Multi-view graph convolutional networks based on multi-source information fusion for mechanical fault diagnosis

Data-driven intelligent diagnosis methods have demonstrated significant success within prognostics and health management systems due to their powerful feature representation and non-linear fitting capabilities. However, most existing methods employ simple fusion strategies and neglecting data structure considerations, which lead to incomplete feature representations for final diagnostic decisions. In this article, we address these limitations by proposing a multiview graph convolutional network [Formula: see text] framework based on multi-source information fusion for fault diagnosis of key components in mechanical equipment. This is achieved through joint research on sample graph and feature graph learning. First, convolution neural networks named the SharedNet module are leveraged to extract multi-source features, and then the deep features are concatenated in a fully connected layer. After that, we construct multi-view initial graphs to combine the correlations between samples and features to mine rich graph topology structure. Then, we redesign the graph learning strategy to further increase the robustness and generalizability of the proposed method. Finally, extensive experimental results on the multi-information datasets show that our proposed [Formula: see text] can not only outperform the state-of-the-art methods of comparison but also extract multi-view graph topology and feature representations for fault diagnosis.