Journal of the Korea Society of Computer and Information (한국컴퓨터정보학회논문지)

Korean Society of Computer Information (한국컴퓨터정보학회)
권호 표지
DOI QR코드

DOI QR Code

Study on Fault Detection of a Gas Pressure Regulator Based on Machine Learning Algorithms

  • Seo, Chan-Yang (Postech Institute of Artificial Intelligence, POSTECH) ;
  • Suh, Young-Joo (Dept. of Computer Science and Engineering, POSTECH) ;
  • Kim, Dong-Ju (Postech Institute of Artificial Intelligence, POSTECH)
  • Received : 2020.02.06
  • Accepted : 2020.04.03
  • Published : 2020.04.29
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose a machine learning method for diagnosing the failure of a gas pressure regulator. Originally, when implementing a machine learning model for detecting abnormal operation of a facility, it is common to install sensors to collect data. However, failure of a gas pressure regulator can lead to fatal safety problems, so that installing an additional sensor on a gas pressure regulator is not simple. In this paper, we propose various machine learning approach for diagnosing the abnormal operation of a gas pressure regulator with only the flow rate and gas pressure data collected from a gas pressure regulator itself. Since the fault data of a gas pressure regulator is not enough, the model is trained in all classes by applying the over-sampling method. The classification model was implemented using Gradient boosting, 1D Convolutional Neural Networks, and LSTM algorithm, and gradient boosting model showed the best performance among classification models with 99.975% accuracy.

본 논문에서는 정압기의 이상 상태 진단을 위한 기계학습 방법을 제안한다. 일반적으로 설비의 이상 상태 탐지를 위한 기계학습 모델 구현에는 관련 센서의 설치와 데이터 수집 과정이 동반되나, 정압기는 설비 특성상 안전문제에 매우 민감하여 추가적인 센서 설치가 매우 까다롭다. 이에 본 논문에서는 센서의 추가 설치 없이 정압기 설비에서 자체 수집되는 유량과 유압 데이터만을 가지고 정압기의 이상 상태를 조기에 판단하는 기계학습 모델을 제안한다. 본 논문에서는 정압기의 비정상데이터가 충분하지 않은 관계로, 모델 학습 시 오버 샘플링(Over-Sampling)을 적용하여 모델이 모든 클래스에 균형적으로 학습하도록 하였다. 또한, 그레이디언트 부스팅(Gradient Boosting), 1차원 합성곱 신경망(1D Convolutional Neural Networks), LSTM(Long Short-Term Memory) 등의 기계학습 알고리즘을 적용하여 정압기의 이상 상태를 판단하는 분류모델을 구현하였고, 실험 결과 그레이디언트 부스팅 알고리즘이 정확도 99.975%로 가장 성능이 우수함을 확인하였다.

Keywords

References

  1. Jiao, J. Y., Wei, Y. P., Li, H. L., Liu, Y., Jiang, F., Song, M. X., & Tan, S. L. "A gas regulator fault detecting method based on acoustic emission technology." IEEE In 2017 Symposium on Piezoelectricity, Acoustic Waves, and Device Applications(SPA WDA), pp. 91-94, 2017, October. doi:10.1109/spawda.2017.8340295
  2. Tian, S., Bian, X., Tang, Z., Yang, K., & Li, L. "Fault Diagnosis of Gas Pressure Regulators Based on CEEMDAN and Feature Clustering", IEEE Access, Vol. 7, pp. 132492-132502, 2019. doi:10.1109/access.2019.2941497
  3. Ishigaki, T., Higuchi, T., & Watanabe, K. "Spectrum Classification for Early Fault Diagnosis of the LP Gas Pressure Regulator Based on the Kullback-Leibler Kernel." 2006 16th IEEE Signal Processing Society Workshop on Machine Learning for Signal Processing, Arlington, VA, pp. 453-458, 2006, doi:10.1109/mlsp.2006.275593
  4. Heo G. "Context Dependent Fusion with Support Vector Machines." Journal of The Korea Society of Computer and Information, Vol. 18, No. 7, pp. 37-45, 2013. doi:10.9708/jksci.2013.18.7.037
  5. Layouni, M., Hamdi, M. S., & Tahar, S. "Detection and sizing of metal-loss defects in oil and gas pipelines using pattern-adapted wavelets and machine learning." Applied Soft Computing, Vol. 52, pp. 247-261, 2017. doi:10.1016/j.asoc.2016.10.040
  6. Mohamed, A., Hamdi, M. S., & Tahar, S. "A machine learning approach for big data in oil and gas pipelines." IEEE, In 2015 3rd International Conference on Future Internet of Things and Cloud, pp. 585-590, 2015, August. doi:10.1109/ficloud.2015.54
  7. Akram, N. A., Isa, D., Rajkumar, R., & Lee, L. H. "Active incremental Support Vector Machine for oil and gas pipeline defects prediction system using long range ultrasonic transducers." Ultrasonics, Vol. 54, No. 6, pp. 1534-1544, 2014. doi:10.1016/j.ultras.2014.03.017
  8. Lee, L. H., Rajkumar, R., Lo, L. H., Wan, C. H., & Isa, D. "Oil and gas pipeline failure prediction system using long range ultrasonic transducers and Euclidean-Support Vector Machines classification approach." Expert Systems with Applications, Vol. 40, No. 6, pp. 1925-1934, 2013. doi:10.1016/j.eswa.2012.10.006
  9. Yeo, D., Bae, J. H., & Lee, J. C. "Unsupervised Learning-Based Pipe Leak Detection using Deep Auto-Encoder." Journal of the Korea Society of Computer and Information, Vol. 24, No. 9, pp. 21-27, 2019. doi:10.9708/JKSCI.2019.24.09.021
  10. Chung, W. H., Park, G., Gu, Y. H., Kim, S., & Yoo, S. J. "City Gas Pipeline Pressure Prediction Model." Journal of Society for e-Business Studies, Vol. 23, No. 2, 2019. doi:10.7838/JSEBS.2018.23.2.033
  11. Kim, J., Kim, H., Jang, K., Lee, J., and Moon, Y. "Object Classification Method Using Dynamic Random Forests and Genetic Optimization." Journal of the Korea Society of Computer and Information, Vol. 21, No. 5, pp. 79-89, 2016. doi:10.9708 /jksci.2016.21.5.079 https://doi.org/10.9708/jksci.2016.21.5.079
  12. Hochreiter, S., & Schmidhuber, J. "Long short-term memory." Neural computation, Vol. 9, No. 8, pp. 1735-1780, 1997. doi:10.1162/neco.1997.9.8.1735
  13. Wang, G., Shin, S. Y., & Lee, W. J. "A Text Sentiment Classification Method Based on LSTM-CNN." Journal of The Korea Society of Computer and Information, Vol. 24, No. 12, pp. 1-7, 2019. doi:10.1049/cje.2018.11.004
  14. Chen, T., & Guestrin, C. "Xgboost: A scalable tree boosting system." In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pp. 785-794, 2016. doi:10.1145/2939672.2939785
  15. Ke G, Meng Q, Finley T, Wang T, Chen W, Ma W, Ye Q, Liu TY. "Lightgbm: A highly efficient gradient boosting decision tree." In Advances in neural information processing systems, pp. 3146-3154, 2017. doi:10.1109/iccse.2019.8845529
  16. Ince, T., Kiranyaz, S., Eren, L., Askar, M., & Gabbouj, M. "Real-time motor fault detection by 1-D convolutional neural networks." IEEE Transactions on Industrial Electronics, Vol. 63, No. 11, pp. 7067-7075, 2016. doi:10.1109/tie.2016.2582729
  17. Mukhopadhyay, R., Panigrahy, P. S., Misra, G., & Chattopadhyay, P. "Quasi 1D CNN-based Fault Diagnosis of Induction Motor Drives." IEEE In 2018 5th International Conference on Electric Power and Energy Conversion Systems (EPECS), pp. 1-5, 2018, April. doi:10.1109/epecs.2018.8443552
  18. Jain, A., Nandakumar, K., & Ross, A. "Score normalization in multimodal biometric systems." Pattern recognition, Vol. 38, No. 12, pp. 2270-2285, 2005. doi:10.1016/j.patcog.2005.01.012
  19. Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. "SMOTE: synthetic minority over-sampling technique." Journal of artificial intelligence research, Vol. 16, pp. 321-357, 2002. doi:10.1613/jair.953