Data-driven Fault Diagnosis Method for Transmission Sensors

被引：0
|
作者：
Wu G. [1 ]
Tao Y. [1 ]
Zeng X. [1 ]
机构：
[1] School of Automotive Studies, Tongji University, Shanghai
来源：
Tongji Daxue Xuebao/Journal of Tongji University | 2021年 / 49卷 / 02期
关键词：
Data-driven method; Probabilistic neural network (PNN); Sensor model; Transmission fault diagnosis; Wavelet packet transform(WPT);
D O I：
10.11908/j.issn.0253-374x.20225
中图分类号：
学科分类号：
摘要：
Aiming at the limitations of model-based and rule-based fault diagnosis methods, a data-driven fault diagnosis method for transmission sensors was proposed. First, a residual sequence was obtained between the output of actual sensor and the output of sensor model established by step-wise regression. Then, the residual sequence was decomposed by wavelet packet transform(WPT), and the Shannon entropy of each node was calculated as the feature values. Finally, a probabilistic neural network(PNN) was adopted to identify the feature values of different sensor faults. This method is verified by transmission signals from hardware-in-the-loop platform. Results indicate that the method has a diagnostic accuracy of 98.50%, and the diagnostic accuracy varies little under different sample divisions. In addition, the fault diagnoses of two speed sensors were also performed, and the diagnostic accuracy is at a relatively high value, which proves the applicability of the method. © 2021, Editorial Department of Journal of Tongji University. All right reserved.
引用
收藏
页码：272 / 279
页数：7
相关论文
共 15 条
  • [1] REZA S, REZA L., Isolability of faults in sensor fault diagnosis, Mechanical Systems and Signal Processing, 25, 7, (2011)
  • [2] IRERMANN R., Supervision, fault-detection and fault-diagnosis methods: an introduction, Control Engineering Practice, 5, 5, (1997)
  • [3] LEE H., Analysis of model-based sensor fault diagnosis with application to a motor-driven power steering system, Proceedings of the Institution of Mechanical Engineering, Part D: Journal of Automobile Engineering, 225, 10, (2011)
  • [4] WANG Dejun, SONG Shiyao, Robust model-based sensor fault monitoring system for nonlinear systems in sensor networks, Sensors, 14, 10, (2014)
  • [5] YANG Zongxiao, YUAN Xiaobo, FENG Zhiqiang, Et al., A fault prediction approach for process plants using fault tree analysis in sensor malfunction, 2006 IEEE International Conference on Mechatronics and Automation, pp. 2415-2420, (2006)
  • [6] ZHANG Q, OKRENT Q, APOSTOLAKIS G, Et al., An expert system approach for fault diagnosis to cope with spurious sensor signals and process state uncertainty, Reliability Engineering & System Safety, 34, 2, (1991)
  • [7] FAN Liwei, Research and optimized realization of self-validating sensor fault diagnosis algorithm based on DSP, (2008)
  • [8] JI Junjie, QU Jianfeng, CHAI Yi, Et al., An algorithm for sensor fault diagnosis with EEMD-SVM, Transactions of the Institute of Measurement and Control, 40, 6, (2018)
  • [9] WANG Kai, CHEN Junghui, SONG Zhihuan, Data-driven sensor fault diagnosis systems for linear feedback control loop, Journal of Process Control, 45, (2017)
  • [10] YOU Shibing, YAN Yan, Stepwise regression analysis and its application, Statistics & Decision, 14, (2017)
12