A novel sensor fault diagnosis method based on Modified Ensemble Empirical Mode Decomposition and Probabilistic Neural Network

A novel fault diagnosis method based on Modified Ensemble Empirical Mode Decomposition (MEEMD) and Probabilistic Neural Network (PNN) is presented in this paper. It aims to achieve more accurate and reliable sensor fault diagnosis in thermal power plant. To restrain the mode mixing problem in traditional EMD, an MEEMD is proposed based on signal reconstruction and pseudo component identification. The MEEMD is applied to decompose the original thermal parameter signals into a finite number of Intrinsic Mode Functions (IMFs) and a residual to extract the sensor fault feature. After analyzing the inherent physical meanings of each IMF and residual, the variances of them are extracted as feature eigenvectors to express the signal feature. Finally, PNN is used as the classifier for detection and identification of sensor faults. Based on the practical normal signals, which are collected from a main steam temperature sensor of a CLN600-24.2/566/566 steam turbine, three types of representative sensor fault signals are simulated to test the proposed method. By analyzing simulation and real signal, the analysis results indicate that the MEEMD can restrain the mode mixing problem in traditional EMD effectively, and the proposed fault diagnosis method had better performance than the other two fault diagnosis methods including basic PNN and EMD-PNN.