关键词: 航空直流起动发电机, 故障检测与诊断, 频谱分析, 神经网络

Abstract: This paper discusses the fault detection and diagnosis of Aero-Starter-Generator. Applying the method of Spectrum Analysis to the motor current to get the characteristics of this signal in frequency domain, and then using them as learning samples to train the network for realizing the mapping relationship between the fault and the spectrum characteristic, this method can be used for detection and diagnosis of the motor faults efficiently. The fault experiments show that the proposed method can detect and diagnose the faults of Aero-Starter-Generator easily, efficiently and in real-time.

Key words: Aero-Starter-Generator, fault detection and diagnosis, spectrum analysis, neural network