Table 14 Performance comparison of 1D-CNN based hybrid models.

From: Early prediction of wind turbine anomalies using 1D-CNN and temporal feature engineering on multi-source SCADA data

Model

CNN-LSTM

CNN-BiLSTM

CNN-RNN

CNN-GRU

Proposed CNN-LSTM-attention

Accuracy

86%

80%

83%

81%

87%

Back to article page