본문 바로가기
KERD
논문KCI 등재

MFCCs를 이용한 입력 변환과 CNN 학습에 기반한운영 환경 변화에 강건한 베어링 결함 진단 방법

An Input Transformation with MFCCs and CNN Learning Based Robust Bearing Fault Diagnosis Method for Various Working Conditions

서양진
한국정보처리학회|2022.04|정보처리학회 논문지 (The Transactions of the Korea Information Processing Society)|제11권 제4호|pp. 179-188

0

조회

0

다운로드

1

인용

0

참고문헌

키워드

딥러닝Deep LearningCNN베어링 결함 진단분포 차이MFCCsBearing Fault DiagnosisDistribution Difference
주제분류컴퓨터학

초록

기계의 주요 부품인 베어링 결함 진단에 딥러닝을 활용하는 연구가 활발하게 진행되어 좋은 성능을 달성하였으나, 학습 데이터와 테스트 데이터의운영 환경 차이로 인해 기계가 실제로 가동되는 환경에서는 성능 저하가 발생하는 문제가 있다. 학습 데이터와 테스트 데이터의 분포 차이 문제를다루는 방법으로 데이터 적응이 제안되어 좋은 결과를 보여주고 있으나, 각 방법이 가정하고 있는 특정 적용 시나리오를 벗어나기 어렵다는 제약이있다. 이에 본 연구는 MFCCs를 이용한 입력 데이터의 변환과 간단한 CNN 구조를 이용해 원시 도메인 데이터로부터 생성된 모델에 대해 추가적인학습이나 조정 없이 타겟 도메인 데이터에 대한 테스트를 강건하게 수행하는 방법을 제안하였으며, 대표적인 베어링 결함 진단 데이터셋인 CWRU베어링 데이터를 이용해 제안한 방법에 대한 실험 및 분석을 수행하였다. 실험 결과 전이 학습 기반의 방법들과 대등한 성능을 보였으며, 입력변환 기반의 베이스라인 방법보다는 최소 15% 정도의 높은 성능을 달성하였다.

Abstract

There have been many successful researches on a bearing fault diagnosis based on Deep Learning, but there is still a critical issueof the data distribution difference between training data and test data from their different working conditions causing performancedegradation in applying those methods to the machines in the field. As a solution, a data adaptation method has been proposed andshowed a good result, but each and every approach is strictly limited to a specific applying scenario or presupposition, which makesit still difficult to be used as a real-world application. Therefore, in this study, we have proposed a method that, using a data transformationwith MFCCs and a simple CNN architecture, can perform a robust diagnosis on a target domain data without an additional learningor tuning on the model generated from a source domain data and conducted an experiment and analysis on the proposed method withthe CWRU bearing dataset, which is one of the representative datasests for bearing fault diagnosis. The experimental results showedthat our method achieved an equal performance to those of transfer learning based methods and a better performance by at least 15%compared to that of an input transformation based baseline method.

참고문헌 (44)

  1. H. Qiu, "Robust performance degradation assessment methods for enhanced rolling element bearing prognostics", Advanced Engineering Informatics, 17(3-4), pp.127~140 (2003)
  2. S. Nandi, "Condition monitoring and fault diagnosis of electrical motors—A review", IEEE Transactions on Energy Conversion, 20(4), pp.719~729 (2005)
  3. F. Camci, "Feature evaluation for effective bearing prognostics", Quality and Reliability Engineering International, 29(4), pp.477~486 (2013)
  4. M. Lebold, "Review of vibration analysis methods for gearbox diagnostics and prognostics", Proceedings of the 54th Meeting of the Society for Machinery Failure Prevention Technology, pp.623~634 (2000)
  5. P. Wang, "Fault prognostics using dynamic wavelet neural networks", AI EDAM, 15(4), pp.349~365 (2001)
  6. R. Yan, "Wavelets for fault diagnosis of rotary machines : A review with applications", Signal Processing, 96, pp.1~15 (2014)
  7. D. An, "Practical options for selecting data-driven or physics-based prognostics algorithms with reviews", Reliability Engineering & System Safety, 133, pp.223~236 (2015)
  8. A. Cubillo, "A review of physics-based models in prognostics : Application to gears and bearings of rotating machinery", Advances in Mechanical Engineering, 8(8), pp.1~21 (2016)
  9. J. Lee, "Prognostics and health management design for rotary machinery systems—Reviews, methodology and applications", Mechanical Systems and Signal Processing, 42(1-2), pp.314~334 (2014)
  10. K. L. Tsui, "Prognostics and health management: A review on data driven approaches" (2015), Mathematical Problems in Engineering
  11. D. Wang, "Prognostics and health management : A review of vibration based bearing and gear health indicators", IEEE Access, 6, pp.665~676 (2017)
  12. Y. Lei, "An intelligent fault diagnosis method using unsupervised feature learning towards mechanical big data", IEEE Transactions on Industrial Electronics, 63(5), pp.3137~3147 (2016)
  13. L. Jing, "A convolutional neural network based feature learning and fault diagnosis method for the condition monitoring of gearbox", Measurement, 111, pp.1~10 (2017)
  14. A. Zhang, "Limited data rolling bearing fault diagnosis with few-shot learning", IEEE Access, 7, pp.110895~110904 (2019)
  15. W. Zhang, "A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals", Sensors, 17(2), pp.425~445 (2017)
  16. L. I. Xueyi, "Semi-supervised gear fault diagnosis using raw vibration signal based on deep learning", Chinese Journal of Aeronautics, 33(2), pp.418~426 (2020)
  17. H. Li, "Raw vibration signal pattern recognition with automatic hyper-parameteroptimized convolutional neural network for bearing fault diagnosis", Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 234(1), pp.343~360 (2020)
  18. G. Jin, "An adaptive anti-noise neural network for bearing fault diagnosis under noise and varying load conditions", IEEE Access, 8, pp.74793~74807 (2020)
  19. I. Goodfellow, "Deep learning" (2016), MIT press
  20. R. Zhang, "Transfer learning with neural networks for bearing fault diagnosis in changing working conditions", IEEE Access, 5, pp.14347~14357 (2017)
  21. B. Zhang, "Intelligent fault diagnosis under varying working conditions based on domain adaptive convolutional neural networks", IEEE Access, 6, pp.66367~66384 (2018)
  22. X. Li, "Multi-layer domain adaptation method for rolling bearing fault diagnosis", Signal Processing, 157, pp.180~197 (2019)
  23. X. Wang, "Triplet loss guided adversarial domain adaptation for bearing fault diagnosis", Sensors, 20(1), pp.320~338 (2020)
  24. J. He, "Deep transfer learning method based on 1D-CNN for bearing fault diagnosis", Shock and Vibration (2021)
  25. W. Zhang, "Bearings fault diagnosis based on convolutional neural networks with 2-D representation of vibration signals as input", Proceedings of the 3rd International Conference on Mechatronics and Mechanical Engineering, pp.13001~13005 (2016)
  26. M. J. Hasan, "Bearing fault diagnosis under variable rotational speeds using stockwell transform-based vibration imaging and transfer learning", Applied Sciences, 8(12), pp.2357~2071 (2018)
  27. Y. Du, "Fault diagnosis under variable working conditions based on STFT and transfer deep residual network", Shock and Vibration (2020)
  28. S. Lee, "A study on deep learning application of vibration data and visualization of defects for predictive maintenance of gravity acceleration equipment", Applied Sciences, 11(4), pp.1564~1578 (2021)
  29. U. E. Akpudo, "A cost-efficient MFCC-based fault detection and isolation technology for electromagnetic pumps", Electronics, 10(4), pp.439~458 (2021)
  30. Z. G. Cheng, "A vibration recognition method based on deep learning and signal processing", Engineering Mechanics, 38(4), pp.230~246 (2021)
  31. A. Lerch, "An introduction to audio content analysis:Applications in signal processing and music informatics" (2012), Wiley-IEEE Press
  32. "Librosa"[URL]
  33. F. Zheng, "Comparison of different implementations of MFCC", Journal of Computer Science and Technology, 16(6), pp.582~589 (2001)
  34. S. Gupta, "Feature extraction using MFCC", Signal & Image Processing : An International Journal, 4(4), pp.101~108 (2013)
  35. S. Tang, "Data preprocessing techniques in convolutional neural network based on fault diagnosis towards rotating machinery", IEEE Access, 8, pp.149487~149496 (2020)
  36. S. Zhang, "Deep learning algorithms for bearing fault diagnostics : A comprehensive review", IEEE Access, 8, pp.29857~29881 (2020)
  37. K. O'Shea, "An introduction to convolutional neural networks", arXiv preprint arXiv : 1511. 08458, ~ (2015)
  38. S. Albawi, "Understanding of a convolutional neural network", International Conference on Engineering and Technology, pp.1~6 (2017)
  39. J. Jiao, "A comprehensive review on convolutional neural network in machine fault diagnosis", Neurocomputing, 417, pp.36~63 (2020)
  40. "Case Western Reserve University (CWRU) Bearing Data Center"[URL]
  41. D. Neupane, "Bearing fault detection and diagnosis using case western reserve university dataset with deep learning approaches : A review", IEEE Access, 8, pp.93155~93178 (2020)
  42. X. Ding, "Repvgg : Making vgg-style convnets great again", Proceedings of the IEEE, 2021, 13733~13742
  43. L. Alzubaidi, "Review of deep learning : Concepts, CNN architectures, challenges, applications, future directions", Journal of Big Data, 8(1), pp.1~74 (2021)
  44. S. A. Alim, "From Natural to Artificial Intelligence", pp.2~119 (2018), IntechOpen

관련 논문AI추천

CNN 기반 딥러닝을 이용한 베어링 고장 진단의 정확도 및 계산 복잡도 분석김철홍, 박재현한국차세대컴퓨팅학회 · 한국차세대컴퓨팅학회 논문지2022 · 제18권 제1호딥러닝 기반 기계음 분석을 통한 환경 소음에 강건한 베어링 샤프트 시스템의 실시간 고장 감지백수정, 오수정, 이건창, 이민희한국산업경영시스템학회 · 한국산업경영시스템학회지2024 · 제47권 제4호스펙트로그램 이미지를 이용한 CNN 기반 자동화 기계 고장 진단 기법강경원, 이경민한국융합신호처리학회 · 융합신호처리학회 논문지2020 · 제21권 제3호전이 학습과 진동 신호를 이용한 설비 고장 진단 및 분석구교권, 김민수, 신우상, 윤종필대한임베디드공학회 · 대한임베디드공학회논문지2019 · 제14권 제6호Scalogram과 Switchable 정규화 기반 합성곱 신경망을 활용한 베이링 결함 탐지김윤수, 석종원, 미아그마르 델레그마한국전기전자학회 · 전기전자학회논문지2022 · 제26권 제2호시계열 데이터에 대한 전이 학습 기반 이상 탐지 방법 연구김재훈, 박철순한국산업경영시스템학회 · 한국산업경영시스템학회지2025 · 제48권 제4호

이 간행물의 다른 논문 (4건)

CoAID+: 소셜 컨텍스트 기반 가짜뉴스 탐지를 위한COVID-19 뉴스 파급 데이터안지원, 박희진, 강윤석, 김상욱, 오성수, 김유심, 한소은, 고윤용pp. 149-156데이터베이스에서 유사도 질의 처리 비용 감소 방법박지수, 손진곤, 김선경pp. 157-162에지 기반 포그 컴퓨팅 환경에서 이동성 지원을 위한라이브 마이그레이션 기반 자원 관리 기법임종범pp. 163-168BERT-Fused Transformer 모델에 기반한한국어 형태소 분석 기법이창재, 나동열pp. 169-178
원문 보기