Fault diagnosis of rotating machinery using Gaussian process and EEMD-treelet

Abstract

Fault detection of rotating machinery is very important for its performance degradation assessment. In this work, an effective feature learning and detecting method based on the ensemble empirical mode decomposition (EEMD) and Gaussian process classifier (GPC) is put forward. Compared with the traditional parameter optimization methods of GPC, this work proposed a bacterial foraging optimization as the optimal solution of the hyperparameters of GP model. To find a valid feature vector, this work also utilized EEMD to decompose the vibration signals and get some time-frequency features. Then, treelet transform is proposed to reduce the feature dimension. The results of some applications indicate that the EEMD has stronger processing capability of the status signals of rotating machinery. Treelet can transform the high-dimensional vector to low-dimensional space, which is used as the input of the proposed BFO-GP model. The proposed diagnosis method can identify not only the optimal feature vector but also the fault locations.