Sensor fault diagnosis method based on wavelet neural network and passive observer

被引：0
|
作者：
Xu H. [1 ,2 ]
Huang Y. [1 ]
Yu W. [1 ,2 ]
机构：
[1] School of Transportation, Wuhan University of Technology, Wuhan
[2] Key Laboratory of High Performance Ship Technology of Ministry of Education, Wuhan University of Technology, Wuhan
来源：
Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of Science and Technology (Natural Science Edition) | 2020年 / 48卷 / 04期
关键词：
Back-propagation neural network; Dynamic positioning; Fault diagnosis; Nonlinear passive observer; Sensors; Wavelet packet decomposition;
D O I：
10.13245/j.hust.200417
中图分类号：
学科分类号：
摘要：
For the autonomous and intelligent dynamic positioning ship, the performance of the sensor fault diagnosis is reduced, and the false negatives and false positives frequently occur, which would affect the safety of the task.Therefore, a diagnostic method combining model and data was proposed.The method combined a nonlinear passive observer with a back-propagation (BP) neural network, and introduced a wavelet packet decomposition method to process the data set.Thereby, the energy in each frequency band of the fault signal was obtained, and the classification features were refined.The simulation based on a dynamic positioning ship was carried out.Results show that the method overcomes the problems of unknown disturbance and low model accuracy in the output of a single observer, which solves the problems of less neural network historical data set and the unknown representativeness, and finally improves the fault recognition performance. © 2020, Editorial Board of Journal of Huazhong University of Science and Technology. All right reserved.
引用
收藏
页码：91 / 96
页数：5
相关论文
共 5 条
  • [1] Li J., Zhang X.Y., Chen X.H., Et al., Sensor fault diagnosis study of UUV based on the grey forecast model, Proc of 2015 IEEE International Conference on Mechatronics and Automation, pp. 1750-1754, (2015)
  • [2] Lo C., Lynch J.P., Liu M., Distributed model-based nonlinear sensor fault diagnosis in wireless sensor networks, Mechanical Systems & Signal Processing, 66-67, pp. 470-484, (2016)
  • [3] Xia J., Guo Y., Dai B., Et al., Sensor fault diagnosis and system reconfiguration approach for electric traction PWM rectifier based on sliding mode observer, IEEE Transactions on Industry Applications, 53, 5, pp. 4768-4778, (2017)
  • [4] Li J., Pan K.P., Zhang D.Z., Et al., Robust fault detection and estimation observer design for switched systems, Nonlinear Analysis: Hybrid Systems, 34, pp. 30-42, (2019)
  • [5] Zhou J., Yang Y., Ding S.X., Et al., A fault detection and health monitoring scheme for ship propulsion systems using SVM technique, IEEE Access, 6, pp. 16207-16215, (2018)
1