Research on relay safety output control method based on BP neural network

Abstract

With the continuous improvement and expansion of the metro network, the issues of train safety capacity, transportation effi-ciency and maintenance cost will become increasingly prominent. As an indispensable switching and controlling device of train safety control system, the health status of relay is the foundation of low-cost, high safety and efficient development of subway. This paper designs and proposes a BP neural network based relay safety output control method, this method utilizes BP neural net-work on the basis of improved two-take-two hardware structure to do fault prediction and safety state management with real-time retrieved detection signals, finally uploads operation and mainte-nance logs to the platform to guide subsequent fault trouble-shooting and maintenance.