DOI QR코드

DOI QR Code

전이학습을 이용한 볼베어링의 진동진단

Transfer Learning-Based Vibration Fault Diagnosis for Ball Bearing

  • 투고 : 2023.04.15
  • 심사 : 2023.05.05
  • 발행 : 2023.05.31

초록

본 논문에서는 전이학습을 이용하여 볼베어링의 진동진단을 수행하는 방법을 제안한다. 고장을 진단하기 위해 진동신호를 시간-주파수로 분석할 수 있는 STFT을 CNN의 입력으로 이용하였다. CNN 기반의 딥러닝 인공신경망을 빠르게 학습하고 진단 성능을 높이기 위해 전이학습 기반의 딥러닝 학습 기법을 제안하였다. 전이학습은 VGG 기반의 영상 분류 모델을 이용하여 특징 추출기와 분류기를 선택적으로 학습하였고, 학습에 사용한 데이터 세트는 Case Western Reserve University 대학에서 제공하는 공개된 볼베어링 진동 데이터를 사용하였으며, 성능평가는 기존의 CNN 모델과 비교하는 방법으로 수행하였다. 실험 결과 전이학습이 볼베어링 진동 데이터에서 상태 진단에 유용하다는 것을 증명할 수 있을 뿐만 아니라 이를 통해 다른 산업에서도 전이학습을 사용하여 상태 진단을 개선할 수 있다.

In this paper, we propose a method for diagnosing ball bearing vibration using transfer learning. STFT, which can analyze vibration signals in time-frequency, was used as input to CNN to diagnose failures. In order to rapidly learn CNN-based deep artificial neural networks and improve diagnostic performance, we proposed a transfer learning-based deep learning learning technique. For transfer learning, the feature extractor and classifier were selectively learned using a VGG-based image classification model, the data set for learning was publicly available ball bearing vibration data provided by Case Western Reserve University, and performance was evaluated by comparing the proposed method with the existing CNN model. Experimental results not only prove that transfer learning is useful for condition diagnosis in ball bearing vibration data, but also allow other industries to use transfer learning to improve condition diagnosis.

키워드

참고문헌

  1. J. P. Yun, M. S. Kim, G. K, W. Shin, "Fault Diagnosis and Analysis Based on Transfer Learning and Vibration Signals", Journal of Korean Embedded Engineering Society, vol.14, no.6, pp. 287-294 (8 pages), 2019. https://doi.org/10.14372/IEMEK.2019.14.6.287
  2. Naver blog, STFT, https://m.blog.naver.com/vmvtech/220936084562
  3. Wikipedia, Convolutional Neural Network, https://ko.wikipedia.org/wiki/%ED%95%A9%EC%84%B1%EA%B3%B1_%EC%8B%A0%EA%B2%BD%EB%A7%9D
  4. Y. J. Kim, H. J. Jeon, Y. K. Kim, "A Comparison Study of Ball Bearing Fault Diagnosis and Classification Analysis Using XAI Grad-CAM", The Transactions of the Korean Institute of Electrical Engineers, Vol. 71, No. 9, p.1315-1325, 2022. DOI https://doi.org/10.5370/KIEE.2022.71.9.1315
  5. G. J. Seong, T. M. Lee, J. W. Kim, D. W. Kim, "A Study on CNN-Based Ball Bearings Fault Detection of a Rotating Shaft Using abnormal vibration emphasis Filter Bank", Proceedings of the conference of the Korean Society for Communications and Communications, pp. 414 -415 (2pages), 2023.
  6. Naver blog, Transfer Learning,https://blog.naver.om/PostView.naver?blogId=beyondlegend&logNo=222521774448&parentCategoryNo=&categoryNo=93&viewDate=&isShowPopularPosts=true&from=search
  7. Karen Simonyan, Andrew Zisserman, "Very Deep Convolutional Networks for Large-Scale Image Recognition", arXiv preprint arXiv:1409.1556, 2015.
  8. CWRU, "48k Drive End Bearing Fault Data,"Jan 2022, https://engineering.case.edu/
  9. D. T. Hoang, H. J. Kang, "Rolling element bearing fault diagnosis using convolutional neural network and vibration image", Cogn. Syst. Res., Vol. 53, pp. 42-50, 2019. DOI https://doi.org/10.1016/j.cogsys.2018.03.002