Fault Diagnosis Technology Research on Autopilot

Abstract

Aiming at the issues of the autopilot that has many fault types, less data sample and less test interface, this paper analyzes the fault isolation ability of automatic test system in detail. Moreover, the knowledge acquisition method based on simulation is studied so that the existing drive instrument test system is improved. In addition, an improved support vector machine inference algorithm is proposed. Based on this, a new method of fault diagnosis of a testing system is presented. Finally, some examples are given to verify the correctness and validity of the method. The successful application in a certain missile drive device shows that the method can achieve good diagnosis results.