Table 5 Performance comparison of fault detection models.

From: Innovative framework for fault detection and system resilience in hydropower operations using digital twins and deep learning

Model

Accuracy (%)

Precision (%)

Recall (%)

F1-Score (%)

RMSE

MSE

Execution Time (s)

Proposed CNN-LSTM

98.5

97.8

98.2

98.0

0.015

0.0002

1.25

Baseline CNN

95.2

94.5

94.8

94.6

0.025

0.0006

0.95

Baseline LSTM

96.3

95.8

96.0

95.9

0.020

0.0004

1.50

GRU-Based Model

97.1

96.6

96.8

96.7

0.018

0.0003

1.35

Traditional RNN

93.8

93.2

93.5

93.3

0.030

0.0009

1.75

Back to article page