Support Vector Machine for Vibration Fault Classification of Steam Turbine-Generator Sets

Abstract

To solve the vibration fault diagnosis of steam turbine-generator sets (STGS), this paper presents support vector machine (SVM) to extract the support vector from database for vibration fault diagnosis of the sets. In this paper, the SVM is used to construct the vibration fault diagnosis model. The test results demonstrate that the proposed method has less learning time and higher diagnosis than the existing methods. Thus, the feasibility of applying the proposed method to the practical vibration fault diagnosis of the STGS has been confirmed.