A New Fault Detection Algorithm for EMUs based on Deep Learning
Zhi Liu, Yanru Sun · 2017
Health monitoring is an important task for high-speed railway EMUs.Traditional methods for detection have the problem of low detection rate or high false alarm.In this paper, a new fault detection algorithm is proposed based on deep learning.A region proposal network is applied and a network is trained based on EMU images.Initial experiments show that the proposed network can achieve 95.67% accuracy in detection, which the speed of 0.1-0.2second per image.