A Deep Learning Network via Shunt-Wound Restricted Boltzmann Machines Using Raw Data for Fault Detection

Intelligent fault detection has been widely used for feature extraction and fault classification. However, various complex signal processing methods are adopted in many researches. This article presents a novel deep learning network via shunt-wound restricted Boltzmann machines (RBMs) with layerwise feature learning to learn the fault features from big raw vibration signals directly. The network consists of split layer, predict layer, update layer, dephasing layer, and softmax layer. The shunt-wound RBMs are used in both predict layer and update layer to improve the feature extraction ability and to ensure effective training of the network. The operation of predicting and updating is considered to be a layerwise feature learning which makes the network effective. The proposed method is verified by three bearing data sets and a few related researches are introduced for comparison. The results prove that the proposed method is capable of extracting sensitive features for fault detection.