Table 8 Bi-LSTM hyperparameters.

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

Hyperparameter

Value

Bi-LSTM layers

2

First layer units

128

Second layer units

64

Activation function

Tanh

Dropout rate

0.1

Dense units

32

Dense activation

ReLU

L2 regularization

1e-05

Learning rate

1e-3

Back to article page