Remaining useful life prediction of bearing based on deep perceptron neural networks

The life assessment and prediction research of the bearing is the most important content of the bearing long life and high reliable research. A novel remaining useful life prediction of bearing model that is deep learning based on deep perceptron neural networks (DPNN) is proposed in the present paper. Wavelet packet energy feature is extracted and then middle layers of the perceptron neural networks constitute a multilayer neural network. After training, remaining useful life (RUL) of bearing can be predicted by the DPNN model according to previous data points. To confirm the effectiveness of DPNN, Least Squares Support Vector Machine (LS-SVM) is employed to present a comprehensive comparison. The experimental results show that DPNN can predict effectively the RUL of bearing with high prediction accuracy and strong robustness.