The invention relates to the technical field of operation and inspection of wind
turbine generator equipment, and discloses a
knowledge graph and
deep learning-based fan anomaly monitoring and operation and inspection optimization method, which comprises the following steps of: acquiring operation data of a wind
turbine generator through an
SCADA (
Supervisory Control and
Data Acquisition)
system, and acquiring state data of the wind
turbine generator through a CMS (
Content Management System)
system; obtaining operation and maintenance data of the wind turbine generator; constructing a TCN-BiGRU-
Attention network model to analyze the multi-dimensional data, and outputting an anomaly type and confidence coefficient predicted by the model; constructing a double-layer
knowledge graph; taking the exception type as input, extracting a feasible scheme according to a graph
reasoning algorithm, and outputting an operation inspection strategy triple; and inputting the operation and
maintenance strategy triple and the multi-dimensional data into the large
language model, performing multi-round semantic reasoning and strategy optimization, and outputting an optimal operation and
maintenance strategy. The method has the advantages that the high precision of anomaly identification and the high reliability of operation and maintenance decision are realized, the expandability and the practical value are good, and the method is suitable for various scenes such as intelligent
wind power plant operation and maintenance, remote state monitoring and intelligent scheduling.