Attention Mechanism-Based CNN-LSTM Model for Wind Turbine Fault Prediction Using SSN Ontology Annotation

Table 4

Experimental results of the model on the dataset of No. 21 and No. 4 wind turbine.

Algorithm	Wind turbine icing fault dataset				Wind turbine yaw fault dataset
	No. 21 wind turbine				No. 4 wind turbine
	CLA	0.7492	0.8171	0.7421	0.7591	0.7709	0.8143	0.7429	0.7737
LSTM	0.7242	0.7279	0.7163	0.7220	0.7455	0.8000	0.6546	0.7201
RNN	0.6793	0.6793	0.6792	0.6793	0.7248	0.7637	0.6511	0.7029
XGBoost	0.7038	0.7120	0.6847	0.6981	0.7038	0.7120	0.6847	0.6981