Decision fusion system for fault diagnosis of elevator traction machine

Fault detection and diagnosis is critical for healthy operation of an elevator system. In order to realize a real-time and convenient diagnosis and satisfy the requirement of advanced maintenance of an elevator system, this paper proposes an intelligent fault diagnosis approach of induction motor for elevator traction machine using a developed decision fusion system. First, the basic knowledge of fusion techniques is briefly introduced which consists of classifier selection and decision fusion. Then a developed decision fusion system is presented. Next, four fusion algorithms-majority voting, Bayesian belief, multi-agent and modified Borda count-are employed for comparison in a real-world diagnosis experiment of a faulty elevator motor system. Based on the satisfactory results shown in the experiment, a big potential in real-world application is presented that is effective and cost saving only by analyzing stator current signals using proposed decision fusion system.