Trans-SBLGCN: A Transfer Learning Model for Event Logic Knowledge Graph Construction of Fault Diagnosis

Abstract

Taking fault diagnosis corpus as the research object, an event logic knowledge graph construction method is proposed in this paper. Firstly, we propose a data labeling strategy based on a constructed event logic ontology model, then collect large-scale robot transmission system fault diagnosis corpus, and label part of the data according to the strategy. Secondly, we propose a transfer learning model called Trans-SBLGCN for event argument entity and event argument relation joint extraction. A language model is trained based on large-scale unlabeled fault diagnosis corpus and transferred to a model based on stacked bidirectional long short term memory (BiLSTM) and bidirectional graph convolutional network (BiGCN). Experimental results show that the method is superior to other methods. Finally, an event logic knowledge graph of robot transmission system fault diagnosis is constructed to provide decision support for autonomous robot transmission system fault diagnosis.