한국인터넷방송통신학회논문지 (The Journal of the Institute of Internet, Broadcasting and Communication)

  • 제18권2호
  • /
  • Pages.185-195
  • /
  • 2018
  • /
  • 2289-0238(pISSN)
  • /
  • 2289-0246(eISSN)
한국인터넷방송통신학회 (The Institute of Internet, Broadcasting and Communication)
권호 표지
DOI QR코드

DOI QR Code

딥 러닝 및 서포트 벡터 머신기반 센서 고장 검출 기법

Sensor Fault Detection Scheme based on Deep Learning and Support Vector Machine

  • 투고 : 2018.01.29
  • 심사 : 2018.04.06
  • 발행 : 2018.04.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

최근 산업현장에서 기계의 자동화가 크게 가속화됨에 따라 자동화 기계의 관리 및 유지보수에 대한 중요성이 갈수록 커지고 있다. 자동화 기계에 부착된 센서의 고장이 발생할 경우 기계가 오동작함으로써 공정라인 운용에 막대한 피해가 발생할 수 있다. 이를 막기 위해 센서의 상태를 모니터링하고 고장의 진단 및 분류를 하는 것이 필요하다. 본 논문에서는 센서에서 발생하는 대표적인 고장 유형인 erratic fault, drift fault, hard-over fault, spike fault, stuck fault를 기계학습 알고리즘인 SVM과 CNN을 적용하여 검출하고 분류하였다. SVM의 학습 및 테스트를 위해 데이터 샘플들로부터 시간영역 통계 특징들을 추출하고 최적의 특징을 찾기 위해 유전 알고리즘(genetic algorithm)을 적용하였다. Multi-class를 분류하기 위해 multi-layer SVM을 구성하여 센서 고장을 분류하였다. CNN에 대해서는 데이터 샘플들을 사용하여 학습시키고 성능을 높이기 위해 앙상블 기법을 적용하였다. 시뮬레이션 결과를 통해 유전 알고리즘에 의해 선별된 특징들을 사용한 SVM의 분류 결과는 모든 특징이 사용된 SVM 분류기 보다는 성능이 향상되었으나 전반적으로 CNN의 성능이 SVM보다 우수한 것을 확인할 수 있었다.

As machines have been automated in the field of industries in recent years, it is a paramount importance to manage and maintain the automation machines. When a fault occurs in sensors attached to the machine, the machine may malfunction and further, a huge damage will be caused in the process line. To prevent the situation, the fault of sensors should be monitored, diagnosed and classified in a proper way. In the paper, we propose a sensor fault detection scheme based on SVM and CNN to detect and classify typical sensor errors such as erratic, drift, hard-over, spike, and stuck faults. Time-domain statistical features are utilized for the learning and testing in the proposed scheme, and the genetic algorithm is utilized to select the subset of optimal features. To classify multiple sensor faults, a multi-layer SVM is utilized, and ensemble technique is used for CNN. As a result, the SVM that utilizes a subset of features selected by the genetic algorithm provides better performance than the SVM that utilizes all the features. However, the performance of CNN is superior to that of the SVM.

키워드

참고문헌

  1. Don-Ha Hwang, Young-Woo Youn, Jong-Ho Sun, Kyeong-Ho Choi, Jong-Ho Lee and Yong-Hwa Kim, "Support Vector Machine Based Bearing Fault Diagnosis for Induction Motors Using Vibration Signals", Journal of Electrical Engineering & Technology, Vol. 10, no. 4, pp. 1558-1565, 2015. DOI: http://dx.doi.org/10.5370/JEET.2015.10.4.1558
  2. WadeA.Smith, RobertB.Randall , "Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark study", Mechanical Systems and Signal Processing, Vol. 64-65, pp. 100-131, 2015. DOI: https://doi.org/10.1016/j.ymssp.2015.04.021
  3. Subhasis Nandi, Hamid A. Toliyat and Xiaodong Li, "Condition Monitoring and Fault Diagnosis of Electrical Motors", IEEE Transactions On Energy Conversion, Vol. 20, no. 4, pp. 719-729, 2005. DOI: http://doi.org/10.1109/TEC.2005.847955
  4. J. L. Yang, Y. S. Chen, L. L. Zhang, and Z. Sun, "Fault detection, isolation, and diagnosis of self-validating multifunctional sensors," Rev. Sci. Instrum., vol. 87, no. 6, 2016. DOI: https://doi.org/10.1063/1.4954184
  5. R. Dunia, S. J. Qin, T. F. Edgar, and T. J. Mcavoy, "Identification of Faulty Sensors Using Principal Component Analysis," Process Syst. Eng., vol. 42, no. 10, pp. 2797-2812, 1996. DOI: https://doi.org/10.1002/aic.690421011
  6. J. Kullaa, "Detection, identification, and quantification of sensor fault in a sensor network," Mech. Syst. Signal Process., vol. 40, no. 1, pp. 208 -221, 2013. DOI: https://doi.org/10.1016/j.ymssp.2013.05.007
  7. Y. Yu, W. Li, D. Sheng, and J. Chen, "A novel sensor fault diagnosis method based on Modified Ensemble Empirical Mode Decomposition and Probabilistic Neural Network," Measurement, vol. 68, pp. 328-336, 2015. DOI: https://doi.org/10.1016/j.measurement.2015.03.003
  8. Ming Liu, Xibin Cao, and Peng Shi, "Fuzzy-Model-Based Fault-Tolerant Design for Nonlinear Stochastic Systems Against Simultaneous Sensor and Actuator Faults," IEEE Transactions on Fuzzy Ststems, vol. 21, no. 5, pp. 789-799, 2015. DOI: https://doi.org/10.1109/TFUZZ.2012.2224872
  9. Gilbert Hock Beng Foo, Xinan Zhang, and D. M. Vilathgamuwa, "A Sensor Fault Detection and Isolation Method in Interior Permanent-Magnet Synchronous Motor Drives Based on an Extended Kalman Filter," IEEE Transactions on Electonics, vol. 60, no 8, pp. 3485-3495, 2013 DOI: https://doi.org/10.1109/TIE.2013.2244537
  10. B. Samanta, "Gear fault detection using artificial neural networks and support vector machines with genetic algorithms," Mech. Syst. Signal Process., vol. 18, no. 3, pp. 625-644, 2004. DOI: https://doi.org/10.1016/S0888-3270(03)00020-7
  11. T. W. Rauber, F. De Assis Boldt, and F.M. Varejaao, "Heterogeneous feature models and feature selection applied to bearing fault diagnosis," IEEE Trans. Ind. Electron., vol. 62, no. 1, pp. 637-646, 2015. DOI: https://doi.org/10.1109/TIE.2014.2327589
  12. Sana Ullah Jan, Young Doo Lee, Jungpil Shin and Insoo Koo, "Sensor Fault Classification Based on Support Vector Machine and Statistical Time-Domain Features", IEEE Access, Vol. 5, pp. 8682-8690, 2017. DOI: https://doi.org/10.1109/ACCESS.2017.2705644
  13. Seung-Jae Kim, Jung-Jae Lee, "A Study on Face Recognition using Support Vector Machine", The Journal of The Institute of Internet, Broadcasting and Communication, Vol. 16, No. 6, pp. 183-190, Jun. 2016. DOI: https://doi.org/10.7236/JIIBC.2016.16.6.183
  14. L.V. Ganyun, Cheng Haozhong, Zhai Haibao and Dong Lixin , "Fault diagnosis of power transformer based on multi-layer SVM classifier", Electric Power Systems Research, Vol. 74, no 1, pp. 1-7, 2005. DOI: https://doi.org/10.1016/j.epsr.2004.07.008
  15. David E. Goldberg and John H. Holland, "Genetic Algorithms and Machine Learning", Machine Learning, Vol. 3, no 2-3, pp. 95-99, 1988. DOI: https://doi.org/10.1023/A:1022602019183
  16. Hideyuki Ishigami, Toshio Fukuda, Takanori Shibata and Fumihito Arai, "Structure optimization of fuzzy neural network by genetic algorithm", Fuzzy Sets and Systems, Vol. 71, no 3, pp. 257-264, 1995. DOI: https://doi.org/10.1016/0165-0114(94)00283-D
  17. Shahrzad Faghih-Roohi, Siamak Hajizadeh and Alfredo Nunez, "Deep Convolutional Neural Networks for Detection of Rail Surface Defects", International Joint Conference on In Neural Networks(IJCNN), pp. 2584-2589, 2016. DOI: https://doi.org/10.1109/IJCNN.2016.7727522
  18. Dean Lee, Vincent Siu, Rick Cruz, and Charles Yetman, "Convolutional Neural Net and Bearing Fault Analysis", in Proc. Int. Conf. Data Min., Las Vegas, NV, USA, 2016, pp. 194-200.
  19. Min Meng, Yiting jacqueline Chua, Erwin Wouterson, and Chin Peng Kelvin Ong, "Ultrasonic signal classification and imaging system for composite materials via deep convolutional neural networks", Neurocomputing, Vol. 257, pp. 128-135, 2017. DOI: https://doi.org/10.1016/j.neucom.2016.11.066
  20. Seok-Cheon Park, "Design and Implementation of Personal Information Identification and Masking System Based on Image Recognition", The Journal of The Institute of Internet, Broadcasting and Communication, Vol. 17, No. 5, pp. 1-8, May. 2017. DOI: https://doi.org/10.7236/JIIBC.2017.17.5.1
  21. Seo-Hyeon Ryu, Jae-Bok Yoon, "The Effect of regularization and identity mapping on the performance of activation functions", Journal of the Korea Academia-Industrial cooperation Society, Vol. 18, No. 10, pp. 75-80, 2017. DOI: https://doi.org/10.5762/KAIS.2017.18.10.75