LAUSR

Abstract In order to denoise the raw signal and fuse multiple sources of information for the fault diagnosis of reciprocating compressor, this paper proposes a novel convolutional deep belief network-based method and employs a novel framework fusing multi-source information to improve the performance of fault diagnosis. Firstly, signals from different sensors of the RC are input into an auto-denoising network, namely, ensemble empirical model decomposition-convolutional deep belief network, to denoise the signal and to extract more robust features by the unsupervised learning. Secondly, the extracted features of each source are input into multiple Gaussian process classifiers which are adopted as the members of probabilistic committee machine (PCM) to calculate the probabilities that each fault occurs. Finally, these probabilities are combined with an optimized weight to make a committee decision on fault type. The proposed method combines the information from multiple sources and enhances the robustness of fault diagnosis. Data from an industrial plant were collected to verify the proposed method. The obtained results demonstrate that the proposed method can effectively diagnose the RC faults with the accuracy rate of up to 91.89%. Furthermore, a comparison of the proposed method with the other methods illustrates the superiority of the proposed method for the diagnosis of RC faults.