Multi-source heterogeneous information fusion fault diagnosis method based on deep neural networks under limited datasets

Intelligent fault diagnosis of critical components of rotating machinery is essential for enhancing production efficiency and reducing maintenance costs. However, the scarce labeled samples and the single monitoring data hinder the engineering application and generalization of diagnostic models to some extent. To this end, a novel multi-source heterogeneous information fusion (MSHIF) network is proposed in this paper to identify the health status of rotating machinery more comprehensively and robustly under limited datasets. Specifically, the data enhanced deep belief network (DEDBN) and data enhanced one-dimension convolutional neural network (DE-1DCNN) are firstly designed by repeatedly appending raw data to the hierarchy of conventional deep belief network (DBN) and one-dimension convolutional neural network (1DCNN). DEDBN and DE-1DCNN improve the diagnostic performance of the model under limited datasets while effectively mitigating the loss of potentially valuable information during layer-by-layer feature extraction and compression of DBN and CNN. Then, the MSHIF is further constructed with the designed DEDBN and DE-1DCNN as structural branches. MSHIF aims to alleviate the limitations of scarce labeled samples and single monitoring data on diagnostic performance within a unified framework by mining the rich and complementary device status information in multi-source heterogeneous monitoring data. Extensive comparative experiments and detailed discussions are constructed on both publicly available datasets and rolling mill experimental dataset to verify the feasibility and effectiveness of MSHIF. The experimental results demonstrate that the proposed MSHIF outperforms other comparative methods in terms of diagnostic accuracy, stability, and robustness against noise, achieving 99.491%, 99.143%, and 99.037% average identification accuracy on three cases, respectively.