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

被引：1
|
作者：
Zhu J. [1 ,2 ]
Chen X. [1 ,2 ]
Lü B. [1 ,2 ]
Wang Y. [1 ,2 ]
Qiao S. [1 ,2 ]
Chen J. [1 ,2 ]
机构：
[1] Hefei General Machinery Research Institute Co. Ltd., Hefei
[2] National Technology Research Center for Safety Engineering of Pressure Vessels and Pipelines, Hefei
来源：
Jixie Gongcheng Xuebao/Journal of Mechanical Engineering | 2020年 / 56卷 / 04期
关键词：
Characteristic parameter; Failure/fault diagnosis; Gaussian Bayesian; Influence analysis; Mahalanobis distance;
D O I：
10.3901/JME.2020.04.035
中图分类号：
学科分类号：
摘要：
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. © 2020 Journal of Mechanical Engineering.
引用
收藏
页码：35 / 41
页数：6
相关论文
共 20 条
  • [1] Chen X., Fan Z., Chen Y., Et al., Green and intelligent design, manufacturing and maintenance of pressure vessels in China, Pressure Vessel Technology, 34, 11, pp. 12-17, (2017)
  • [2] David J.S., Reliability maintainability and risk-practical methods for engineers including reliability centered maintenance and safety related systems, (2005)
  • [3] Zhu J., Chen X., Ai Z., Et al., Consideration on the construction of risk management system for Chinese petrochemical plants, Petrochemical Equipment, 38, 6, pp. 45-49, (2009)
  • [4] Chen X., Fan Z., Jiang H., Et al., Creep-fatigue life prediction methods of pressure vessel typical steels under complicated loading conditions, Journal of Mechanical Engineering, 45, 2, pp. 81-87, (2009)
  • [5] Liu H., Ding P., Guo C., Et al., Study on Chinese spam filtering system based on Bayes algorithm, Journal on Communications, 39, 12, pp. 151-159, (2018)
  • [6] Zhao S., Jiang C., Long X., Remaining useful life estimation of mechanical systems based on the data-driven method and Bayesian theory, Journal of Mechanical Engineering, 54, 12, pp. 115-124, (2018)
  • [7] Liu D., Wang X., Huang J., Et al., Vibration fault diagnosis for hydro-power units based on Bayesian network, Journal of Hydroelectric Engineering, 38, 2, pp. 112-120, (2019)
  • [8] Xu B., Qu L., Tao X., Bayesian network framework for rotor fault diagnosis, Journal of Mechanical Engineering, 40, 1, pp. 66-72, (2004)
  • [9] Md T., Faisal K., Syed I., Fault detection and pathway analysis using a dynamic Bayesian network, Chemical Engineering Science, 195, pp. 777-790, (2019)
  • [10] Xu X., Liu X., Jiang Z., Et al., Multi-sensor distributed fault detection method based on subjective Bayesian reasoning, Journal of Mechanical Engineering, 51, 7, pp. 91-98, (2015)
12