Automated Inspection System for Defect Detection in Trains

Accurate inspection and rapid identification of defects and faults would assist in taking measures to reduce the overall operation and maintenance cost and improve the energy efficiency. In this context, application of automated inspection system for defect or fault detection has gained wider attention. In this paper automated defect detection in trains is discussed. One part of inspection in railways includes the checking of springs, which connect axlebox to bogie and frame to the train. The inspection process these days in railways are mostly manual hardships which results in less accuracy and efficiency. To minimize errors and increase the work efficiency machine vision systems are being developed. This paper talks about one such machine vision system which inspects the springs in railway train. This system uses advanced cameras stationed trackside to capture images of the train as it passes by. This inspection system uses deep learning algorithms - UNet, to capture multiple images and learn about faults in the spring. Furthermore, to increase the efficiency of the algorithm, a basic optimizer called RMSProp was modified.