Research on the Health State Assessment of Electromagnetic Relays Based on PSO-SVM-DS

Relay is widely used in the control system of metro vehicles. Its reliable and safe operation is the necessary condition to ensure the normal operation of metro vehicle system. To effectively assess the operating status of the relay and timely discover potential hazards, this paper proposes a state assessment method based on support vector machine optimized by particle swarm optimization algorithm combined with D-S evidence theory (PSO-SVM-DS). And an electromagnetic relay test rig is set up to collect five sorts of time characteristic parameters. Finally, compared with the traditional D-S evidence theory algorithm on the test set, the model proposed in this paper achieves higher recognition accuracy.