Turbine Blade Fault Detection Based On Feature Extraction

This paper is aimed at making diagnosis for turbine blades by processing data. In this paper three kinds of feature are extracted, using time-domain analysis, wavelet packet decomposition and fractal analysis respectively. K-means algorithm is improved to classify data. The method of improved ReliefF is taken to allocate weights of each feature. This article calculates combined feature center distance synthesized. Take the obtained centre distance as a threshold to diagnose faults. Comparison is made to verify that application of cluster analysis and weight allocation algorithm can reduce error rate in detecting diagnosing faults for turbine blades.