基于深度学习的缓变故障早期诊断及寿命预测

doi:10.6040/j.issn.1672-3961.0.2017.193

山东大学学报(工学版) ›› 2017, Vol. 47 ›› Issue (5): 30-37.doi: 10.6040/j.issn.1672-3961.0.2017.193

基于深度学习的缓变故障早期诊断及寿命预测

周福娜¹,高育林^1*,王佳瑜¹,文成林²

1. 河南大学计算机与信息工程学院, 河南开封 475004;2. 杭州电子科技大学自动化学院, 浙江杭州 310018

收稿日期:2017-02-10 出版日期:2017-10-20 发布日期:2017-02-10
通讯作者: 高育林(1992— ),男,河南滑县人,硕士研究生,主要研究方向为故障诊断. E-mail:gaoyulinhn@163.com E-mail:zhoufn2002@henu.edu.cn
作者简介:周福娜(1978— ),女,河南鲁山人,副教授,博士,主要研究方向为数据驱动的故障诊断. E-mail:zhoufn2002@henu.edu.cn
基金资助:
国家自然科学基金资助项目(U1604158);河南省教育厅科学技术研究重点资助项目(16A413002)

Early diagnosis and life prognosis for slowlyvarying fault based on deep learning

ZHOU Funa¹, GAO Yulin^1*, WANG Jiayu¹, WEN Chenglin²

1. School of Computer and Information Engineering, Henan University, Kaifeng 475004, Henan, China;
2. School of Automation, Hangzhou Dianzi University, Hangzhou 310018, Zhejiang, China

Received:2017-02-10 Online:2017-10-20 Published:2017-02-10

摘要/Abstract

摘要： 为了克服传统的早期微小故障诊断方法不能区分多个不同时刻发生故障的不足,提出一种将深度学习和PCA相结合的方法实现微小缓变故障早期诊断及寿命预测。对采集的数据进行深度学习实现逐层特征抽取,学习早期微小故障特征,建立微小缓变故障早期诊断模型,结合PCA方法将深度学习所抽取的高维故障特征向量集成为一个故障特征变量,根据历史故障数据特征变量演化规律定义数据驱动的故障演变标尺,并通过指数型非线性拟合方法建立寿命预测模型。选取TE平台数据进行算法有效性检验,并与其他算法对比,从而验证了所提出算法的有效性。

关键词: 缓变故障, 深度学习, 非线性拟合, 寿命预测, 早期诊断

Abstract: In order to overcome the shortcoming of traditional early fault diagnosis methods, a method of combining deep learning with PCA to realize early diagnosis of slowly varying small fault and life prognosis was proposed. Using the deep learning method to extract the sampled data characteristics layer by layer, learning the early fault characteristics and establishing the early fault diagnosis model for slowly varying small fault, the combining deep learning was combined with PCA to integrate the high dimensional fault feature vector extracted by the deep learning into a fault characteristic variable. A data-driven fault precursor could be defined according to the evolution rule of the characteristic variable of the historical fault data, and life prognosis model was established by exponential nonlinear fitting method. The TE benchmark data was used to verify the effectiveness of the proposed algorithm, experimental results showed the validity of the proposed algorithm by comparing with other algorithms.

Key words: early diagnosis, life prognosis, slowly varying faults, nonlinear fitting, deep learning

中图分类号:

TP277

周福娜,高育林,王佳瑜,文成林. 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(工学版), 2017, 47(5): 30-37.

ZHOU Funa, GAO Yulin, WANG Jiayu, WEN Chenglin. Early diagnosis and life prognosis for slowlyvarying fault based on deep learning[J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2017, 47(5): 30-37.

参考文献

[1] SHANG Chao, YANG Fan, HUANG Dexian, et al. Data-driven soft sensor development based on deep learning technique[J]. Journal of Process Control, 2014, 24(3):223-233.
[2] ZHOU Funa, PARK Ju H, LIU Yajuan. Differential feature based hierarchical PCA fault detection method for dynamic fault[J]. Neurocomputing, 2016, 202:27-35.
[3] 庞荣, 余志斌, 熊维毅,等. 基于深度学习的高速列车转向架故障识别[J]. 铁道科学与工程学报, 2015,12(6):1283-1288. PANG Rong, YU Zhibin, XIONG Weiyi, et al. Faults recognition of high-speed train bogie based on deep learning[J]. Journal of Railway Science and Engineering, 2015, 12(6):1283-1288.
[4] CHEN Xiaoyue, ZHOU Jianzhong, XIAO Jian, et al. Fault diagnosis based on dependent feature vector and probability neural network for rolling element bearings[J].Applied Mathematics and Computation, 2014, 247:835-847.
[5] 周东华, 胡艳艳. 动态系统的故障诊断技术[J].自动化学报, 2009,35(6):748-758. ZHOU Donghua, HU Yanyan. Fault diagnosis techniques for dynamic systems[J]. Acta Automatica Sinica, 2009, 35(6):748-758.
[6] 李娟, 周东华, 司小胜,等. 微小故障诊断方法综述[J]. 控制理论与应用, 2012, 29(12):1517-1529. LI Juan, ZHOU Donghua, SI Xiaosheng, et al. Review of incipient fault diagnosis methods[J] ,Control Theory and Applications, 2012, 29(12):1517-1529.
[7] 葛志强, 杨春节, 宋执环. 基于MEWMA-PCA的微小故障检测方法研究及其应用[J]. 信息与控制, 2007, 36(5):650-656. GE Zhiqiang, YANG Chunjie, SONG Zhihuan. Research and application of small shifts detection method based on MEWMA-PCA[J]. Information and Control, 2007, 36(5):650-656.
[8] 董小亮, 帕孜来·马合木提. 混杂系统传感器微小故障的检测与隔离方法[J].自动化与仪表, 2015, 30(11):13-17. DONG Xiaoliang, PAZILAI Mahemuti. Sensor incipient fault detection and isolation method of hybrid system[J].Automation and Instrumentation, 2015, 30(11):13-17.
[9] 邱天, 白晓静, 郑茜予,等. 多元指数加权移动平均主元分析的微小故障检测[J].控制理论与应用, 2014, 31(1):19-26. QIU Tian, BAI Xiaojing, ZHENG Xiyu, et al. Incipient fault detection of multivariate exponentially weighted[J]. Control Theory and Applications, 2014, 31(1):19-26.
[10] 周福娜, 文成林, 陈志国,等. 基于指定元分析的多级相对微小故障诊断方法[J].电子学报, 2010, 38(8):1874-1879. ZHOU Funa, WEN Chenglin, CHEN Zhiguo, et al. DCA based multi-level small fault diagnosis method[J].Acta Electronica Sinica, 2010, 38(8):1874-1879.
[11] 孙美红, 孙巍, 赵劲松,等. 多变量统计方法监测化工过程的缓变故障[J].计算机与应用化学, 2009, 26(10):1228-1232. SUN Meihong, SUN Wei, ZHAO Jinsong, et al. MCUSUM-MSPCA based small shift monitoring in TE process[J].Computers and Applied Chemistry, 2009, 26(10):1228-1232.
[12] 文成林, 吕菲亚, 包哲静,等. 基于数据驱动的微小故障诊断方法综述[J].自动化学报, 2016, 42(9):1285-1299. WEN Chenglin, LYU Feiya, BAO Zhejing, et al. A review of data driven-based incipient fault diagnosis[J].Acta Automatica Sinica, 2016, 42(9):1285-1299.
[13] JIA Feng, LEI Yaguo, LIN Jing, et al. Deep neural networks: a promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data[J].Mechanical Systems and Signal Processing, 2016, 72-73:303-315.
[14] HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786):504-507.
[15] 孙志军, 薛磊, 许阳明,等.深度学习研究综述[J].计算机应用研究,2012,29(8):2806-2810. SUN Zhijun, XUE Lei, XU Yangming, et al. Overview of deep learning[J]. Application Research of Computers, 2012, 29(8):2806-2810.
[16] 彭宇, 刘大同. 数据驱动故障预测和健康管理综述[J].仪器仪表学报,2014, 35(3):481-495. PENG Yu, LIU Datong. Data-driven prognostics and health management: a review of recent advances[J]. Chinese Journal of Scientific Instrument, 2014, 35(3):481-495.
[17] LIAO Haitao, ZHAO Wenbiao, GUO Huairui. Predicting remaining useful life of an individual unit using proportional hazards model and logistic regression model[C] //Proceeding of Rams'06: Annual Reliability and Maintainability Symposium.Newport Beach, USA, CA:IEEE, 2006:127-132.
[18] 周东华, 魏慕恒, 司小胜. 工业过程异常检测、寿命预测与维修决策的研究进展[J].自动化学报,2013,39(6):711-722. ZHOU Donghua, WEI Muheng, SI Xiaosheng. A survey on anomaly detection, life prediction and maintenance decision for industrial processes[J]. Acta Automatica Sinica, 2013, 39(6):711-722.
[19] SIKORSKA J Z, HODKIEWICZ M, MA L. Prognostic modelling options for remaining useful life estimation by industry[J].Mechanical Systems and Signal Processing, 2011, 25(5):1803-1836.
[20] LIAO Linxia, K(¨overO)TTIG Felix. Review of hybrid prognostics approaches for remaining useful life prediction of engineered systems, and an application to battery life prediction[J]. Reliability IEEE Transactions on, 2014, 63(1):191-207.
[21] LU Chen, WANG Zhenya, QIN Weili, et al. Fault diagnosis of rotary machinery components using a stacked denoisingautoencoder-based health state identification[J].Signal Processing, 2017, 130:377-388.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于深度学习的缓变故障早期诊断及寿命预测

Early diagnosis and life prognosis for slowlyvarying fault based on deep learning

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

多维度评价

本文评价

推荐阅读 0

[1]	谢志峰,吴佳萍,马利庄. 基于卷积神经网络的中文财经新闻分类方法[J]. 山东大学学报(工学版), 2018, 48(3): 34-39.
[2]	唐乐爽,田国会,黄彬. 一种基于DSmT推理的物品融合识别算法[J]. 山东大学学报(工学版), 2018, 48(1): 50-56.
[3]	何正义,曾宪华,曲省卫,吴治龙. 基于集成深度学习的时间序列预测模型[J]. 山东大学学报(工学版), 2016, 46(6): 40-47.
[4]	郑毅, 朱成璋. 基于深度信念网络的PM_2.5预测[J]. 山东大学学报(工学版), 2014, 44(6): 19-25.
[5]	谭忠盛,黄成造 ,刘恒,朋改非 . 大跨公路隧道结构耐久性分析[J]. 山东大学学报(工学版), 2008, 38(3): 18-22 .