Fault Diagnosis of a Hydro Turbine Generating Set Based on Support Vector Machine

With the application of large capacity hydro turbine generating set, it is important for the hydro turbine generating set to monitoring its vibration and diagnoses its faulty. In this paper, fault diagnosis based on support vector machine is proposed for hydro turbine generating set. The most important advantage of SVM is effective for the case of lack of training samples. Some key parameters of SVM and kernel functions are surveyed. Compared with the artificial neural network methods, SVM methods are more effective. The experiment shows that the SVM method has good classification ability and robust performances.