Bearing fault detection and diagnosis based on densely connected convolutional networks

• Autorzy: Niyongabo Julius , Zhang Yingjie , Ndikumagenge Jérémie

Identyfikatory

DOI

10.2478/ama-2022-0017

• Języki publikacji: EN

Abstrakty

EN

Rotating machines are widely used in today’s world. As these machines perform the biggest tasks in industries, faults are naturally observed on their components. For most rotating machines such as wind turbine, bearing is one of critical components. To reduce failure rate and increase working life of rotating machinery it is important to detect and diagnose early faults in this most vulner-able part. In the recent past, technologies based on computational intelligence, including machine learning (ML) and deep learning (DL), have been efficiently used for detection and diagnosis of bearing faults. However, DL algorithms are being increasingly favoured day by day because of their advantages of automatically extracting features from training data. Despite this, in DL, adding neural layers reduces the training accuracy and the vanishing gradient problem arises. DL algorithms based on convolutional neural networks (CNN) such as DenseNet have proved to be quite efficient in solving this kind of problem. In this paper, a transfer learning consisting of fine-tuning DenseNet-121 top layers is proposed to make this classifier more robust and efficient. Then, a new intelligent model inspired by DenseNet-121 is designed and used for detecting and diagnosing bearing faults. Continuous wavelet transform is applied to enhance the dataset. Experimental results obtained from analyses employing the Case Western Reserve University (CWRU) bearing dataset show that the proposed model has higher diagnostic performance, with 98% average accuracy and less complexity.

Słowa kluczowe

EN

bearing; deep learning; machine learning; transfer learning; fault detection; fault diagnosis; CWRU dataset

• Wydawca: Oficyna Wydawnicza Politechniki Białostockiej
• Czasopismo: Acta Mechanica et Automatica
• Rocznik: 2022
• Tom: Vol. 16, no. 2
• Strony: 130--135
• Opis fizyczny: Bibliogr. 26 poz., rys., tab., wykr.

Twórcy

autor

Niyongabo Julius

• Doctoral School, University of Burundi, UNESCO Road No 2, Bujumbura 1550, Burundi

• https://orcid.org/0000-0002-1429-9918

autor

Zhang Yingjie

• College of Computer Science and Electronic Engineering, Hunan University, Lushan Road (S), Changsha 410082, China

• https://orcid.org/0000-0002-4170-6152

autor

Ndikumagenge Jérémie

• Faculty of Engineering Science, Department of Information and Communication Technology, University of Burundi, UNESCO Road No 2, Bujumbura 1550, Burundi

• https://orcid.org/0000-0003-1094-0066

Bibliografia

• 1. Zhang S, Zhang S, Wang B, Habetler TG. Deep Learning Algorithms for Bearing Fault Diagnosticsx - A Comprehensive Review. IEEE Ac-cess. 2020;8:29857–81.
• 2. Zhang Z, Li H, Chen L, Han P. Shrinkage Networks. 2021;2021(Dl).
• 3. Neupane D, Seok J. Bearing fault detection and diagnosis using case western reserve university dataset with deep learning approaches: A review. IEEE Access. 2020;8:93155–78.
• 4. Li G, Tang G, Luo G, Wang H. Underdetermined blind separation of bearing faults in hyperplane space with variational mode decomposi-tion. Mech Syst Signal Process. 2019;120:83–97. https://doi.org/10.1016/j.ymssp.2018.10.016
• 5. Huang T, Fu S, Feng H, Kuang J. Bearing fault diagnosis based on shallow multi-scale convolutional neural network with attention. En-ergies. 2019;12(20).
• 6. Awadallah MA, Morcos MM. Application of AI tools in fault diagnosis of electrical machines and drives - An overview. IEEE Trans Energy Convers. 2003;18(2):245–51.
• 7. Batista L, Badri B, Sabourin R, Thomas M. A classifier fusion system for bearing fault diagnosis. Expert Syst Appl [Internet]. 2013;40(17):6788–97. http://dx.doi.org/10.1016/j.eswa.2013.06.033
• 8. Liu R, Yang B, Zio E, Chen X. Artificial intelligence for fault diagnosis of rotating machinery: A review. Mech Syst Signal Process. 2018;108:33–47. https://doi.org/10.1016/j.ymssp.2018.02.016
• 9. Bansal N, Sharma A, Singh RK. A Review on the Application of Deep Learning in Legal Domain. IFIP Adv Inf Commun Technol. 2019;559:374–81.
• 10. Zhao R, Yan R, Chen Z, Mao K, Wang P, Gao RX. Deep Learning and Its Applications to Machine Health Monitoring: A Survey. 2016;14(8):1–14. Available from: http://arxiv.org/abs/1612.07640
• 11. Brownlee J. What is Deep Learning? August 14, 2020 . Available from: https://machinelearningmastery.com/what-is-deep-learning/, October 15 2021.
• 12. Great Learning Team. Introduction to Resnet or Residual Network. Sep 28. 2020, Available online: https://www.mygreatlearning.com/blog/resnet/, October 15, 2021. 2021;2021.
• 13. Sahoo B. Fault Diagnosis using Deep Learning on raw time domain data. July 15 2020. Available on line: https://github.com/biswajitsahoo1111/cbm_codes_open/blob/master/notebooks/Deep_learning_based_fault_diagnosis_using_CNN_on_ raw_time _domain_data. 2021.
• 14. Chen Z, Cen J, Xiong J. Rolling Bearing Fault Diagnosis Using Time-Frequency Analysis and Deep Transfer Convolutional Neural Net-work. 2020;8.
• 15. Singhal G. Introduct ion to DenseNet with TensorFlow. May 6, 2020, Available online: https://www.pluralsight.com/guides/introduction- to-densenet-with-tensorflow, October 25, 2021.
• 16. Si L, Xiong X, Wang Z. Tan C. A Deep Convolutional Neural Network Model for Intelligent Discrimination between Coal and Rocks in Coal Mining Face. Math Probl Eng. 2020.
• 17. Guo X, Chen L, Shen C. Application To Bearing Fault Diagnosis. Measurement [Internet]. 2016; Available from: http://dx.doi.org/10.1016/j.measurement.2016.07.054
• 18. Janssens O, Slavkovikj V, Vervisch B, Stockman K, Loccufier M, Verstockt S, et al. Convolutional Neural Network Based Fault Detec-tion for Rotating Machinery. J Sound Vib. 2016;377:331–45.
• 19. Liu R, Meng G, Yang B, Sun C, Chen X. Dislocated Time Series Convolutional Neural Architecture: An Intelligent Fault Diagnosis Ap-proach for Electric Machine. IEEE Trans Ind Informatics. 2017;13(3):1310–20.
• 20. Lu C, Wang Z, Zhou B. Intelligent fault diagnosis of rolling bearing using hierarchical convolutional network based health state classifi-cation. Adv Eng Informatics. 2017;32:139–51.
• 21. Wang H, Xu J, Yan R, Sun C, Chen X. Intelligent bearing fault diag-nosis using multi-head attention-based CNN. Procedia Manuf. 2020;49:112–8. https://doi.org/10.1016/j.promfg.2020.07.005
• 22. Zilong Z, Wei Q. Intelligent fault diagnosis of rolling bearing using one-dimensional multi-scale deep convolutional neural network based health state classification. ICNSC 2018 - 15th IEEE Int Conf Networking, Sens Control. 2018;(April):1–6.
• 23. Li S, Liu G, Tang X, Lu J, Hu J. An ensemble deep convolutional neural network model with improved D-S evidence fusion for bearing fault diagnosis. Sensors (Switzerland). 2017;17(8).
• 24. Magar R, Ghule L, Li J, Zhao Y, Farimani AB. FaultNet: A Deep Convolutional Neural Network for Bearing Fault Classification. IEEE Access. 2021;9(October):25189–99.
• 25. Guo S, Yang T, Gao W, Zhang C, Zhang Y. An intelligent fault diag-nosis method for bearings with variable rotating speed based on py-thagorean spatial pyramid pooling CNN. Sensors (Switzerland). 2018;18(11).
• 26. Huang G, Liu Z, Van Der Maaten L, Weinberger KQ. Densely con-nected convolutional networks. Proc - 30th IEEE Conf Comput Vis Pattern Recognition. CVPR 2017. 2017:2261–9.