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

Experimental Study on Application of an Anomaly Detection Algorithm in Electric Current Datasets Generated from Marine Air Compressor with Time-series Features

시계열 특징을 갖는 선박용 공기 압축기 전류 데이터의 이상 탐지 알고리즘 적용 실험

  • Lee, Jung-Hyung (Division of Marine System Engineering, Mokpo Maritime University)
  • 이정형 (목포해양대학교 기관시스템공학부)
  • Received : 2021.02.08
  • Accepted : 2021.02.25
  • Published : 2021.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, an anomaly detection (AD) algorithm was implemented to detect the failure of a marine air compressor. A lab-scale experiment was designed to produce fault datasets (time-series electric current measurements) for 10 failure modes of the air compressor. The results demonstrated that the temporal pattern of the datasets showed periodicity with a different period, depending on the failure mode. An AD model with a convolutional autoencoder was developed and trained based on a normal operation dataset. The reconstruction error was used as the threshold for AD. The reconstruction error was noted to be dependent on the AD model and hyperparameter tuning. The AD model was applied to the synthetic dataset, which comprised both normal and abnormal conditions of the air compressor for validation. The AD model exhibited good detection performance on anomalies showing periodicity but poor performance on anomalies resulting from subtle load changes in the motor.

본 연구는 선박용 공기압축기의 상태기반보전 시스템에 필요한 이상치 탐지 알고리즘 적용에 대한 실험적 연구로서 고장모사 실험을 통해 시계열 전류 센서 데이터를 이용한 이상탐지 적용 가능성을 확인하였다. 고장 유형 10개에 대해 실험실 규모의 고장 모사 실험을 수행하여 정상 운전데이터와 고장 데이터를 구축하였다. 실험 결과 구축된 이상탐지 모델은 시계열 데이터의 주기에 변화를 유발하는 이상은 잘 탐지하는 반면 미세한 부하 변동에 대한 탐지 성능은 떨어졌다. 또한 오토인코더를 이용한 시계열 이상탐지 모델은 입력 시퀀스의 길이와 초모수 조정에 따라 이상 탐지 성능이 상이한 것으로 나타났다.

Keywords

References

  1. Bae, Y. M., M. J. Kim, K. J. Kim, C. H. Jun, S. S. Byeon, and K. M. Park(2018), A Case Study on the Establishment of Upper Control Limit to Detect Vessel's Main Engine Failures using Multivariate Control Chart, Journal of the Society of Naval Architects of Korea, Vol. 55, No. 6, pp. 505-513. https://doi.org/10.3744/SNAK.2018.55.6.505
  2. Cook, A. A., G. Misirli, and Z. Fan(2019), Anomaly detection for IoT time-series data: A survey, IEEE Internet of Things Journal, Vol. 7, No. 7, 6481-6494. https://doi.org/10.1109/jiot.2019.2958185
  3. Korean Maritime Safety Tribunal(2019), Investigation report of Maritime Safety Judgement.
  4. Lee, J. H., S. Y. Yoo, S. Shin, D. H. Kang, S. S. Lee, and J. C. Lee(2019), Fault diagnosis of bearings using machine learning algorithm, Journal of Advanced Marine Engineering and Technology, Vol. 43, No. 6, pp. 455-462. https://doi.org/10.5916/jkosme.2019.43.6.455
  5. Nicolau, M. and J. McDermott(2018), Learning neural representations for network anomaly detection, IEEE transactions on cybernetics, Vol. 49, No. 8, pp. 3074-3087. https://doi.org/10.1109/tcyb.2018.2838668
  6. Park, J. C., J. S. Jang, and Y. H. Jo(2019), A Study for the Development of Fault Diagnosis Technology Based on Condition Monitoring of Marine Engine, Proceedings of the Korean Institute of Navigation and Port Research Conference, pp. 230-231.
  7. Park, J., M. Song, and S. Ahn(2020), Developing the Fault Diagnostics and Prognostics Model of a Rotating Machinery, Journal of the Korean Operations Research and Management Science Society, Vol. 45, No. 1, pp. 25-38. https://doi.org/10.7737/jkorms.2020.45.1.025