DOI QR코드

DOI QR Code

Development of a New Prediction Alarm Algorithm Applicable to Pumped Storage Power Plant

양수발전 설비에 적용 가능한 새로운 고장 예측경보 알고리즘 개발

  • Dae-Yeon Lee (Department of Smart Production & Management Engineering, Hanbat National University) ;
  • Soo-Yong Park (Department of Convergence Technology, Hanbat National University) ;
  • Dong-Hyung Lee (Department of Industrial & Management Engineering, Hanbat National University)
  • 이대연 (국립 한밭대학교 스마트생산경영공학과, 가온플랫폼(주)) ;
  • 박수용 (국립 한밭대학교 융합기술학과) ;
  • 이동형 (국립 한밭대학교 산업경영공학과)
  • Received : 2023.06.05
  • Accepted : 2023.06.19
  • Published : 2023.06.30

Abstract

The large process plant is currently implementing predictive maintenance technology to transition from the traditional Time-Based Maintenance (TBM) approach to the Condition-Based Maintenance (CBM) approach in order to improve equipment maintenance and productivity. The traditional techniques for predictive maintenance involved managing upper/lower thresholds (Set-Point) of equipment signals or identifying anomalies through control charts. Recently, with the development of techniques for big analysis, machine learning-based AAKR (Auto-Associative Kernel Regression) and deep learning-based VAE (Variation Auto-Encoder) techniques are being actively applied for predictive maintenance. However, this predictive maintenance techniques is only effective during steady-state operation of plant equipment, and it is difficult to apply them during start-up and shutdown periods when rises or falls. In addition, unlike processes such as nuclear and thermal power plants, which operate for hundreds of days after a single start-up, because the pumped power plant involves repeated start-ups and shutdowns 4-5 times a day, it is needed the prediction and alarm algorithm suitable for its characteristics. In this study, we aim to propose an approach to apply the optimal predictive alarm algorithm that is suitable for the characteristics of Pumped Storage Power Plant(PSPP) facilities to the system by analyzing the predictive maintenance techniques used in existing nuclear and coal power plants.

Keywords

Acknowledgement

This work was supported by KOREA HYDRO & NUCLEAR POWER CO., LTD. (No. H22-S023-000).

References

  1. Barello, G., Sparse-Coding Variational Auto-Encoders, Institute of Neuroscience, University of Oregon, https://doi.org/10.1101/399246.
  2. Cha, J.S., Trend of Pumped-Hydro Storage Oversea and Prospect in Korea, The 45th KIEE Summer Conference, pp. 235-236, 2014.
  3. Chen, T., Unsupervised Anomaly Detection of Industrial Robots Using Sliding-Window Convolutional Variational Autoencoder, IEEE ACCESS, 2020, 2977892.
  4. Hines, J.W., MSET Performance Optimization Through Regularization, Nuclear Engineering and Technology, 2005, Vol. 37, No. 2, pp. 177-184.
  5. Kim, K.H., Fault Detection Using Signal Reconstruction Model Based on Autoencoder in Thermal Power Plant, The Transaction of Korean Institute of Electrical Engineers, 2020, Vol. 69, No. 6, pp. 800-807. https://doi.org/10.5370/KIEE.2020.69.6.800
  6. Kim, S.H., Application of Sensor Fault Detection Scheme Based on AANNto Risk Measurement System, The Korean Society of Oceanography Reserves, 2006, Vol. 11, No. 2, pp. 92-96.
  7. Kwon, S.H., Anomaly Detection of Big Time Series Using Machine Learning, Society of Korea Industrial and Systems Engineering, 2020, Vol. 43, No. 2, pp. 33-38. https://doi.org/10.11627/jkise.2020.43.2.033
  8. Lim, B.S., Development of Pumped Storage Power Fault Predictive Diagnosis, The Transaction of Korean Institue of Electrical Engineers, Summer Conference Proceedings, 2016, pp. 13-15.
  9. Min, J.H.(KHNP), Development of Early Warning Model Based on Pattern Learning for the Operation Condition in Nuclear Power Plant, Journal of the Korean Society for Power System, Engineering, 2018, Vol. 22, No. 4, pp. 17-23. https://doi.org/10.9726/kspse.2018.22.4.017
  10. Min, J.H.(KHNP), Optimization of Pattern Model and Fault Decision Rule for Early Warning System in NPPs, Journal of Mechanical Science and Technology Engineering, 2017, Vol. 42, No. 1, pp. 63-70. https://doi.org/10.3795/KSME-B.2018.42.1.063
  11. Yang, H.J., Deciding the Optimal Shutdown Time Incorporating the Accident Forecasting Model, Society of Korea Industrial and Systems Engineering, 2018, Vol. 41, No. 4, pp. 171-178. https://doi.org/10.11627/jkise.2018.41.4.171