Spatial-temporal graph convolutional networks (STGCN) based method for localizing acoustic emission sources in composite panels

•Spatial-temporal graph convolutional networks (STGCN) based method for damage localization is proposed.•Spatial-temporal features of AE sensor networks are extracted combining with graph theory.•A new distance-based graph connectivity method is developed.•Validity of the proposed STGCN method is approved by experiments. A novel spatial–temporal graph convolutional networks (STGCN) based method for the regression task of localizing acoustic emission (AE) sources in composite panels is proposed. This is the first time that graph convolutional networks are introduced into the AE source localization task. Data generated by AE sensor networks is represented by a graph structure, in which the temporal features extracted from AE waveforms using one-dimensional convolutional neural networks (1D-CNN) and the spatial information of sensors constitute the node features. An adaptive distance-based adjacency matrix calculation method according to the geographical locations of AE sensors is further developed to represent the connectivity of the graph. Finally, the proposed method is experimentally validated on a glass fiber-reinforced plastic (GFRP) panel, and 5-fold cross-validation was carried out to evaluate the performance of the method effectively. The results show that the proposed STGCN method has a high performance in damage source localization and it significantly outperforms other methods.