Journal of the Korea Academia-Industrial cooperation Society (한국산학기술학회논문지)

The Korea Academia-Industrial cooperation Society (한국산학기술학회)
권호 표지
DOI QR코드

DOI QR Code

Deep Learning-Based Vehicle Anomaly Detection by Combining Vehicle Sensor Data

차량 센서 데이터 조합을 통한 딥러닝 기반 차량 이상탐지

  • Kim, Songhee (Department of Industrial & Systems Enginnering, Dongguk University) ;
  • Kim, Sunhye (Department of Industrial & Systems Enginnering, Dongguk University) ;
  • Yoon, Byungun (Department of Industrial & Systems Enginnering, Dongguk University)
  • 김송희 (동국대학교 산업시스템공학과) ;
  • 김선혜 (동국대학교 산업시스템공학과) ;
  • 윤병운 (동국대학교 산업시스템공학과)
  • Received : 2020.12.18
  • Accepted : 2021.03.05
  • Published : 2021.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

In the Industry 4.0 era, artificial intelligence has attracted considerable interest for learning mass data to improve the accuracy of forecasting and classification. On the other hand, the current method of detecting anomalies relies on traditional statistical methods for a limited amount of data, making it difficult to detect accurate anomalies. Therefore, this paper proposes an artificial intelligence-based anomaly detection methodology to improve the prediction accuracy and identify new data patterns. In particular, data were collected and analyzed from the point of view that sensor data collected at vehicle idle could be used to detect abnormalities. To this end, a sensor was designed to determine the appropriate time length of the data entered into the forecast model, compare the results of idling data with the overall driving data utilization, and make optimal predictions through a combination of various sensor data. In addition, the predictive accuracy of artificial intelligence techniques was presented by comparing Convolutional Neural Networks (CNN) and Long Short Term Memory (LSTM) as the predictive methodologies. According to the analysis, using idle data, using 1.5 times of the data for the idling periods, and using CNN over LSTM showed better prediction results.

4차산업혁명 시대에는 대량의 데이터를 학습하여 예측과 분류의 정확성을 향상시킬 수 있는 인공지능의 활용이 핵심적이다. 그러나, 기존 이상탐지를 위한 방법은 제한된 데이터를 다루는 전통적인 통계 방법에 의존하고 있어, 정확한 이상탐지가 어렵다. 그러므로, 본 연구는 인공지능 기반 이상탐지 방법을 제시하여 예측 정확도를 높이고, 새로운 데이터 패턴을 정의하는 것을 목적으로 한다. 특히, 자동차의 경우 공회전 기간의 센서 데이터가 이상 탐지에 활용될 수 있다는 관점에서 데이터를 수집하고 분석하였다. 이를 위해, 예측 모델에 입력되는 데이터의 적정 시간 길이를 결정하고, 공회전 기간 데이터와 전체 운행 데이터의 분석 결과를 비교하며, 다양한 센서 데이터 조합에 의한 최적 예측 방법을 도출하였다. 또한, 인공지능 방법으로 선택된 CNN의 예측 정확성을 검증하기 위해 LSTM 결과와 비교하였다. 분석 결과, 공회전 데이터를 이용하고, 공회전 기간보다 1.5배 많은 기간의 데이터를 이용하며 LSTM보다는 CNN을 활용하는 것이 더 좋은 예측결과를 보였다.

Keywords

References

  1. M., Heinrich, A., Golz, T., Arul, S. Katzenbeisser, "Rule-based Anomaly Detection for Railway Signalling Networks", arXiv preprint arXiv:2008.05241, 2020.
  2. H. Sarmadi, A. Karamodin, "A novel anomaly detection method based on adaptive Mahalanobis-squared distance and one-c lass kNN rule for structural health monitoring under environmental effects.", Mechanical Systems and Signal Processing, Vol. 140, 106495, 2020. DOI: https://doi.org/10.1016/j.ymssp.2019.106495
  3. S. Lawrence, C.L. Giles, A.C. Tsoi, A.D. Back, "Face recognition: A convolutional neural-network approach." IEEE transactions on neural networks, Vol. 8, No. 1, pp. 98-113, 1997. DOI: https://doi.org/110.1109/72.554195
  4. M. Xia, T. Li, L. Xu, L. Liu, C.W. de Silva, "Fault Diagnosis for Rotating Machinery Using Multiple Sensors and Convolutional Neural Networks", IEEE/ASME Transactions on Mechatronics, Vol. 23, No. 1, pp. 101-110, 2018. DOI: https://doi.org/10.1109/TMECH.2017.2728371
  5. S.H. Lee, J.S. Kim, B.B. Shin, "CNN-Based Noise System for Motorized Driving Unit Fault Causes Classification System", Proceedings of the Korean Computer Information Conference, Vol. 26, No. 1, pp. 7-8, 2018.
  6. F.A. Gers, J. Schmidhuber, "Recurrent nets that time and count", In Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, Neural Computing: New Challenges and Perspectives for the New Millennium, Vol. 3, pp. 189-194, 2000. DOI: https://doi.org/10.1109/IJCNN.2000.861302
  7. P. Malhotra, L. Vig, G. Shroff, P. Agarwal "Long short term memory networks for anomaly detection in time series", In Proceedings, Presses universitaires de Louvain, p.89, 2015.
  8. S.G. Kim, T.I. Oh, "Real-time PM10 Concentration Prediction LSTM Model Based on IoT Streaming Sensor Data" Korea Journal of the Korean Society of Science and Technology, Vol. 19, No. 11, pp. 310-318, 2018. DOI: https://doi.org/10.5762/KAIS.2018.19.11.310
  9. B. Zong, Q. Song, M.R. Min, W. Cheng, C, Lumezanu, D. Cho, H. Chen, "Deep autoencoding gaussian mixture model for unsupervised anomaly detection", In Proceeding of International Conference on Learning Representations, 2018.
  10. D. Li, D. Chen, J. Goh, S.K. Ng, "Anomaly detection with generative adversarial networks for multivariate time series", arXiv preprint arXiv:1809.04758, 2018.
  11. C. Baur, B. Wiestler, S. Albarqouni, N. Navab, "Deep autoencoding models for unsupervised anomaly segmentation in brain MR images", In Proceeding of International MICCAI Brainlesion Workshop, pp. 161-169, 2018. DOI: https://doi.org/10.1007/978-3-030-11723-8_16
  12. ,M.R. Moore, J.M. Vann. (2019, January). Anomaly detection of cyber physical network data using 2D images. In Proceeding of 2019 IEEE International Conference on Consumer Electronics (ICCE) (pp. 1-5), 2019. DOI: https://doi.org/10.1109/ICCE.2019.8662084
  13. Q. Wei, Y, Ren, R. Hou, B. Shi, J.Y. Lo, L. Carin, "Anomaly detection for medical images based on a one-class classification", In Proceeding of Medical Imaging 2018: Computer-Aided Diagnosis, 2018. DOI: https://doi.org/10.1117/12.2293408
  14. M. Hasan, M.M. Islam, M.I.I. Zarif, M.M.A. Hashem, "Attack and anomaly detection in IoT sensors in IoT sites using machine learning approaches", Internet of Things, 7, 100059, 2019. DOI: https://doi.org/10.1016/j.iot.2019.100059
  15. P. Malhotra, L. Vig, G. Shroff, P. Agarwal, "Long short term memory networks for anomaly detection in time series", In Proceedings of Presses universitaires de Louvain, Vol. 89, pp. 89-94, 2015.
  16. N.Y. Choi, W.H. Kim, "Detecting user behavior anomalies using Generative Adversarial Networks", Intelligence Information Research, 25(3), 43-62, 2019.