Smart Structures and Systems

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Normal data based rotating machine anomaly detection using CNN with self-labeling

  • Bae, Jaewoong (Department of Mechanical Engineering, Korean Advanced Institute for Science and Technology) ;
  • Jung, Wonho (Department of Mechanical Engineering, Korean Advanced Institute for Science and Technology) ;
  • Park, Yong-Hwa (Department of Mechanical Engineering, Korean Advanced Institute for Science and Technology)
  • Received : 2021.10.31
  • Accepted : 2022.04.26
  • Published : 2022.06.25
⟨ Previous Next ⟩

Abstract

To train deep learning algorithms, a sufficient number of data are required. However, in most engineering systems, the acquisition of fault data is difficult or sometimes not feasible, while normal data are secured. The dearth of data is one of the major challenges to developing deep learning models, and fault diagnosis in particular cannot be made in the absence of fault data. With this context, this paper proposes an anomaly detection methodology for rotating machines using only normal data with self-labeling. Since only normal data are used for anomaly detection, a self-labeling method is used to generate a new labeled dataset. The overall procedure includes the following three steps: (1) transformation of normal data to self-labeled data based on a pretext task, (2) training the convolutional neural networks (CNN), and (3) anomaly detection using defined anomaly score based on the softmax output of the trained CNN. The softmax value of the abnormal sample shows different behavior from the normal softmax values. To verify the proposed method, four case studies were conducted, on the Case Western Reserve University (CWRU) bearing dataset, IEEE PHM 2012 data challenge dataset, PHMAP 2021 data challenge dataset, and laboratory bearing testbed; and the results were compared to those of existing machine learning and deep learning methods. The results showed that the proposed algorithm could detect faults in the bearing testbed and compressor with over 99.7% accuracy. In particular, it was possible to detect not only bearing faults but also structural faults such as unbalance and belt looseness with very high accuracy. Compared with the existing GAN, the autoencoder-based anomaly detection algorithm, the proposed method showed high anomaly detection performance.

Keywords

Acknowledgement

This research was supported by UNDERGROUND CITY OF THE FUTURE program funded by the Ministry of Science and ICT.

References

  1. Akcay, S., Atapour-Abarghouei, A. and Breckon, T.P. (2019), "GANomaly: Semi-supervised anomaly detection via adversarial training", Asian Conference Computer Vision 2018, Perth Western, Australia, December.
  2. Amar, M., Gondal, I. and Wilson, C. (2015), "Vibration spectrum imaging: A novel bearing fault classification approach", IEEE Trans. Ind. Electron., 62(1), 494-502. https://doi.org/10.1109/TIE.2014.2327555.
  3. Breunig, M.M., Kriegel, H.P., Ng, R.T. and Sander, J. (2000), "LOF: Identifying density-based local outliers", Proceedings of the 2000 ACM Sigmod International Conference on Management of Data, Dallas, USA, May.
  4. Case Western Reserve University Bearing Data Center (2022), Case Western Reserve University, Cleveland, USA. https://engineering.case.edu/bearingdatacenter.
  5. Choi, S., Akin, B., Rahimian, M.M. and Toliyat, H.A. (2012), "Performance-oriented electric motors diagnostics in modern energy conversion systems", IEEE Trans. Ind. Electron., 59(2), 1266-1277. https://doi.org/10.1109/TIE.2011.2158037.
  6. da Silva, A.M., Povinelli, R.J. and Demerdash, N.A.O. (2008), "Induction machine broken bar and stator short-circuit fault diagnostics based on three-phase stator current envelopes", IEEE Trans. Ind. Electron., 55(3), 1310-1318. https://doi.org/10.1109/TIE.2007.909060.
  7. Dai, X. and Gao, Z. (2013), "From model, signal to knowledge: A data-driven perspective of fault detection and diagnosis", IEEE Trans. Ind. Inform., 9(4), 2226-2238. https://doi.org/10.1109/TII.2013.2243743.
  8. Data challenge on PHMAP 2021 (2021), Asian Pacific Conference of the Prognostics and Health Management Society 2021, Seoul, Korea. http://phmap.org/data-challenge.
  9. Girshick, R., Donahue, J., Darrell, T. and Malik, J. (2014), "Rich feature hierarchies for accurate object detection and semantic segmentation", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, USA, June.
  10. Golan, I. and El-Yaniv, R. (2018), "Deep anomaly detection using geometric transformations", Proceeding of NeurIPS 2018, Montreal, Canada, December.
  11. Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A. and Bengio, Y. (2014), "Generative adversarial networks", Proceeding of NeurIPS 2014, Montreal, Canada, December.
  12. Guo, L., Chen, J. and Li, X. (2009), "Rolling bearing fault classification based on envelope spectrum and support vector machine", J. Vib. Control, 15(9), 1349-1363. https://doi.org/10.1177/1077546308095224.
  13. Hoang, D.T. and Kang, H.J. (2019), "Rolling element bearing fault diagnosis using convolutional neural network and vibration image", Cognit. Syst. Res., 53, 42-50. https://doi.org/10.1016/j.cogsys.2018.03.002.
  14. Isermann, R. (1984), "Process fault detection based on modeling and estimation methods-A survey", Automatica, 20(4), 387-404. https://doi.org/10.1016/0005-1098(84)90098-0.
  15. Jia, F., Lei, Y., Lu, N. and Xing, S. (2018), "Deep normalized convolutional neural network for imbalanced fault classification of machinery and its understanding via visualization", Mech. Syst. Signal Pr., 110, 349-367. https://doi.org/10.1016/j.ymssp.2018.03.025.
  16. Jiang, W., Hong, Y., Zhou, B., He, X. and Cheng, C. (2019), "A GAN-based anomaly detection approach for imbalanced industrial time series", IEEE Access, 7, 143608-143619. https://doi.org/10.1109/ACCESS.2019.2944689.
  17. Jing, L. and Tian, Y. (2020), "Self-supervised visual feature learning with deep neural networks: A survey", IEEE Trans. Pattern Anal. Mach. Intell., 43(11), 4037-4058. https://doi.org/10.1109/tpami.2020.2992393.
  18. Krizhevsky, A., Sutskever, I. and Hinton, G.E. (2012), "ImageNet classification with deep convolutional neural networks", Proceeding of NeurIPS 2012, Tahoe, USA, December.
  19. LeCun, Y., Bottou, L., Bengio, Y. and Haffner, P. (1998), "Gradient-based learning applied to document recognition", Proc. IEEE, 86(11), 2278-2323. https://doi.org/10.1109/5.726791.
  20. Meng, Z., Guo, X., Pan, Z., Sun, D. and Liu, S. (2019), "Data segmentation and augmentation methods based on raw data using deep neural networks approach for rotating machinery fault diagnosis", IEEE Access, 7, 79510-79522. https://doi.org/10.1109/ACCESS.2019.2923417.
  21. Nectoux, P., Gouriveau, R., Medjaher, K., Ramasso, E., Chebel-morello, B., Zerhouni, N., Varnier, C., Nectoux, P., Gouriveau, R., Medjaher, K., Ramasso, E., Chebel-morello, B., Nectoux, P., Gouriveau, R., Medjaher, K., Ramasso, E., Morello, B., Zerhouni, N. and Varnier, C. (2012), "PRONOSTIA : An experimental platform for bearings accelerated degradation tests", Proc. IEEE Int. Conf. Prog. Health Manage., Denver, USA, June.
  22. Noroozi, M. and Favaro, P. (2016), "Unsupervised learning of visual representations by solving jigsaw puzzles", Proceeding of European Conference on Computer Vision, Amsterdam, Netherlands, October.
  23. Oh, H., Jung, J.H., Jeon, B.C. and Youn, B.D. (2018), "Scalable and unsupervised feature engineering using vibration-imaging and deep learning for rotor system diagnosis", IEEE Trans. Ind. Electron., 65(4), 3539-3549. https://doi.org/10.1109/TIE.2017.2752151.
  24. Randall, R.B. (2010), Vibration-based Condition Monitoring, John Wiley & Sons, Ltd , West Sussex, UK.
  25. Ren, S., He, K., Girshick, R. and Sun, J. (2017), "Faster R-CNN: Towards real-time object detection with region proposal networks", Proceeding of NeurIPS 2014, Montreal, Canada, December.
  26. Ruff, L., Vandermeulen, R.A., Gornitz, N., Deecke, L., Siddiqui, S.A., Binder, A., Muller, E. and Kloft, M. (2018), "Deep one-class classification", Proceedings of the 35th International Conference on Machine Learning, Stockholm, Sweden, July.
  27. Schlegl, T., Seebock, P., Waldstein, S.M., Schmidt-Erfurth, U. abd Langs, G. (2017), "Unsupervised anomaly detection with generative adversarial networks to guide marker discovery", arXiv preprint arXiv:1703.05921.
  28. Scholkopf, B., Platt, J.C., Shawe-Taylor, J., Smola, A.J. and Williamson, R.C. (2001), "Estimating the support of a high-dimensional distribution", Neur. Comput., 13, 1443-1471. https://doi.org/10.1162/089976601750264965.
  29. Shelhamer, E., Long, J. and Darrell, T. (2017), "Fully convolutional networks for semantic segmentation", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, USA, June.
  30. Srividya, A., Verma, A.K. and Sreejith, B. (2009), "Automated diagnosis of rolling element bearing defects using time-domain features and neural networks", Int. J. Min., Reclam. Environ., 23(3), 206-215. https://doi.org/10.1080/17480930902916437.
  31. Sutrisno, E., Oh, H., Vasan, A.S.S. and Pecht, M. (2012), "Estimation of remaining useful life of ball bearings using data driven methodologies", 2012 IEEE Conference on Prognostics and Health Management, June.
  32. Tao, S., Zhang, T., Yang, J., Wang, X. and Lu, W. (2015), "Bearing fault diagnosis method based on stacked autoencoder and softmax regression", 2015 34th Chinese Control Conference, 6331-6335. https://doi.org/10.1109/ChiCC.2015.7260634.
  33. Tian, J., Azarian, M.H. and Pecht, M. (2015), "Rolling element bearing fault detection using density-based clustering", 2014 International Conference on Prognostics and Health Management, June.
  34. Wang, H., Li, S., Song, L. and Cui, L. (2019), "A novel convolutional neural network based fault recognition method via image fusion of multi-vibration-signals", Comput. Indus., 105, 182-190. https://doi.org/10.1016/j.compind.2018.12.013.
  35. Yin, S., Ding, S.X., Xie, X. and Luo, H. (2014), "A review on basic data-driven approaches for industrial process monitoring", IEEE Trans. Ind. Electron., 61(11), 6418-6428. https://doi.org/10.1109/TIE.2014.2301773.
  36. Yoo, Y. and Baek, J.G. (2018), "A novel image feature for the remaining useful lifetime prediction of bearings based on continuous wavelet transform and convolutional neural network", Appl. Sci., 8(7), 1102. https://doi.org/10.3390/app8071102.
  37. Zeiler, M.D. and Fergus, R. (2014), "Visualizing and understanding convolutional networks", Proceeding of European Conference on Computer Vision, Zurich, Switzerland, September.
  38. Zhang, R., Isola, P. and Efros, A.A. (2016), "Colorful Image Colorization", Proceeding of European Conference on Computer Vision, Amsterdam, Netherlands, October.