Table 12 Ablation results of MFRANet under Gaussian noise (%).

From: A novel intelligent fault diagnosis method for gearbox based on multi-dimensional attention denoising convolution

Methods

6 dB

4 dB

2 dB

0 dB

− 2 dB

− 4 dB

− 6 dB

MFRANet

93.91

88.89

80.37

67.12

50.53

36.68

28.16

MDSCMod

No DSC

88.58

82.80

72.30

59.21

44.44

33.18

25.27

No DSC

91.78

86.61

77.63

62.71

50.38

37.29

26.18

No ECA

91.93

87.82

81.13

67.58

49.92

36.83

27.25

ERCAMod

No D&E

92.39

88.28

78.84

66.36

49.32

37.29

27.55

EAMod

No EAMod

92.39

87.52

78.69

65.45

52.36

38.51

30.44

  1. Significance values are in bold.
Back to article page