This paper proposed a neural network (NN) based remaining useful life (RUL) prediction approach. A new performance degradation index is designed using multi-feature fusion techniques to represent deterioration severities of facilities. Based on this indicator, back propagation neural networks are trained for RUL prediction, and average of the networks’ outputs is considered as the final RUL in order to overcome prediction errors caused by random initiations of NNs. Finally, an experiment is set up based on a Bently-RK4 rotor unbalance test bed to validate the neural network based life prediction models, experimental results illustrate the effectiveness of the methodology.

A novel feature extraction method is presented by combining wavelet packet transform with ant colony clustering analysis in this paper. Vibration signals acquired from equipments are decomposed by wavelet packet transform, after which frequency bands of signals are clustered by ant colony algorithm, and each cluster as a set of data is analyzed in frequency-domain for extracting intrinsic features reflecting operating condition of machinery. Furthermore, the robust ant colony clustering algorithm is proposed by adjusting comparing probability dynamically. Finally, effectiveness and feasibility of the proposed method are verified by vibration signals acquired from a rotor test bed.