Reciprocating compressor fault diagnosis using an optimized convolutional deep belief network

Abstract

This article proposes an optimized convolutional deep belief network for fault diagnosis of reciprocating compressors. Sparse filtering is first used to compress raw signal into compact time series by refining the most representative information and to reduce the computational burden. Then, the proposed convolutional deep belief network is adopted to learn the unsupervised features of the compressed signal without the need of feature extraction by human effort. To improve the generalization ability of the network, an optimized probabilistic pooling out is proposed in this article to replace the standard one in the pooling layer of the convolutional deep belief network. Finally, the unsupervised features calculated by the optimized convolutional deep belief network are fed as the input of the softmax regression classifier for fault identification. Four types of vibration signals reflecting different operating conditions are collected from the industry to validate the effectiveness of the proposed method. The obtained results demonstrate that the proposed convolutional deep belief network method can achieve a higher classification accuracy rate of up to 91% for fault diagnosis than the traditional methods and accomplish the fault diagnosis of reciprocating compressor effectively.