Li-Yan Yang

FD-SE-LLM: A Semantic-Enhanced Large Language Model Framework for Fault Diagnosis of Hydropower Carbon Brush Bearings

FD-SE-LLM, a Semantic-Enhanced Large Language Model Framework for Fault Diagnosis targeting hydropower carbon brush bearings is proposed, which includes a Fault-specific Multi-class Conditional Variational Autoencoder, and an embedded Bearing Time-Adapter to enhance transient pulse sensitivity.