基于机器学习的设备剩余寿命预测方法综述

被引：162

作者：

裴洪

胡昌华

司小胜

张建勋

庞哲楠

张鹏

机构：

[1] 火箭军工程大学导弹工程学院

来源：

机械工程学报 | 2019年 / 55卷 / 08期

关键词：

剩余寿命预测; 机器学习; 神经网络; 支持向量机; 深度学习;

D O I：

暂无

中图分类号：

TH17 [机械运行与维修];

学科分类号：

0802 ;

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。

引用

页码：1 / 13

页数：13

共 50 条

[31]

Hybrid PSO–SVM-based method for forecasting of the remaining useful life for aircraft engines and evaluation of its reliability[J] . P.J. García Nieto,E. García-Gonzalo,F. Sánchez Lasheras,F.J. de Cos Juez.Reliability Engineering and System Safety . 2015

[32] Residual life estimation based on nonlinear-multivariate Wiener processes [J].

Wang, Xiaolin ;

Balakrishnan, Narayanaswamy ;

Guo, Bo .

JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION, 2015, 85 (09) :1742-1764

[33]

Stochastic modelling and analysis of degradation for highly reliable products[J] . Zhi‐Sheng Ye,Min Xie.Appl. Stochastic Models Bus. Ind. . 2015 (1)

[34]

Online sequential extreme learning machine with kernels for nonstationary time series prediction[J] . Xinying Wang,Min Han.Neurocomputing . 2014

[35]

An integrated framework for online diagnostic and prognostic health monitoring using a multistate deterioration process[J] . Ramin Moghaddass,Ming J. Zuo.Reliability Engineering and System Safety . 2014

[36]

Combining Relevance Vector Machines and exponential regression for bearing residual life estimation[J] . Francesco Di Maio,Kwok Leung Tsui,Enrico Zio.Mechanical Systems and Signal Processing . 2012

[37]

Special Issue on Prognostics and Health Management[J] . Daniel Lau,Bernard Fong.Microelectronics Reliability . 2010 (2)

[38] A prognostics and health management roadmap for information and electronics-rich systems [J].

Pecht, Michael ;

Jaai, Rubyca .

MICROELECTRONICS RELIABILITY, 2010, 50 (03) :317-323

[39]

Remaining useful life estimation – A review on the statistical data driven approaches[J] . Xiao-Sheng Si,Wenbin Wang,Chang-Hua Hu,Dong-Hua Zhou.European Journal of Operational Research . 2010 (1)

[40]

A data-driven fuzzy approach for predicting the remaining useful life in dynamic failure scenarios of a nuclear system[J] . Enrico Zio,Francesco Di Maio.Reliability Engineering and System Safety . 2009 (1)

← 1 2 3 4 5 →