Neural Network Based Expert System for Induction Motor Faults Detection

摘要: Early detection and diagnosis of incipient induction machine faults increases machinery availability, reduces consequential damage, improves operational efficiency. However, fault using analytical methods is not always possible because it requires perfect knowledge a process model. This paper proposes neural network based expert system for diagnosing problems with motors vibration analysis. The short-time Fourier transform (STFT) used to the quasi-steady signals, trained tested spectra. efficiency developed evaluated. results show that can be on measurements acquired on-line from machine.