Fault Diagnosis of Roller Bearing Based on Volterra and Flexible Polyhedron Search Algorithm

In this paper, the basic theory of Voltera series is briefly introduced. The kernel of Volterra is identified by the polyhedron search algorithm. Different from the traditional diagnostic method based on signal processing, this method applies the Volterra series based on the system model to the fault diagnosis of the roller bearing system. The change of the Volterra series kernel is used to distinguish the different fault state of the roller bearing. The experimental results verify the feasibility and effectiveness of the method.