On-line condition monitoring of railway neural networks-based intelligent sensors

The paper deals with the research carried out at the University of Birmingham, UK and funded by London Underground Limited (LUL) into early-failure warning systems for safety-critical railway signalling equipment. The paper outlines the motivation for the research, a brief overview of the requirements for condition monitoring systems, a summary of various condition monitoring and fault diagnosis used in the study. The process of laboratory tests and field trials which led to the development of ideas and techniques for the employment of intelligent neural network-based sensors for online condition monitoring of railway equipment are briefly reported. Problems still to be tackled are addressed. (3 pages)