Journal of the Korean Society of Marine Environment & Safety (해양환경안전학회지)

The Korean Society of Marine Environment and safety (해양환경안전학회)
권호 표지
DOI QR코드

DOI QR Code

Vibration Data Denoising and Performance Comparison Using Denoising Auto Encoder Method

Denoising Auto Encoder 기법을 활용한 진동 데이터 전처리 및 성능비교

  • Jang, Jun-gyo (Dept. of Ocean System Engineering, Gyeongsang Nat'l Univ.) ;
  • Noh, Chun-myoung (Dept. of Ocean System Engineering, Gyeongsang Nat'l Univ.) ;
  • Kim, Sung-soo (Adia Lab inc.) ;
  • Lee, Soon-sup (Dept. of Naval Architecture and Ocean Engineering, Gyeongsang Nat'l Univ.) ;
  • Lee, Jae-chul (Dept. of Naval Architecture and Ocean Engineering, Gyeongsang Nat'l Univ.)
  • 장준교 (경상대학교 해양시스템공학과) ;
  • 노천명 (경상대학교 해양시스템공학과) ;
  • 김성수 ((주)아디아랩) ;
  • 이순섭 (경상대학교 해양시스템공학과) ;
  • 이재철 (경상대학교 해양시스템공학과)
  • Received : 2021.11.08
  • Accepted : 2021.12.28
  • Published : 2021.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Vibration data of mechanical equipment inevitably have noise. This noise adversely af ects the maintenance of mechanical equipment. Accordingly, the performance of a learning model depends on how effectively the noise of the data is removed. In this study, the noise of the data was removed using the Denoising Auto Encoder (DAE) technique which does not include the characteristic extraction process in preprocessing time series data. In addition, the performance was compared with that of the Wavelet Transform, which is widely used for machine signal processing. The performance comparison was conducted by calculating the failure detection rate. For a more accurate comparison, a classification performance evaluation criterion, the F-1 Score, was calculated. Failure data were detected using the One-Class SVM technique. The performance comparison, revealed that the DAE technique performed better than the Wavelet Transform technique in terms of failure diagnosis and error rate.

기계 장비의 진동 데이터는 필연적으로 노이즈를 포함하고 있다. 이러한 노이즈는 기계 장비의 유지보수를 진행하는데 악영향을 끼친다. 그에 따라 데이터의 노이즈를 얼마나 효과적으로 제거해주냐에 따라 학습 모델의 성능을 좌우한다. 본 논문에서는 시계열 데이터를 전처리 함에 있어 특성추출 과정을 포함하지 않는 Denoising Auto Encoder 기법을 활용하여 데이터의 노이즈를 제거했다. 또한 기계 신호 처리에 널리 사용되는 Wavelet Transform과 성능 비교를 진행했다. 성능비교는 고장 탐지율을 계산하여 진행했으며 보다 정확한 비교를 위해 분류 성능 평가기준 중 하나인 F-1 Score를 계산하여 성능 비교를 진행했다. 고장을 탐지하는 과정에서는 One-Class SVM 기법을 활용하여 고장 데이터를 탐지했다. 성능 비교 결과 고장 진단율과 오차율 측면에서 Denoising Auto Encoder 기법이 Wavelet Transform 기법에 비해 보다 좋은 성능을 나타냈다.

Keywords

Acknowledgement

이 논문은 2021년도 산업통상자원부, 해양수산부 재원으로 한국산업기술진흥원(P0001968, 2021년 산업혁신인재성장 지원사업)과 해양수산과학기술진흥원(스마트 항만-자율운항 선박연계 기술개발)의 지원을 받아 수행된 연구임.

References

  1. Ahn, B. H., H. J. Kim, S. W. Park, Y. S. Kim, and H. K. Choi(2015), Study on Noise Reduction Method of Acoustic Emission Signal for Rotorcraft Gearboxes Condition Monitoring and Diagnosis, Journal of the Korean Society for Noise And Vibraion Engineering (KSNVE), pp. 359-363
  2. Cho, Y. J., Y. H. Ji, G. H. Nam, S. Y. Jeong, and H. C. Lee(2021), PCA-One Class SVM Based Anomaly Detection on TMED Hybrid Vehicle, The Korean Institute of Electrical Engineers, pp. 168-169.
  3. Hwang, B. Y., J. H. Jung, and J. M. Lee(2015), Advanced Sound Source Localization Study Using De-noising Filter based on the Discrete Wavelet Transform (DWT), Institute of Control, Robotics and Systems. Journal of Institute of Control, Robotics and Systems 21(12), pp. 1185-1192. https://doi.org/10.5302/J.ICROS.2015.15.0012
  4. Jang, J. Y., B. W. Min, and C. W. Kim(2016), Semiconductor process anomaly detection based on Denoising Autoencoder, Journal of the spring Academic Conference of Korean Institute Of Industrial Engineers, pp. 1928-1948.
  5. Jang, J. G. and J. C. Lee(2020), Performance Comparison of Data-Driven Prognostics Techniques by Predicting the Remaining Useful Life of Bearing, Journal of the 26th Winter Academic Conference of the Korean CDE Association, pp. 331-333.
  6. Jia, Y., G. Li, X. Dong, and K. He(2021), A novel denoising method for vibration signal of hob spindle based on EEMD and grey theory, Measurement, Vol. 169, 10S490.
  7. Jun, S. H.(2008), An Outlier Data Analysis using Support Vector Regression, Journal of Korean Institute of Intelligent Systems, 18(6), pp. 876-880. https://doi.org/10.5391/JKIIS.2008.18.6.876
  8. Kim, D. H., S. J. Han, B. K. Jung, S. H. Han, and S. B. Lee(2019), A Machine Learning-Based Method to Predict Engine Power, Journal of the Korean Society of Marine Environment & Safety, Vol. 25, No. 7, pp. 851-857. https://doi.org/10.7837/kosomes.2019.25.7.851
  9. Kim, K. M., D. Y. Kim, and J. H. Lee(2014), Measuring Similarity Between Movies Based on Polarity of Tweets, Journal of Korean Institute of Intelligent Systems, 24(3), pp. 292-297. https://doi.org/10.5391/JKIIS.2014.24.3.292
  10. Lee, J. E. and I. S. Kim(2011), A Study on the Fault Detection Technique of the Grid-Connected Photovoltaic System using Wavelet Transformation, The Transactions of Korean Institute of Power Electronics, 16(1), pp. 79-87. https://doi.org/10.6113/TKPE.2011.16.1.79
  11. Lee, J. H.(2021), Experimental Study on Application of an Anomaly Detection Algorithm in Electric Current Datasets Generated from Marine Air Compressor with Time-series Features, Journal of the Korean Society of Marine Environment & Safety, Vol. 27, No. 1, pp. 127-134. https://doi.org/10.7837/kosomes.2021.27.1.127
  12. Lee, J. H., S. Y. Yu, S. C. Sin, D. H. Kang, S. S. Lee, and J. C. Lee(2019), A Study on the Development of Failure Prediction Algorithm for Bearing Using Machine Learning Algorithm, The Korea Marine Engineering Association, 43(6), pp. 455-462.
  13. Lu, Q. and M. Li(2021), A Method Combining Fractal Analyss and Single Channel ICA for Vibration Noise Reduction, Hindawi Shock and Vibration, Volume 2021, Article ID 5583587, 10 pages.
  14. Raj, A. S. and N. Murali(2013), Morlet Wavelet UDWT Denoising and EMD based Bearing Fault Diagnosis. ELECTRONICS, Vol. 17, No. 1
  15. Tsui, K. L., N. Chen, Q. Zhou, Y. Hai, and W. Wang(2015), Prognostics and Health Management: A Review on Data Driven Approaches.
  16. Yang, B., B. Zheng, Y. Zhang, X. Zhu, D. Zhang, and Y. Jiang(2021), The Vibration Trend Prediction of Hydropower Units Based on Wavelet Threshold Denoising and Bidirectional Long Short-Term Memory Network, 2021 IEEE International Conference on Power Electronics, Computer Applications (ICPECA).
  17. Yoon, Y. J., and Y. J. Jung(2019), Detection of System Abnormal State by Cyber Attack. Journal of The Korea Institute of Information Security & Cryptology, Vol. 29, No. 5.