,24(5):1542-1555.
[37] BEZAZI A,PIERCE S G,WORDEN K,et al. Fatigue life prediction of sandwich composite materials under flexural tests using a Bayesian trained artificial neural network[J]. International Journal of Fatigue,2007,29(4):738-747.
[38] PIERCE S G,WORDEN K,BEZAZI A. Uncertainty analysis of a neural network used for fatigue lifetime prediction[J]. Mechanical Systems & Signal Processing,2008,22(6):1395-1411.
[39] POWELL M J D. Radial basis functions for multivariable interpolation:A review[C]//Algorithms for Approximation,1987:143-167.
[40] BORS A G. Introduction of the Radial Basis Function (RBF) Networks[C]//Online Symposium for Electronics Engineers,1996:393-408.
[41] LIU H,FAN M J,ZENG Q H,et al. RBF network based on artificial immune algorithm and application of predicting the residual life of injecting water pipeline[C]//Sixth International Conference on Natural Computation,2010:1305-1309.
[42] LI S Z,LI X Y,JIANG T M. A prediction method of life and reliability for CSALT using Grey RBF neural networks[C]//International Conference on Industrial Engineering and Engineering Management,2009:699-703.
[43] 李志刚,刘伯颖,李玲玲,等. 基于小波包变换及RBF神经网络的继电器寿命预测[J]. 电工技术学报,2015,30(14):233-240. LI Zhigang,LIU Boying,LI Lingling,et al. Life prediction of relay based on wavelet packet transform and RBF neural network[J]. Transactions of China Electrotechnical Society,2015,30(14):233-240.
[44] CHEN X S,XIAO H,GUO Y J,et al. A multivariate grey RBF hybrid model for residual useful life prediction of industrial equipment based on state data[J]. International Journal of Wireless and Mobile Computing,2016,10(1):90-96.
[45] HUANG G B,ZHU Q Y,SIEW C K. Extreme learning machine:A new learning scheme of feedforward neural networks[C]//IEEE International Joint Conference on Neural Networks,2004:985-990.
[46] 李磊. 基于极限学习机的风机机械传动部件剩余寿命预测研究[D]. 秦皇岛:燕山大学,2015. LI Lei. Residual life prediction for mechanical drive components of wind turbine based on extreme learning machine[D]. Qinhuangdao:Yanshan University,2015.
[47] LIU F,LIU Y B,CHEN F L,et al. Residual life prediction for ball bearings based on joint approximate diagonalization of eigen matrices and extreme learning machine[J]. Proceedings of the Institution of Mechanical Engineers Part C:Journal of Mechanical Engineering Science,2015,231(9):1-13.
[48] LIU Y B,HE B,LIU F,et al. Remaining useful life prediction of rolling bearings using PSR,JADE,and extreme learning machine[J]. Mathematical Problems in Engineering,2016,2016:1-13.
[49] 杜占龙,李小民,席雷平,等. 多分类概率极限学习机及其在剩余使用寿命预测中的应用[J]. 系统工程与电子技术,2015,37(12):2777-2784. DU Zhanlong,LI Xiaomin,XI Leiping,et al. Multi-class probabilistic extreme learning machine and its application in remaining useful life prediction[J]. Systems Engineering and Electronics,2015,37(12):2777-2784.
[50] YANG Z,BARALDI P,ZIO E. A comparison between extreme learning machine and artificial neural network for remaining useful life prediction[C]//Prognostics and System Health Management Conference,2017:1-7.
[51] WANG X Y,HAN M. Online sequential extreme learning machine with kernels for nonstationary time series prediction[J]. Neurocomputing,2014,145(145):90-97.
[52] 何群,李磊,江国乾,等. 基于PCA和多变量极限学习机的轴承剩余寿命预测[J]. 中国机械工程,2014,25(7):984-989. HE Qun,LI Lei,JIANG Guoqian,et al. Residual life predictions for bearings based on PCA and MELM[J]. China Mechanical Engineering,2014,25(7):984-989.
[53] 吴婧睿. 基于GSO-ELM的锂离子电池剩余寿命间接预测方法研究[D]. 大连:大连海事大学,2017. WU Jingrui. Research on indirect prediction of remaining life based on GSO-ELM for Lithium-ion battety[D]. Dalian:Dalian Maritime University,2017.
[54] JOACHIMS T. Making large-scale SVM Learning Practical[C]//Technische Universität Dortmund,Sonderforschungsbereich 475:Komplexitätsreduktion in multivariaten Datenstrukturen,1998:499-526.
[55] CHERKASSKY V,MA Y. Practical selection of SVM parameters and noise estimation for SVM regression[J]. Neural Networks,2004,17(1):113-126.
[56] ROCCO C M,MORENO J A. Fast Monte Carlo reliability evaluation using support vector machine[J]. Reliability Engineering & System Safety,2002,76(3):237-243.
[57] HONG W C,PAI P F. Predicting engine reliability by support vector machines[J]. International Journal of Advanced Manufacturing Technology,2006,28(1-2):154-161.
[58] MIAO J Q,LI X G,YE J H. Predicting research of mechanical gyroscope life based on wavelet support vector[C]//First International Conference on Reliability Systems Engineering,2016:1-5.
[59] NIETO P J G,GARCÍA-GONZALO E,LASHERAS F S,et al. Hybrid PSO-SVM-based method for forecasting of the remaining useful life for aircraft engines and evaluation of its reliability[J]. Reliability Engineering & System Safety,2015,138:219-231.
[60] MAIOR C B S,MOURA M D C,LINS I D,et al. Remaining useful life estimation by empirical mode decomposition and support vector machine[J]. IEEE Latin America Transactions,2016,14(11):4603-4610.
[61] CHEN Z Z,CAO S C,MAO Z J. Remaining useful life estimation of aircraft engines using a modified similarity and supporting vector machine (SVM) approach[J]. Energies,2017,11(1):1-14.
[62] TIPPING M E,SMOLA A. Sparse Bayesian learning and the relevance vector machine[J]. Journal of Machine Learning Research,2001,1(3):211-244.
[63] MAIO F D,TSUI K L,ZIO E. Combining relevance vector machines and exponential regression for bearing residual life estimation[J]. Mechanical Systems & Signal Processing,2012,31(8):405-427.
[64] SONG Y C,LIU D T,HOU Y D,et al. Satellite lithium-ion battery remaining useful life estimation with an iterative updated RVM fused with the KF algorithm[J]. Chinese Journal of Aeronautics,2018(1):31-40.
[65] 王烨,左洪福,蔡景,等. 基于Bayesian推断和LS-SVM的发动机在翼寿命预测模型[J]. 南京理工大学学报,2013,37(6):955-959. WANG Ye,ZUO Hongfu,CAI Jing,et al. Forecasting model of engine life on wing based on LS-SVM and Bayesian inference[J]. Journal of Nanjing University of Science and Technology,2013,37(6):955-959.
[66] HINTON G E,OSINDERO S,TEH Y W. A fast learning algorithm for deep belief nets[J]. Neural Computation,2006,18(7):1527-1554.
[67] SHAH S A A,BENNAMOUN M,BOUSSAID F. Iterative deep learning for image set based face and object recognition[J]. Neurocomputing,2016,174:866-874.
[68] DENG L. Deep learning:From speech recognition to language and multimodal processing[J]. Apsipa Transactions on Signal & Information Processing,2016,5:1-15.
[69] HE M,HE D. Deep learning based approach for bearing fault diagnosis[J]. IEEE Transactions on Industry Applications,2017,53(3):3057-3065.
[70] REN L,CUI J,SUN Y Q,et al. Multi-bearing remaining useful life collaborative prediction:A deep learning approach[J]. Journal of Manufacturing Systems,2017,43:248-256.
[71] ZHAO R,YAN R Q,CHEN Z H,et al. Deep learning and its applications to machine health monitoring:A survey[C]//IEEE Transactions on Neural Networks and Learning Systems,arXiv:1612.07640,2016.
[72] REN L,SUN Y,CUI J,et al. Bearing remaining useful life prediction based on deep autoencoder and deep neural networks[J]. Journal of Manufacturing Systems,2018,48:71-77.
[73] 雷亚国,贾峰,周昕,等. 基于深度学习理论的机械装备大数据健康监测方法[J]. 机械工程学报,2015,51(21):49-56. LEI Yaguo,JIA Feng,Zhou Xin,et al. A deep learning-based method for machinery health monitoring with big data[J]. Journal of Mechanical Engineering,2015,51(21):49-56.
[74] 周福娜,高育林,王佳瑜,等. 基于深度学习的缓变故障早期诊断及寿命预测[J]. 山东大学学报,2017,47(5):30-37. ZHOU Funa,GAO Yulin,WANG Jiayu,et al. Early diagnosis and life prognosis for slowlyvarying fault based on deep learning[J]. Journal of Shandong University,2017,47(5):30-37.
[75] 王佳瑜. 数据驱动的缓变微小故障早期诊断及剩余寿命预测[D]. 开封:河南大学,2017. WANG Jiayu. Data-driven early diagnosis and residual useful life prediction of slowly varying small fault[D]. Kaifeng:Henan University,2017.
[76] YAN H,WAN J,ZHANG C,et al. Industrial big data analytics for prediction of remaining useful life based on deep learning[J]. IEEE Access,2018,6:17190-17197.
[77] FISCHER A,IGEL C. Progress in pattern recognition,image analysis,computer vision,and applications[M]. Berlin:Springer-Verlag,2012.
[78] 单晨晨. 基于深度置信网络的发动机状态监控研究[D].天津:中国民航大学,2017. SHAN Chenchen. Research on the engine condition monitoring based on deep belief net[D]. Tianjin:Civil Aviation University of China,2017.
[79] DEUTSCH J,HE D. Using deep learning based approaches for bearing remaining useful life prediction[C]//Annual Conference of the Prognostics and Health Management Society,2016:1-7.
[80] DEUTSCH J,HE D. Using deep learning-based approach to predict remaining useful life of rotating components[J]. IEEE Transactions on Systems Man & Cybernetics Systems,2017,48(1):11-20.
[81] DEUTSCH J,HE M,HE D. Remaining useful life prediction of hybrid ceramic bearings using an integrated deep learning and particle filter approach[J]. Applied Sciences,2017,649(7):1-17.
[82] 张国辉. 基于深度置信网络的时间序列预测方法及其应用研究[D]. 哈尔滨:哈尔滨工业大学,2017. ZHANG Guohui. Research on time series prediction and its application based on deep belief net work[D]. Harbin:Harbin Institute of Technology,2017.
[83] ZHAO G Q,ZHANG G H,LIU Y F,et al. Lithium-ion battery remaining useful life prediction with deep belief network and relevance vector machine[C]//IEEE International Conference on Prognostics and Health Management,2017:7-13.
[84] ZHANG C,LIM P,QIN A K,et al. Multiobjective deep belief networks ensemble for remaining useful life estimation in prognostics[J]. IEEE Transactions on Neural Networks & Learning Systems,2016,28(10):2306-2318.
[85] LAWRENCE S,GILES C L,TSOI A C,et al. Face recognition:A convolutional neural-network approach[J]. IEEE Transactions on Neural Networks,1997,8(1):98-113.
[86] SUN M L,SONG Z J,JIANG X H,et al. Learning pooling for convolutional neural network[J]. Neurocomputing,2016,224:96-104.
[87] BABU G S,ZHAO P,LI X L. Database systems for advanced applications[M]. Berlin:Springer,2016.
[88] LI X,DING Q,SUN J Q. Remaining useful life estimation in prognostics using deep convolution neural networks[J]. Reliability Engineering and System Safety,2018,172(C):1-11.
[89] REN L,SUN Y,WANG H,et al. Prediction of bearing remaining useful life with deep convolution neural network[J]. IEEE Access,2018,6(99):13041-13049.
[90] CHOW T W S,FANG Y. A recurrent neural-network- based real-time learning control strategy applying to nonlinear systems with unknown dynamics[J]. IEEE Transactions on Industrial Electronics,1998,45(1):151-161.
[91] HEIMES F O. Recurrent neural networks for remaining useful life estimation[C]//International Conference on Prognostics and Health Management,2008:1-6.
[92] LIU J,SAXENA A,KAI G,et al. An adaptive recurrent neural network for remaining useful life prediction of lithium-ion batteries[C]//Annual Conference of the Prognostics and Health Management Society,2010:1-9.
[93] MALHI A,YAN R,GAO R X. Prognosis of defect propagation based on recurrent neural networks[J]. IEEE Transactions on Instrumentation & Measurement,2011,60(3):703-711.
[94] WU Y T,YUAN M,DONG S P,et al. Remaining useful life estimation of engineered systems using vanilla LSTM neural networks[J]. Neurocomputing,2017,275:167-179.
[95] ZHANG Y Z,XIONG R,HE H W,et al. Long short-term memory recurrent neural network for remaining useful life prediction of lithium-ion batteries[J]. IEEE Transactions on Vehicular Technology,2018,67(7):5695-5705.
[96] GUO L,LI N,JIA F,et al. A recurrent neural network based health indicator for remaining useful life prediction of bearings[J]. Neurocomputing,2017,240(C):98-109.
[97] ZHANG J J,WANG P,YAN R Q,et al. Long short-term memory for machine remaining life prediction[J]. Journal of Manufacturing Systems,2018,48:78-86.