Abstract
Many cross-domain bearings fault diagnosis approaches have been developed by researchers. However, how to reduce the shift of training and test data remains a big challenge. To this end, a new deep dynamic adaptation network (DDAN) is developed for fault diagnosis. DDAN simultaneously takes advantage of stacked sparse autoencoder (SSAE), correlation alignment (CORAL), dynamic distribution adaptation (DDA) and domain-invariant classifier. Firstly, multiple domain feature extraction approach is developed to extract diverse features from raw signal, and then an unsupervised SSAE network as feature extractor to extract deep features from diverse original features. Secondly, CORAL reduces shift via matching the second-order statistics of training and test data. Finally, DDAN exploits the principles of structural risk minimization and DDA to learn an adaptive domain-invariant classifier for fault transfer diagnosis. Paderborn University (PU) and Case Western Reserve University (CWRU) bearing datasets were used to verify performance of the DDAN network. Comparing the performances with the best deep adaptation network (DAN), the average accuracy of DDAN is improved by 2.11%, and the SD is decreased by 1.76% on CWRU bearings dataset. Comparing the performances with best deep CORAL network, the average accuracy of DDAN is increased by 1.74%, and the SD is decreased by 2.31% on PU bearings dataset. The experimental results reveal that DDAN network can accurately diagnose fault type and effectively eliminate distribution divergence.
Similar content being viewed by others
Abbreviations
- DDAN:
-
Deep dynamic adaptation network
- SSAE:
-
Stacked sparse autoencoder
- DDA:
-
Dynamic distribution adaptation
- CORAL:
-
Correlation alignment
- SRM:
-
Structural risk minimization
- MDA:
-
Marginal distribution adaptation
- CDA:
-
Conditional distribution adaptation
- MMD:
-
Maximum mean discrepancy
- R(f):
-
Regularization term
- \(\mathop {|| \cdot ||}\nolimits_{F}^{2}\) :
-
Frobenius norm
- Sim(⋅):
-
Cosine distance
- MDFE:
-
Multiple domain feature extraction
- D s/D t :
-
Source data/Target data
- C s :
-
Covariance matrix of source data
- C t :
-
Covariance matrix of target data
- f :
-
Classifier
- µ :
-
Adaptive factor
- M :
-
MMD distance matrix
- L :
-
Laplacian matrix
- B :
-
Linear transformation matrix
- K :
-
Kernel matrix
- tr(⋅):
-
Trace operation of matrix
- W :
-
Pair-wise affinity matrix
- D ii :
-
Diagonal matrix
References
El-Thalji I, Jantunen E (2015) A summary of fault modelling and predictive health monitoring of rolling element bearings. Mech Syst Signal Process 60–61:252–272
Miao Y et al (2022) A review on the application of blind deconvolution in machinery fault diagnosis. Mech Syst Signal Process 163:108202
Dong SJ, He K, Tang BP (2020) The fault diagnosis method of rolling bearing under variable working conditions based on deep transfer learning. J Brazil Soc Mech Sci Eng. https://doi.org/10.1007/s40430-020-02661-3
Xu H et al (2022) A novel joint distinct subspace learning and dynamic distribution adaptation method for fault transfer diagnosis. Measurement 203:111986
Jin XH et al (2014) Motor bearing fault diagnosis using trace ratio linear discriminant analysis. IEEE Trans Industr Electron 61(5):2441–2451
Cococcioni M, Lazzerini B, Volpi SL (2013) Robust diagnosis of rolling element bearings based on classification techniques. IEEE Trans Industr Inf 9(4):2256–2263
Zhang Z et al (2022) Bearing fault diagnosis via generalized logarithm sparse regularization. Mech Syst Signal Process 167:108576
Li R et al (2020) Rolling bearings fault diagnosis based on improved complete ensemble empirical mode decomposition with adaptive noise, nonlinear entropy, and ensemble SVM. Appl Sci-Basel 10(16):5542
Raj EFI, Balaji M (2021) Analysis and classification of faults in switched reluctance motors using deep learning neural networks. Arab J Sci Eng 46(2):1313–1332
Long J et al (2022) A novel self-training semi-supervised deep learning approach for machinery fault diagnosis. Int J Prod Res. https://doi.org/10.1080/00207543.2022.2032860
Wan LJ et al (2021) An efficient rolling bearing fault diagnosis method based on spark and improved random forest algorithm. Ieee Access 9:37866–37882
He C et al (2021) Rolling bearing fault diagnosis based on composite multiscale permutation entropy and reverse cognitive fruit fly optimization algorithm - Extreme learning machine. Measurement 173:108636
Xu L, Chatterton S, Pennacchi P (2021) Rolling element bearing diagnosis based on singular value decomposition and composite squared envelope spectrum. Mech Syst Signal Process 148:107174
Hou JB et al (2021) A novel rolling bearing fault diagnosis method based on adaptive feature selection and clustering. Ieee Access 9:99756–99767
Jiao WD et al (2021) Multi-scale sample entropy-based energy moment features applied to fault classification. Ieee Access 9:8444–8454
Cui ML et al (2021) Fault diagnosis of rolling bearings based on an improved stack autoencoder and support vector machine. IEEE Sens J 21(4):4927–4937
Zhao XL et al (2021) Multiple-order graphical deep extreme learning machine for unsupervised fault diagnosis of rolling bearing. Ieee Trans Instrum Meas 70:1–12
Niu GX et al (2021) An optimized adaptive PReLU-DBN for rolling element bearing fault diagnosis. Neurocomputing 445:26–34
Han T et al (2021) Rolling bearing fault diagnosis with combined convolutional neural networks and support vector machine. Measurement 177:109022
Xiong SC et al (2021) Fault diagnosis of a rolling bearing based on the wavelet packet transform and a deep residual network with lightweight multi-branch structure. Meas Sci Technol 32(8):085106
Zhao C et al (2021) Fault Diagnosis Method for Rolling Mill Multi Row Bearings Based on AMVMD-MC1DCNN under Unbalanced Dataset. Sensors 21(16):5494
Choudhary A, Mian T, Fatima S (2021) Convolutional neural network based bearing fault diagnosis of rotating machine using thermal images. Measurement 176:109196
Li X et al (2021) Rolling bearing fault diagnosis using optimal ensemble deep transfer network. Knowl-Based Syst 213:106695
Chen C et al. (2017) Topic Correlation Analysis for Bearing Fault Diagnosis Under Variable Operating Conditions. in 12th International Conference on Damage Assessment of Structures (DAMAS). Kyushu Inst Technol, Kitakyushu, JAPAN
Ma P et al (2020) A diagnosis framework based on domain adaptation for bearing fault diagnosis across diverse domains. ISA Trans 99:465–478
Xu Z et al (2020) A fault diagnosis method based on improved adaptive filtering and joint distribution adaptation. Ieee Access 8:159683–159695
Kang SQ et al (2020) Fault diagnosis method of rolling bearings under varying working conditions based on deep feature transfer. J Mech Sci Technol 34(11):4383–4391
Cao N et al (2020) Bearing State Recognition Method Based on Transfer Learning Under Different Working Conditions. Sensors 20(1):234
Yu Y et al (2020) A New transfer learning fault diagnosis method using TSC and JGSA under variable condition. Ieee Access 8:177287–177295
Zhang, J.Q., et al., An intelligent fault diagnosis method based on domain adaptation for rolling bearings under variable load conditions. Proceedings of the institution of mechanical engineers part c-journal of mechanical engineering science
Zhao K et al (2022) A novel transfer learning fault diagnosis method based on manifold embedded distribution alignment with a little labeled data. J Intell Manuf 33(1):151–165
Gong, B., et al. (2012) Geodesic flow kernel for unsupervised domain adaptation. In: 2012 IEEE conference on computer vision and pattern recognition. IEEE
Sun B J F, Saenko K. (2016) Return of frustratingly easy domain adaptation. In: Proceedings of the AAAI Conference on Artificial Intelligence
Baktashmotlagh M et al. (2013) Unsupervised domain adaptation by domain invariant projection. In: Proceedings of the IEEE international conference on computer vision
Chen Z, Gryllias K, Li W (2020) Intelligent fault diagnosis for rotary machinery using transferable convolutional neural network. IEEE Trans Industr Inf 16(1):339–349
Wang XM et al. (2019) Transferable Attention for Domain Adaptation. In: 33rd AAAI Conference on Artificial Intelligence/31st Innovative Applications of Artificial Intelligence Conference/9th AAAI Symposium on Educational Advances in Artificial Intelligence. Honolulu, HI
Pang S, Yang XY (2019) A cross-domain stacked denoising autoencoders for rotating machinery fault diagnosis under different working conditions. Ieee Access 7:77277–77292
Sun MD et al (2019) A sparse stacked denoising autoencoder with optimized transfer learning applied to the fault diagnosis of rolling bearings. Measurement 146:305–314
Che C et al (2019) Deep transfer learning for rolling bearing fault diagnosis under variable operating conditions. Adv Mech Eng 11(12):1687814019897212
Li X et al (2019) Multi-Layer domain adaptation method for rolling bearing fault diagnosis. Signal Process 157:180–197
Zhou K et al (2021) Domain adaptation-based deep feature learning method with a mixture of distance measures for bearing fault diagnosis. Meas Sci Technol 32(9):157–180
Qian Q et al (2021) A new deep transfer learning network based on convolutional auto-encoder for mechanical fault diagnosis. Measurement 178:109352
Abraham B, Nair MS (2018) Computer-aided classification of prostate cancer grade groups from MRI images using texture features and stacked sparse autoencoder. Comput Med Imaging Graph 69:60–68
Yang B, Duan K, Zhang T (2016) Removal of EOG artifacts from EEG using a cascade of sparse autoencoder and recursive least squares adaptive filter. Neurocomputing 214:1053–1060
Ben-David S et al. (2006) Analysis of representations for domain adaptation. Advances in neural information processing systems, 19
Wang J et al. (2018) Visual domain adaptation with manifold embedded distribution alignment. In: 26th ACM Multimedia Conference (MM). Seoul, South Korea
Vapnik VN, Vapnik V (1998) Statistical learning theory, vol 1. Wiley, New York
Belkin M, Niyogi P, Sindhwani V (2006) Manifold regularization: A geometric framework for learning from labeled and unlabeled examples. J Mach Learn Res 7(11):2400–2434
Boudiaf A et al (2016) A comparative study of various methods of bearing faults diagnosis using the case Western Reserve University data. J Fail Anal Prev 16(2):271–284
Lessmeier C et al. (2016) Condition monitoring of bearing damage in electromechanical drive systems by using motor current signals of electric motors: a benchmark data set for data-driven classification. In: PHM Society European Conference
Dong S et al (2020) Rolling bearing performance degradation assessment based on improved convolutional neural network with anti-interference. Measurement 151:107219
Richman JS, Moorman JR (2000) Physiological time-series analysis using approximate entropy and sample entropy. Am J Phys-Heart Circ Physiol 278(6):H2039–H2049
Chen L, Xu H (2020) Deep neural network for semi-automatic classification of term and preterm uterine recordings. Artif Intell Med 105:101861
van der Maaten L (2014) Accelerating t-SNE using Tree-Based Algorithms. J Mach Learn Res 15:3221–3245
Long M et al. (2015) Learning transferable features with deep adaptation networks. In: International conference on machine learning. PMLR
Sun B, Saenko K (2016) Deep coral: correlation alignment for deep domain adaptation. In: European conference on computer vision. Springer
Acknowledgements
This research was funded by Sichuan Science and Technology Program, grant number 2021YFS0065.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
No conflict of interest exits in the submission of this manuscript, and manuscript is approved by all authors for publication. We would like to declare on behalf of my co-authors that the work described was original research that has not been published previously, and not under consideration for publication elsewhere, in whole or in part. All the authors listed have approved the manuscript that is enclosed.
Additional information
Technical Editor: Jarir Mahfoud.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Xu, H., Liu, J., Peng, X. et al. Deep dynamic adaptation network: a deep transfer learning framework for rolling bearing fault diagnosis under variable working conditions. J Braz. Soc. Mech. Sci. Eng. 45, 41 (2023). https://doi.org/10.1007/s40430-022-03950-9
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s40430-022-03950-9