Journal of Korean Association for Spatial Structures (한국공간구조학회논문집)

Korean Association for Spatial Structures (한국공간구조학회)
권호 표지
DOI QR코드

DOI QR Code

Performance Evaluation of Machine Learning Model for Seismic Response Prediction of Nuclear Power Plant Structures considering Aging deterioration

원전 구조물의 경년열화를 고려한 지진응답예측 기계학습 모델의 성능평가

  • Kim, Hyun-Su (Division of Architecture, Sunmoon University.) ;
  • Kim, Yukyung (Division of Architecture, Sunmoon University) ;
  • Lee, So Yeon (Division of Architecture, Sunmoon University) ;
  • Jang, Jun Su (Division of Architecture, Sunmoon University)
  • Received : 2024.08.07
  • Accepted : 2024.08.24
  • Published : 2024.09.15
Download PDF
⟨ Previous Next ⟩

Abstract

Dynamic responses of nuclear power plant structure subjected to earthquake loads should be carefully investigated for safety. Because nuclear power plant structure are usually constructed by material of reinforced concrete, the aging deterioration of R.C. have no small effect on structural behavior of nuclear power plant structure. Therefore, aging deterioration of R.C. nuclear power plant structure should be considered for exact prediction of seismic responses of the structure. In this study, a machine learning model for seismic response prediction of nuclear power plant structure was developed by considering aging deterioration. The OPR-1000 was selected as an example structure for numerical simulation. The OPR-1000 was originally designated as the Korean Standard Nuclear Power Plant (KSNP), and was re-designated as the OPR-1000 in 2005 for foreign sales. 500 artificial ground motions were generated based on site characteristics of Korea. Elastic modulus, damping ratio, poisson's ratio and density were selected to consider material property variation due to aging deterioration. Six machine learning algorithms such as, Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Artificial Neural Networks (ANN), eXtreme Gradient Boosting (XGBoost), were used t o construct seispic response prediction model. 13 intensity measures and 4 material properties were used input parameters of the training database. Performance evaluation was performed using metrics like root mean square error, mean square error, mean absolute error, and coefficient of determination. The optimization of hyperparameters was achieved through k-fold cross-validation and grid search techniques. The analysis results show that neural networks present good prediction performance considering aging deterioration.

Keywords

Acknowledgement

본 논문은 2022년도 가동원전 안전성향상 핵심기술개발사업의 지원으로 수행되고 있는 과제(과제번호: 20224B10200080) 내용의 일부입니다. 산업통상자원부와 한국에너지기술평가원의 연구비 지원에 깊은 감사를 드립니다.

References

  1. Leel, Y., Kim, J.H. and Park, H.G., "Seismic fragility analysis of anchorage failure in nuclear power plant structure", Journal of the Korea Concrete Institute, Vol. 34, pp. 321-331, 2022, DOI:https://doi.org/10.4334/JKCI.2022.34.3.321.
  2. Choi, I.K., "Review and proposal for seismic safety assessment of nuclear power plants against beyond design basis earthquake", Transactions of the Korean Society of Pressure Vessels and Piping, Vol. 13, pp. 1-15, 2017, DOI:https://doi.org/10.20466/KPVP.2017.13.1.001
  3. Wakefield, W., Ravindra, M., Merz, K., and Hardy, G., "Seismic probabilistic risk assessment implementation guide," Electric Power Research Institute, EPRI-1002989, 2003.
  4. Lee, S., Kwag, S., and Ju, B.S., "A development of seismic fragility curve of box-type squat shear walls using data-driven surrogate model techniques," International Journal of Energy Research, Vol. 2024, Article ID 5872960, 2024, DOI:https://doi.org/10.1155/2024/5872960
  5. Jia, D.W., and Wu, Z.Y., "Seismic fragility analysis of RC frame-shear wall structure under multidimensional performance limit state based on ensemble neural network", Vol. 246, Article ID 112975, 2022, DOI:https://doi.org/10.1016/j.engstruct.2021.112975
  6. Kiani, J., Camp, C., and Pezeshk, S., "On the application of machine learning techniques to derive seismic fragility curves", Computers & Structures, Vol. 218, pp. 108-122, 2019, DOI:https://doi.org/10.1016/j.compstruc.2019.03.004
  7. Thai, H.T., "Machine learning for structural engineering: A state-of-the-art review", Structures, Vol. 38, pp. 448-491, 2022, DOI:https://doi.org/10.1016/j.istruc.2022.02.003.
  8. Kazemi, F., Asgarkhani, N. and Jankowski, R., "Machine learning-based seismic response and performance assessment of reinforced concrete buildings", Archives of Civil and Mechanical Engineering, Vol. 23, 2023, DOI:https://doi.org/10.1007/s43452-023-00631-9
  9. Kim, H.S., Kim, Y., Lee, S.Y., and Jang, J.S., "Development of machine learning based seismic response prediction model for shear wall structure considering aging deteriorations", Journal of Korean Association for Spatial Structures, Vol. 24, pp. 83-90, 2024, DOI:http://dx.doi.org/10.9712/KASS.2024.24.2.83.
  10. Hariri-Ardebili, M.A., Sanchez, L. and Rezakhani, R., "Aging of Concrete Structures and Infrastructures: Causes, Consequences, and Cures (C3 )", Advances in Materials Science and Engineering, 2020, DOI:https://doi.org/10.1155/2020/9370591
  11. Arel, H.S., Aydin, E. and Kore, S.D., "Ageing management and life extension of concrete in nuclear power plants", Powder Technology, Vol. 321, pp. 390-408, 2017, DOI:https://doi.org/10.1016/j.powtec.2017.08.053.
  12. Choi, J.H., Kim, Y.S., Gwon, S., Edwards, P., Rezaei, S., Kim, T., and Lim, S.B., "Characteristics of large-scale fault zone and quaternary fault movement in Maegok-dong, Ulsan", The Journal of Engineering Geology, Vol. 24, pp. 485-498, 2015, DOI:http://dx.doi.org/10.9720/kseg.2015.4.485
  13. Wang, Z., Pedroni, N., Zentner, I. and Zio. E., "Seismic fragility analysis with artificial neural networks: Application to nuclear power plant equipment", Engineering Structures, Vol. 162, pp.213-225, 2018, DOI:https://doi.org/10.1016/j.engstruct.2018.02.024