A Novel Fault Detection with Minimizing the Noise-Signal Ratio Using Reinforcement Learning

Dapeng Zhang; Zhiling Lin; Zhiwei Gao

doi:10.3390/s18093087

A Novel Fault Detection with Minimizing the Noise-Signal Ratio Using Reinforcement Learning

Sensors (Basel). 2018 Sep 13;18(9):3087. doi: 10.3390/s18093087.

Authors

Dapeng Zhang¹, Zhiling Lin², Zhiwei Gao³

Affiliations

¹ School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China. zdp@tju.edu.cn.
² School of Electrical Engineering, Tianjin University of Technology, Tianjin 300384, China. Linzl2002@163.com.
³ Faculty of Engineering and Environment, University of Northumbria, Newcastle upon Tyne NE2 8ST, UK. zhiwei.gao@northumbria.ac.uk.

Abstract

In this paper, a reinforcement learning approach is proposed to detect unexpected faults, where the noise-signal ratio of the data series is minimized to achieve robustness. Based on the information of fault free data series, fault detection is promptly implemented by comparing with the model forecast and real-time process. The fault severity degrees are also discussed by measuring the distance between the healthy parameters and faulty parameters. The effectiveness of the algorithm is demonstrated by an example of a DC-motor system.

Keywords: fault detection; noise-signal ratio; reinforcement learning.