Support vector machine used to diagnose the fault of rotor broken bars of induction motors

The data-based machine learning is an important aspect of modern intelligent technology, while Statistical Learning Theory (SLT) is a new tool that studies the machine learning methods in the case of a small number of samples. As a common learning method, Support Vector Machine (SVM) is derived from the SLT. Here we were done some analogical experiments of the rotor broken bar faults of induction motors used, analyzed the signals of the sample currents with Fourier transform, and constructed the spectrum characteristics from low frequency to high frequency used as learning sample vectors for the SVM. After a SVM is trained with learning sample vectors, so each kind of the rotor broken bar faults of induction motors can be classified. Finally the retest is demonstrated, which proves that the SVM really has preferable ability of classification. In this paper we tried applying the SVM to diagnose the faults of induction motors, and the results suggested that the SVM could yet be regarded as a new method in the fault diagnosis.