Bearing fault diagnosis method based on bearing fault knowledge graph

The invention discloses a bearing fault diagnosis method based on a bearing fault knowledge graph, and relates to the technical field of aviation, and the method comprises the steps: obtaining a text classification model through the training of a sample text content and a text label corresponding to the sample text content based on a deep learning model of fusion adversarial training; a confrontation training and text classification model fusion mode is adopted to adapt to text data with different sources and different qualities and realize automatic classification, and then a fault description text of a fault bearing is input into a text classification model after data preprocessing to obtain a corresponding text label; the text label is used for representing an attribute type of a fault phenomenon described by the fault description text, and then filling the fault description text into an FMECA table according to the text label of the fault description text to construct a bearing fault knowledge graph which