Study of a Fault Diagnosis Method Based on Elman Neural Network and Trouble Dictionary

摘要

Because the traditional fault diagnosis methods had shortcomings, such as that the diagnosis speed was slow and it was hard to accurately fix the faults taking place at one time when it was diagnosing the complicated system or equipment, the fault diagnosis technology based on Elman neural network and trouble dictionary were introduced here. With the major failure of certain mould aircraft autopilot's flying-controlled box as the example, the real diagnosis course and method was analyzed and explained, and so on, the simulation research was made. The high-speed diagnosis for one fault and some faults taking place at one time is realized. The results show that this failure diagnosis method is effective to solve the issue.