Accesso libero

A Bearing Fault Diagnosis Model based on Minimum Average Composite Entropy and Parallel Attention Mechanism Convolutional Neural Network

Zhen Zhang

Zhen Zhang

  • Henan University of TechnologyZhengzhou, China
  • Zhejiang University - Zhongyuan InstituteZhengzhou, China
Profilo Orcid
Cerca questo autore su
Sciendo|Google Scholar
Zhang, Zhen
, 
Shixi Yang

Shixi Yang

  • School of Mechanical Engineering, Zhejiang UniversityHangzhou, China
  • Zhejiang University - Zhongyuan InstituteZhengzhou, China
Cerca questo autore su
Sciendo|Google Scholar
Yang, Shixi
, 
Jun He

Jun He

  • School of Mechanical Engineering, Zhejiang UniversityHangzhou, China
  • Zhejiang University - Zhongyuan InstituteZhengzhou, China
Cerca questo autore su
Sciendo|Google Scholar
He, Jun
, 
Wanchun Zhou

Wanchun Zhou

Zhejiang University - Zhongyuan InstituteZhengzhou, China
Cerca questo autore su
Sciendo|Google Scholar
Zhou, Wanchun
 e 
Yanxu Liu

Yanxu Liu

Zhejiang University - Zhongyuan InstituteZhengzhou, China
Cerca questo autore su
Sciendo|Google Scholar
Liu, Yanxu
  
14 ago 2025
A Bearing Fault Diagnosis Model based on Minimum Average Composite Entropy and Parallel Attention Mechanism Convolutional Neural Network's Cover Image
INFORMAZIONI SU QUESTO ARTICOLO
Articolo precedente
Articolo Successivo
Cita
Scarica la copertina
Pubblicato online: 14 ago 2025
Pagine: 178 - 189
Ricevuto: 28 feb 2025
Accettato: 27 mag 2025
DOI: https://doi.org/10.2478/msr-2025-0022
Parole chiave
© 2025 Zhen Zhang, published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial 4.0 International License.

Fig. 1.

Research block diagram.
Research block diagram.

Fig. 2.

Sk, Sr, Re schematic diagram of variation with defects.
Sk, Sr, Re schematic diagram of variation with defects.

Fig. 3.

Sk, Sr, Re sensitivity to accidental noise.
Sk, Sr, Re sensitivity to accidental noise.

Fig. 4.

Schematic diagram of the variation with defects.
Schematic diagram of the variation with defects.

Fig. 5.

Schematic diagram of the channel attention mechanism.
Schematic diagram of the channel attention mechanism.

Fig. 6.

Schematic diagram of the spatial attention mechanism.
Schematic diagram of the spatial attention mechanism.

Fig. 7.

MACE + PFACNN model structure diagram.
MACE + PFACNN model structure diagram.

Fig. 8.

Time domain waveform of outer ring signal.
Time domain waveform of outer ring signal.

Fig. 9.

Fitness function.
Fitness function.

Fig. 10.

Entropy change curve.
Entropy change curve.

Fig. 11.

Analysis results after MACE-VMD.
Analysis results after MACE-VMD.

Fig. 12.

Analysis results of noise resistance.
Analysis results of noise resistance.

Fig. 13.

Analysis results of the ability to resist complex noises.
Analysis results of the ability to resist complex noises.

Fig. 14.

Analysis results of the generalization ability.
Analysis results of the generalization ability.

Fig. 15.

Experimental layout.1. Motor, 2. Coupling, 3. Acceleration sensor, 4. Bearing housing I, 5. Spindle, 6. Rotor, 7. Acceleration sensor, 8. Bearing housing II, 9. Bearing I, 10. Bearing II.
Experimental layout.1. Motor, 2. Coupling, 3. Acceleration sensor, 4. Bearing housing I, 5. Spindle, 6. Rotor, 7. Acceleration sensor, 8. Bearing housing II, 9. Bearing I, 10. Bearing II.

Fig. 16.

Fault diagnosis results.
Fault diagnosis results.

Fig. 17.

Visualization results after diagnosis.
Visualization results after diagnosis.

Fig. 18.

Analysis results of generalization ability.
Analysis results of generalization ability.

Dataset classification_

Fault location Failure diameter [mm] Tag Dataset
Training set Test set
Regular —— 1 70 30
Inner ring —— 2 70 30
Outer ring 90° 3A 70 30
135° 3B 70 30
Regular —— 4 70 30
Compound failure outer 90° 5A 70 30
outer 135° 5B 70 30

Experimental results of 5 dB complex noise comparison_

Model MACE + PFACNN RVMD+ DCNN RVMD+ CNN E+CNN BiGRU E+CNN SVM
Accuracy [%] 91.3 80.1 52.1 54.2 48.3
Recall rate [%] 91.6 80.5 52.7 54.9 48.8
F1 [%] 91.4 80.3 52.5 54.6 48.6

Results of ablation experiment_

Module
 Model Accuracy [%]
1 2 3
× × √ A 91.2
× √ √ B 93.7
√ × √ C 97.4
√ √ × D 95.3
√ √ √ E 98.9

Experimental parameters_

Inner diameter [mm] Pitch diameter [mm] Thickness [mm] Outer diameter [mm] Rolling diameter [mm] Contact angle [°]
25 39 15 52 8 0

Fault diagnosis results_

Category Accuracy [%] Category Accuracy [%]
1 100 6 100
2 100 7 100
3 100 8 99.3
4 100 9 99.3
5 100 10 100

Results of 0 dB white noise comparison test_

Model MACE + PFACNN IF+ CNN M+ CNN E+CNN E+ CNNSVM
Accuracy [%] 89.2 64.5 51.6 67.8 72.4
Recall rate [%] 89.8 64.9 52.1 68.2 72.9
F1 [%] 89.7 64.6 51.8 67.7 72.6

Generalization experiment results – Accuracy [%]_

Model MACE + PFACNN E+CNN E+SVM IF+CNN M+ DCNN
3A-3B 97.98 91.14 91.12 89.99 90.11
3B-3A 93.64 92.13 88.96 90.96 89.11
5A-5B 93.87 90.11 89.13 86.57 90.40
5B-5A 92.01 89.41 90.11 88.76 89.13
Mean 94.37 90.69 89.83 89.07 89.68
Lingua:
Inglese
Frequenza di pubblicazione:
6 volte all'anno
Argomenti della rivista:
Ingegneria, Elettrotecnica, Ingegneria dell'automazione, metrologia e collaudo
Feed RSS della rivista