Structural Engineering and Mechanics

  • 제88권6호
  • /
  • Pages.569-581
  • /
  • 2023
  • /
  • 1225-4568(pISSN)
  • /
  • 1598-6217(eISSN)
테크노프레스 (Techno-Press)
권호 표지
DOI QR코드

DOI QR Code

Multi-sensor data-based anomaly detection and diagnosis of a pumped storage hydropower plant

  • Sojin Shin (Department of Mechanical Engineering, Korean Advanced Institute for Science and Technology) ;
  • Cheolgyu Hyun (Department of Mechanical Engineering, Korean Advanced Institute for Science and Technolog) ;
  • Seongpil Cho (School of Aerospace and Mechanical Engineering, Korea Aerospace University) ;
  • Phill-Seung Lee (Department of Mechanical Engineering, Korean Advanced Institute for Science and Technolog)
  • 투고 : 2023.11.01
  • 심사 : 2023.12.02
  • 발행 : 2023.12.25
⟨ 이전 논문 다음 논문 ⟩

초록

This paper introduces a system to detect and diagnose anomalies in pumped storage hydropower plants. We collect data from various types of sensors, including those monitoring temperature, vibration, and power. The data are classified according to the operation modes (pump and turbine operation modes) and normalized to remove the influence of the external environment. To detect anomalies and diagnose their types, we adopt a multivariate normal distribution analysis by learning the distribution of the normal data. The feasibility of the proposed system is evaluated using actual monitoring data of a pumped storage hydropower plant. The proposed system can be used to implement condition monitoring systems for other plants through modifications.

키워드

과제정보

This research was supported by Korea Hydro & Nuclear Power Co. Ltd. (No. 2017-Tech-11).

참고문헌

  1. Assaf, R., Nefti-Meziani, S. and Scarf, P. (2017), "Unsupervised learning for improving fault detection in complex systems", 2017 IEEE International Conference on Advanced Intelligent Mechatronics (AIM), 1058-1064. 
  2. Astolfi, D., Scappaticci, L. and Terzi, L. (2017), "Fault diagnosis of wind turbine gearboxes through temperature and vibration data", Int. J. Renew. Energy Res., 7(2), 965-976. 
  3. Bahrami, F. and Moazzami, M. (2019), "Long-term generation maintenance scheduling with integration of pumped storage units", Int. J. Renew. Eng. Res., 9(4), 1694-1704. https://doi.org/10.20508/ijrer.v9i4.10035.g7828. 
  4. Banerjee, T.P. and Das, S. (2012), "Multi-sensor data fusion using support vector machine for motor fault detection", Inform. Sci., 217, 96-107. https://doi.org/10.1016/j.ins.2012.06.016. 
  5. Bayarjargal, D. and Cho, G. (2014), "Detecting an anomalous traffic attack area based on entropy distribution and mahalanobis distance", Int. J. Sec. Its Appl., 8(2), 87-94.  https://doi.org/10.14257/ijsia.2014.8.2.09
  6. Cheliotis, M., Lazakis, I. and Theotokatos, G. (2020), "Machine learning and data-driven fault detection for ship systems operations", Ocean Eng., 216, 107968. https://doi.org/10.1016/j.oceaneng.2020.107968. 
  7. Dunteman, G.H. (1989), Principal Components Analysis, Vol. 69, Sage. 
  8. Forrester, B.D. (1996), "Advanced vibration analysis techniques for fault detection and diagnosis in geared transmission systems", Ph.D. Dissertation, Swinburne University of Technology, Melbourne. 
  9. Frank, P.M., Ding, S.X. and Marcu, T. (2000), "Model-based fault diagnosis in technical processes", Trans. Inst. Meas. Control, 22(1), 57-101. https://doi.org/10.1177/014233120002200104. 
  10. Gao, Z., Cecati, C. and Ding, S.X. (2015), "A survey of fault diagnosis and fault-tolerant techniques-Part I: Fault diagnosis with model-based and signal-based approaches", IEEE Trans. Indus. Electron., 62(6), 3757-3767. https://doi.org/10.1109/TIE.2015.2417501. 
  11. Gertler, J.J. (1988), "Survey of model-based failure detection and isolation in complex plants", IEEE Control Syst. Mag., 8(6), 3-11. https://doi.org/10.1109/37.9163. 
  12. Gross, K.C., Singer, R.M., Wegerich, S.W., Herzog, J.P., VanAlstine, R. and Bockhorst, F. (1997), Application of a Model-Based Fault Detection System to Nuclear Plant Signals, IL, United States. 
  13. Isermann, R. (2005), "Model-based fault-detection and diagnosis-status and applications", Ann. Rev. Control, 29(1), 71-85. https://doi.org/10.1016/j.arcontrol.2004.12.002. 
  14. Kim, T.W., Chang, Y., Kim, D.W. and Kim, M.K. (2020), "Preventive maintenance and forced outages in power plants in Korea", Energi., 13(14), 3571. https://doi.org/10.3390/en13143571. 
  15. Kurien, C. and Srivastava, A.K. (2018), "Condition monitoring of systems in thermal power plant for vibration, motor signature, noise and wear debris analysis", World Scientif. News, 91, 31-43. 
  16. Lee, J. (2019), "Anomaly detection of hydro turbine using autoencoder", 32nd KKHTCNN Symposium on Civil Engineering, KAIST. 
  17. Li, C., Sanchez, R.V., Zurita, G., Cerrada, M. and Cabrera, D. (2016), "Fault diagnosis for rotating machinery using vibration measurement deep statistical feature learning", Sensor., 16(6), 895. https://doi.org/10.3390/s16060895. 
  18. Ma, M., Sun, C. and Chen, X. (2018), "Deep coupling autoencoder for fault diagnosis with multimodal sensory data", IEEE Trans. Indus. Inform., 14(3), 1137-1145. https://doi.org/10.1109/TII.2018.2793246. 
  19. Madeti, S.R. and Singh, S.N. (2018), "Modeling of PV system based on experimental data for fault detection using kNN method", Solar Energy, 173, 139-151. https://doi.org/10.1016/j.solener.2018.07.038. 
  20. Neville, S.W. and Dimopoulos, N.J. (1995), "Techniques for confident and reliable fault detection in large scale engineering plants", 1995 IEEE International Conference on Systems, Man and Cybernetics. Intelligent Systems for the 21st Century, 2, 1807-1812. https://doi.org/10.1109/ICSMC.1995.538037. 
  21. Prajapati, A., Bechtel, J. and Ganesan, S. (2012), "Condition based maintenance: A survey", J. Qual. Maint. Eng., 18(4), 384-400. https://doi.org/10.1108/13552511211281552. 
  22. Rao, B. (1996), Handbook of Condition Monitoring, Elsevier.
  23. Safizadeh, M.S. and Latifi, S.K. (2014), "Using multi-sensor data fusion for vibration fault diagnosis of rolling element bearings by accelerometer and load cell", Inform. Fus., 18, 1-8. https://doi.org/10.1016/j.inffus.2013.10.002. 
  24. Schwabacher, M. (2005), A Survey of Data-Driven Prognostics, In Infotech@ Aerospace. https://doi.org/10.2514/6.2005-7002. 
  25. Shatnawi, Y. and Al-Khassaweneh, M. (2013), "Fault diagnosis in internal combustion engines using extension neural network", IEEE Trans. Indus. Electron., 61(3), 1434-1443. https://doi.org/10.1109/TIE.2013.2261033. 
  26. Simani, S., Fantuzzi, C. and Patton, R.J. (2003), Model-based Fault Diagnosis Techniques, Springer, London. 
  27. Sovacool, B.K. and Sovacool, K.E. (2009), "Identifying future electricity water tradeoffs in the United States", Eng. Pol., 37(7), 2763-2773. https://doi.org/10.1016/j.enpol.2009.03.012. 
  28. Tong, Y.L. (2012), The Multivariate Normal Distribution, Springer Science & Business Media. 
  29. Tsang, A.H. (1995), "Condition-based maintenance: tools and decision making", J. Qual. Maint. Eng., 1(3), 3-17. https://doi.org/10.1108/13552519510096350. 
  30. Wen, L., Li, X., Gao, L. and Zhang, Y. (2017), "A new convolutional neural network-based data-driven fault diagnosis method", IEEE Trans. Indus. Electron., 65(7), 5990-5998. https://doi.org/10.1109/TIE.2017.2774777. 
  31. Wu, B., Saxena, A., Khawaja, T.S., Patrick, R., Vachtsevanos, G. and Sparis, P. (2004), "An approach to fault diagnosis of helicopter planetary gears", Proceedings AUTOTESTCON 2004, 475-481. https://doi.org/10.1109/AUTEST.2004.1436936.