A Fault Diagnosis Approach for Gas Turbine Exhaust Gas Temperature Based on Fuzzy C-Means Clustering and Support Vector Machine

摘要: As an important gas path performance parameter of turbine, exhaust temperature (EGT) can represent the thermal health condition turbine. In order to monitor and diagnose EGT effectively, a fusion approach based on fuzzy C-means (FCM) clustering algorithm support vector machine (SVM) classification model is proposed in this paper. Considering distribution characteristics turbine EGT, FCM used realize analysis obtain state pattern, basis which preclassification completed. Then, SVM multiclassification designed carry out pattern recognition fault diagnosis. example, historical monitoring data from industrial analyzed verify diagnosis presented The results show that make full use unsupervised feature extraction ability sample generalization properties model, offers effective way online EGT.