Skip to main content

Table 2 Overall classification accuracy, precision, recall, F-score results from the first bearing dataset using the RGBVI-CNN method with 40% to 70% training size

From: Connected Components-based Colour Image Representations of Vibrations for a Two-stage Fault Diagnosis of Roller Bearings Using Convolutional Neural Networks

Training size (%)

Overall classification accuracy

Overall precision

Overall recall

F-score

40

99.3% ± 0.7

99.2% ± 0.8

99.3% ± 0.6

99.3% ± 0.7

50

99.8% ± 0.1

99.8% ± 0.1

99.8% ± 0.1

99.8% ± 0.1

60

99.9% ± 0.1

99.9% ± 0.1

99.9% ± 0.1

99.9% ± 0.1

70

100% ± 0.0

100% ± 0.0

100% ± 0.0

100% ± 0.0