Smart Failure/Fault Diagnosis and Influence Analysis for Mechanical Equipment with Multivariate Gaussian Bayesian Method

doi:10.3901/JME.2020.04.035

Abstract

Abstract: The failure/fault of mechanical equipment is diagnosed with multivariate Gaussian Bayesian classifier. Based on the maximum likelihood methodology, a novel influence analysis model based on "Mahalanobis distance" estimation is proposed. The method is then applied to two datasets for the mechanical equipment failure/fault mode identification. The results show that the proposed method obtains high diagnostic recognition rate (failure/fault mode recognition rate in two cases are 96% and 86%, respectively), as well as principal attributes that contribute to specific failure/fault modes. It is found that the specific failure/fault mode mainly depends on a few characteristic parameters, while the unspecified failure/fault mode always involves several diverse characteristic parameters. The desperation of key parameters will cause the unsatisfactory result of multivariate Gaussian Bayesian classifier. The model proposed in this paper is helpful for the intelligent diagnose of failure/fault mode of mechanical equipment and the analysis of key parameters that contribute to specific failure/fault mode, and so as to provide guidance for failure/fault reasoning.

Key words: Gaussian Bayesian, failure/fault diagnosis, characteristic parameter, influence analysis, Mahalanobis distance

CLC Number:

TG156

ZHU Jianxin, CHEN Xuedong, Lü Baolin, WANG Yifang, QIAO Song, CHEN Jiahong. Smart Failure/Fault Diagnosis and Influence Analysis for Mechanical Equipment with Multivariate Gaussian Bayesian Method[J]. Journal of Mechanical Engineering, 2020, 56(4): 35-41.

References

[1] 陈学东,范志超,陈永东,等. 我国压力容器设计制造与维护的绿色化与智能化[J]. 压力容器,2017,34(11):12-27. CHEN Xuedong,FAN Zhichao,CHEN Yongdong,et al. Green and intelligent design,manufacturing and maintenance of pressure vessels in China[J]. Pressure Vessel Technology,2017,34(11):12-17.
[2] DAVID J Smith. Reliability maintainability and risk-practical methods for engineers including reliability centered maintenance and safety related systems[M]. Burlington:Elsevier Butterworth-Heinemann,2005.
[3] 朱建新,陈学东,艾志斌,等. 我国石化装置风险管理体系建设设想[J]. 石油化工设备,2009,38(6):45-49. ZHU Jianxin,CHEN Xuedong,AI Zhibin,et al. Consideration on the construction of risk management system for Chinese petrochemical plants[J]. Petrochemical Equipment,2009,38(6):45-49.
[4] 陈学东,范志超,江慧丰,等. 复杂加载条件下压力容器典型用钢疲劳蠕变寿命预测方法[J]. 机械工程学报,2009,45(2):81-87. CHEN Xuedong,FAN Zhichao,JIANG Huifeng,et al. Creep-fatigue life prediction methods of pressure vessel typical steels under complicated loading conditions[J]. Journal of Mechanical Engineering,2009,45(2):81-87.
[5] 刘浩然,丁攀,郭长江,等. 基于贝叶斯算法的中文垃圾邮件过滤系统研究[J]. 通信学报,2018,39(12):151-159. LIU Haoran,DING Pan,GUO Changjiang,et al. Study on Chinese spam filtering system based on Bayes algorithm[J]. Journal on Communications,2018,39(12):151-159.
[6] 赵申坤,姜潮,龙湘云. 一种基于数据驱动和贝叶斯理论的机械系统剩余寿命预测方法[J]. 机械工程学报,2018,54(12):115-124. ZHAO Shenkun,JIANG Chao,LONG Xiangyun. Remaining useful life estimation of mechanical systems based on the data-driven method and Bayesian theory[J]. Journal of Mechanical Engineering,2018,54(12):115-124.
[7] 刘东,王昕,黄建荧,等. 基于贝叶斯网络的水电机组振动故障诊断研究[J]. 水力发电学报,2019,38(2):112-120. LIU Dong,WANG Xin,HUANG Jianying,et al. Vibration fault diagnosis for hydro-power units based on Bayesian network[J]. Journal of Hydroelectric Engineering,2019,38(2):112-120.
[8] 徐宾刚,屈梁生,陶肖明. 转子故障贝叶斯诊断网络的研究[J]. 机械工程学报,2004,40(1):66-72. XU Bingang,QU Liangsheng,TAO Xiaoming. Bayesian network framework for rotor fault diagnosis[J]. Journal of Mechanical Engineering,2004,40(1):66-72.
[9] MD T,FAISAL K,SYED I. Fault detection and pathway analysis using a dynamic Bayesian network[J]. Chemical Engineering Science,2019,195:777-790.
[10] 徐小力,刘秀丽,蒋章雷,等. 基于主观贝叶斯推理的多传感器分布式故障检测融合方法[J]. 机械工程学报,2015,51(7):91-98. XU Xiaoli,LIU Xiuli,JIANG Zhanglei,et al. Multi-sensor distributed fault detection method based on subjective Bayesian reasoning[J]. Journal of Mechanical Engineering,2015,51(7):91-98.
[11] PAULA R,HOSSAM A,PETRÔNIO V,et al. A new methodology for multiple incipient fault diagnosis in transmission lines using QTA and Naïve Bayes classifier[J]. International Journal of Electrical Power & Energy Systems,2018,103:326-346.
[12] MURALIDHARAN V,UGUMARAN V. A comparative study of naïve Bayes classifier and Bayes net classifier for fault diagnosis of monoblock centrifugal pump using wavelet analysis[J]. Appl. Soft Computing,2012,12(8):2023-2029.
[13] ABDOLRAHMAN P,STEPHEN J,THAHIRAH J,et al. Evolutionary multi-objective fault diagnosis of power transformers[J]. Swarm and Evolutionary Computation,2017,36:62-75.
[14] 陈学东,范志超,崔军,等. 极端条件重大承压设备的设计、制造与维护[J]. 机械工程学报,2013,49(22):66-75. CHEN Xuedong,FAN Zhichao,CUI Jun,et al. Risk based design,manufacture and maintenance of extreme pressure equipment[J]. Journal of Mechanical Engineering,2013,49(22):66-75.
[15] CHANG C,LEE H,LIU H. A review of artificial intelligence algorithms used for smart machine tools[J]. Inventions,2018,3(3):1-28.
[16] 高金吉. 机器故障诊断与自愈化[M]. 北京:高等教育出版社,2012. GAO Jinji. Machine failure diagnosis & self-healing[M]. Beijing:High Education Press,2012.
[17] DUA D,GRAFF C. Mechanical Analysis Data Set[EB/OL]. Irvine:UCI Machine Learning Repository,1990[2019-03-11]. https://archive.ics.uci.edu/ml/datasets/Mechanical+Analysis.
[18] Research Center of Sciences of Communication. Steel plates faults data set[EB/OL]. Irvine:UCI Machine Learning Repository,2010[2019-03-11]. https://archive.ics.uci.edu/ml/datasets/Steel+Plates+Faults.
[19] 盛骤,谢式千,潘承毅. 概率论与数理统计[M]. 北京:高等教育出版社,1995 SHENG Zhou,XIE Shiqian,PAN Chengyi. Probability and mathematical statistics[M]. Beijing:High Education Press,1995
[20] CHRISTOPHER M. Pattern recognition and machine learning[M]. Singapore:Springer, 2006.