Fault diagnosis of rotating machinery based on multiple probabilistic classifiers

Abstract

Abstract Intelligent fault diagnosis of rotating machinery is vital for industries to improve fault prediction performance and reduce the maintenance cost. The new fault diagnostic framework is proposed which consists of three stages: (1) signal processing and feature extraction, (2) fault diagnosis by combining the classification results through a probabilistic ensemble method, and (3) parameter optimization and performance evaluation. In the first stage, ensemble empirical mode decomposition (EEMD) decomposes the acquired signal into a suite of intrinsic mode functions (IMF) which encounters redundant components and large data problems. To eliminate the redundant IMF and select fault feature from residual IMF, correlation coefficient (CC) and singular value decomposition (SVD) method are applied respectively. In the second stage, to improve the performance of fault diagnosis based on single classifier and increase the number of detectable fault, a new probabilistic committee machine (PCM) method is proposed, in which multiple pairwise-coupled sparse Bayesian extreme learning machines (PCSBELM) are individually trained using air ration, ignition pattern and engine sound signal. In addition, each classifier is assigned with an optimal weight in accordance with their reliability and accuracy so that a reliable and widely-covered fault diagnostic result can be obtained from the weighted combination of the members. To verify the effectiveness of the proposed fault diagnostic framework, it is applied to automotive engine fault detection. The evaluation results show the proposed framework is superior to the existing single classifier in terms of both single- and simultaneous-faults in automotive engine.