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

Dongdong Liu. Jun Wei. Mingzhe Wu. Nan Yu. Chao Wang. Shuan Ji.

DOI: https://doi.org/10.70114/acmsr.2024.1.1.P223

Keywords:

Condition prediction; neural network; train safety protection; intelligent control.

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.