Study of fault diagnosis based on SVM for turbine generator unit

Abstract

A support vector machine (SVM) is presented for diagnosing the fault of the turbine generator unit. The SVM is based on the statistical learning theory and the structural risk minimization principle. It not only has greater generalization ability, but also a better solution to the small sample learning classification problems. In the case of limited feature information, SVM can explore furthest the classification of knowledge implicit in the sample data, and thus achieve better classification results. The simulation results show that the proposed method can effectively diagnose the vibration fault of turbine generator, and has good application prospects.