47 Bearing Fault Transfer Diagnosis Based on Acoustic Emission …
541
1. The difference of data samples distribution under different working conditions
is effectively eliminated by domain adaptation, and the labeled knowledge in
source domain is transferred to the without labeled target domain. The problem
of lack of labeled samples under variable working conditions is well solved.
2. Convolution neural network is used to extract sensitive features directly from
acoustic emission signal map, which makes feature extraction independent of
professional knowledge. In order to extract better features, one-dimensional
acoustic emission waveform is transformed into two-dimensional acoustic
emission map, which improves the performance of convolution neural network.
3. Finally, the feasibility and superiority of the proposed method was verified by lots
of bearing experiments, and the classification accuracy reached 88.40%, which
is much higher than the traditional methods.
Acknowledgements This research was supported by the Science and Technology Plan Projects of
State Administration for Market Regulation (2019MK131), China Special Equipment Inspection
& Research Institute (2019-Youth-10) and the National Key Research and Development Program
of China (2018YFF0214702).
References
1. P. Ma, H. Zhang, W. Fan, C. Wang, A diagnosis framework based on domain adaptation for
bearing fault diagnosis across diverse domains. ISA Trans. 359, 77–92 (2019)
2. K. Yu, T.R. Lin, J. Tan, H. Ma, An adaptive sensitive frequency band selection method for
empirical wavelet transform and its application in bearing fault diagnosis. Measurement 134,
375–384 (2019)
3. S. Lu, Q. He, J. Zhao, Bearing fault diagnosis of a permanent magnet synchronous motor via
a fast and online order analysis method in an embedded system. Mech. Syst. Signal Proc. 113,
36–49 (2018)
4. X. Zhang, Z. Liu, Q. Miao, L. Wang, Bearing fault diagnosis using a whale optimization
algorithm-optimized orthogonal matching pursuit with a combined time–frequency atom
dictionary. Mech. Syst. Signal Proc. 107, 29–42 (2018)
5. C. Zhao, Z. Feng, X. Wei, Y. Qin, Sparse classification based on dictionary learning for planet
bearing fault identification. Expert Syst. Appl. 108, 233–245 (2018)
6. T. Berredjem, M. Benidir, Bearing faults diagnosis using fuzzy expert system relying on an
improved range overlaps and similarity method. Expert Syst. Appl. 108, 134–142 (2018)
7. M.S. Hoseinzadeh, S.E. Khadem, M.S. Sadooghi, Quantitative diagnosis for bearing faults by
improving ensemble empirical mode decomposition. ISA Trans. 83, 261–275 (2018)
8. A. Khadersab, S. Shivakumar, Vibration analysis techniques for rotating machinery and its
effect on bearing faults. Procedia Manuf. 20, 247–252 (2018)
9. Y. Yang, W. Yang, D. Jiang, Simulation and experimental analysis of rolling element bearing
fault in rotor-bearing-casing system. Eng. Fail. Anal. 92, 205–221 (2018)
10. X. Li, W. Zhang, Q. Ding, J.-Q. Sun, Multi-layer domain adaptation method for rolling bearing
fault diagnosis. Signal Process. 157, 180–197 (2019)
11. W. Qian, S. Li, P. Yi, K. Zhang, A novel transfer learning method for robust fault diagnosis of
rotating machines under variable working conditions. Measurement 138, 514–525 (2019)
12. W. Zhang, C. Li, G. Peng, Y. Chen, Z. Zhang, A deep convolutional neural network with new
training methods for bearing fault diagnosis under noisy environment and different working
load. Mech. Syst. Signal Proc. 100, 439–453 (2018)
541
1. The difference of data samples distribution under different working conditions
is effectively eliminated by domain adaptation, and the labeled knowledge in
source domain is transferred to the without labeled target domain. The problem
of lack of labeled samples under variable working conditions is well solved.
2. Convolution neural network is used to extract sensitive features directly from
acoustic emission signal map, which makes feature extraction independent of
professional knowledge. In order to extract better features, one-dimensional
acoustic emission waveform is transformed into two-dimensional acoustic
emission map, which improves the performance of convolution neural network.
3. Finally, the feasibility and superiority of the proposed method was verified by lots
of bearing experiments, and the classification accuracy reached 88.40%, which
is much higher than the traditional methods.
Acknowledgements This research was supported by the Science and Technology Plan Projects of
State Administration for Market Regulation (2019MK131), China Special Equipment Inspection
& Research Institute (2019-Youth-10) and the National Key Research and Development Program
of China (2018YFF0214702).
References
1. P. Ma, H. Zhang, W. Fan, C. Wang, A diagnosis framework based on domain adaptation for
bearing fault diagnosis across diverse domains. ISA Trans. 359, 77–92 (2019)
2. K. Yu, T.R. Lin, J. Tan, H. Ma, An adaptive sensitive frequency band selection method for
empirical wavelet transform and its application in bearing fault diagnosis. Measurement 134,
375–384 (2019)
3. S. Lu, Q. He, J. Zhao, Bearing fault diagnosis of a permanent magnet synchronous motor via
a fast and online order analysis method in an embedded system. Mech. Syst. Signal Proc. 113,
36–49 (2018)
4. X. Zhang, Z. Liu, Q. Miao, L. Wang, Bearing fault diagnosis using a whale optimization
algorithm-optimized orthogonal matching pursuit with a combined time–frequency atom
dictionary. Mech. Syst. Signal Proc. 107, 29–42 (2018)
5. C. Zhao, Z. Feng, X. Wei, Y. Qin, Sparse classification based on dictionary learning for planet
bearing fault identification. Expert Syst. Appl. 108, 233–245 (2018)
6. T. Berredjem, M. Benidir, Bearing faults diagnosis using fuzzy expert system relying on an
improved range overlaps and similarity method. Expert Syst. Appl. 108, 134–142 (2018)
7. M.S. Hoseinzadeh, S.E. Khadem, M.S. Sadooghi, Quantitative diagnosis for bearing faults by
improving ensemble empirical mode decomposition. ISA Trans. 83, 261–275 (2018)
8. A. Khadersab, S. Shivakumar, Vibration analysis techniques for rotating machinery and its
effect on bearing faults. Procedia Manuf. 20, 247–252 (2018)
9. Y. Yang, W. Yang, D. Jiang, Simulation and experimental analysis of rolling element bearing
fault in rotor-bearing-casing system. Eng. Fail. Anal. 92, 205–221 (2018)
10. X. Li, W. Zhang, Q. Ding, J.-Q. Sun, Multi-layer domain adaptation method for rolling bearing
fault diagnosis. Signal Process. 157, 180–197 (2019)
11. W. Qian, S. Li, P. Yi, K. Zhang, A novel transfer learning method for robust fault diagnosis of
rotating machines under variable working conditions. Measurement 138, 514–525 (2019)
12. W. Zhang, C. Li, G. Peng, Y. Chen, Z. Zhang, A deep convolutional neural network with new
training methods for bearing fault diagnosis under noisy environment and different working
load. Mech. Syst. Signal Proc. 100, 439–453 (2018)