Optimization and range expansion of IRIS reactor accident diagnosis model based on LSTM neural network
-
Tianze Bai
Abstract
Small reactors have the advantages of compact structure and wide application scenarios, and can be deployed in remote areas. However, due to the complex structure and special application scenarios, it is more difficult for operators to diagnose and identify accident information. This article conducts accident diagnosis research using simulated data from IRIS reactors. An accident diagnosis model based on LSTM neural network has been established. The diagnostic ability of the model has been analyzed when there is an error in the time of the accident occurrence. When there are numerical and time errors in the dataset, the simulated diagnostic accuracy is 96.8 %. The method of using a diagnostic model based on shutdown signal partitioning has improved the diagnostic ability of transient operating events and minor accident conditions, achieving an accuracy of 96.1 % when there is ±5 % noise in the dataset. By optimizing the output form of the diagnostic model, the diagnosis of unknown accidents was achieved. When using LOCA and LOFA accidents as unknown accidents, the diagnostic accuracy of the model reached 98.5 %.
-
Research ethics: Not applicable.
-
Informed consent: Not applicable.
-
Author contributions: All authors have accepted responsibility for the entire content of this manuscript and approved its submission.
-
Use of Large Language Models, AI and Machine Learning Tools: None declared.
-
Conflict of interest: The authors state no conflict of interest.
-
Research funding: None declared.
-
Data availability: The raw data can be obtained on request from the corresponding author.
References
Abdellatif, H.H., Bhowmik, P.K., Arcilesi, D., and Sabharwall, P. (2024). Evaluating direct vessel injection accident-event progression of AP1000 and key figures of merit to support the design and development of water-cooled small modular reactors. Nucl. Eng. Technol. 56: 2375–2387, https://doi.org/10.1016/j.net.2024.01.049.Search in Google Scholar
Boring, R.L., Thomas, K.D., Ulrich, T.A., and Lew, R.T. (2015). Computerized operator support systems to aid decision making in nuclear power plants. Procedia. Manuf. 3: 5261–5268, https://doi.org/10.1016/j.promfg.2015.07.604.Search in Google Scholar
Carelli, M.D., Conway, L., Oriani, L., Petrović, B., Lombardi, C., Ricotti, M.E., Barroso, A., Collado, J., Cinotti, L., Todreas, N., et al.. (2004). The design and safety features of the IRIS reactor. Nucl. Eng. Des. 230: 151–167, https://doi.org/10.1016/j.nucengdes.2003.11.022.Search in Google Scholar
Chen, H.Y., Liu, F.D., Wang, S.W., Wang, Y.C., Xu, C., and Liu, Q.F. (2023). Accident source term and radiological consequences of a small modular reactor. Nucl. Sci. Techniques 34: 40, https://doi.org/10.1007/s41365-023-01192-5.Search in Google Scholar
Choi, G.P., Yoo, K.H., Back, J.H., and Na, M.G. (2017). Estimation of LOCA break size using cascaded fuzzy neural networks. Nucl. Eng. Technol. 49: 495–503, https://doi.org/10.1016/j.net.2016.11.001.Search in Google Scholar
Farber, J.A. and Cole, D.G. (2020). Detecting loss-of-coolant accidents without accident-specific data. Prog. Nucl. Energy 128: 103469, https://doi.org/10.1016/j.pnucene.2020.103469.Search in Google Scholar
Fletcher, C. and Schultz, R. (1995). RELAP5/MOD3 code manual. Technical Report NUREG/CR-5535, INEL-95/0174, Idaho National Engineering Laboratory.Search in Google Scholar
Hanna, B., Son, T.C., and Dinh, N. (2021). AI-guided reasoning-based operator support system for the nuclear power plant management. Ann. Nucl. Energy 154: 108079, https://doi.org/10.1016/j.anucene.2020.108079.Search in Google Scholar
Kim, S.G., No, Y.G., and Seong, P.H. (2015). Prediction of severe accident occurrence time using support vector machines. Nucl. Eng. Technol. 47: 74–84, https://doi.org/10.1016/j.net.2014.10.001.Search in Google Scholar
Li, X., Huang, T., Cheng, K., Qiu, Z., and Sichao, T. (2022). Research on anomaly detection method of nuclear power plant operation state based on unsupervised deep generative model. Ann. nucl. energy 167: 108785, https://doi.org/10.1016/j.anucene.2021.108785.Search in Google Scholar
Li, X., Fu, X.M., Xiong, F.R., and Bai, X.M. (2020). Deep learning-based unsupervised representation clustering methodology for automatic nuclear reactor operating transient identification. Knowl. Base. Syst. 204: 106178, https://doi.org/10.1016/j.knosys.2020.106178.Search in Google Scholar
Lin, T.H. and Wu, S.C. (2019). Sensor fault detection, isolation and reconstruction in nuclear power plants. Ann. Nucl. Energy 126: 398–409, https://doi.org/10.1016/j.anucene.2018.11.044.Search in Google Scholar
Lin, T.H., Wang, T.C., and Wu, S.C. (2021). Deep learning schemes for event identification and signal reconstruction in nuclear power plants with sensor faults. Ann. Nucl. Energy 154: 108113, https://doi.org/10.1016/j.anucene.2020.108113.Search in Google Scholar
Moshkbar-Bakhshayesh, K. and Pourjafarabadi, E. (2019). Unsupervised classification of NPPs transients based on online dynamic quantum clustering. Eur. Phys. J. Plus 134: 483, https://doi.org/10.1140/epjp/i2019-12915-4.Search in Google Scholar
Oriani, L. (2003). IRIS preliminary safety assessment. WCAP-16082-NP.Search in Google Scholar
Prasad, S., Abdulla, A., Morgan, M.G., and Azevedo, I.L. (2015). Nonproliferation improvements and challenges presented by small modular reactors. Prog. Nucl. Energy 80: 102–109, https://doi.org/10.1016/j.pnucene.2014.11.023.Search in Google Scholar
Ricotti, M.E., Cammi, A., Cioncolini, A., Cipollaro, A., Oriolo, F., Lombardi, C., Conway, L., and Barroso, A. (2002). Preliminary safety analysis of the IRIS reactor. In: Proceedings series international conference on nuclear engineering ICONE10-22398, pp. 797–805.10.1115/ICONE10-22398Search in Google Scholar
Saeed, H.A., Peng, M.j., Wang, H., and Zhang, B.W. (2020). Novel fault diagnosis scheme utilizing deep learning networks. Prog. Nucl. Energy 118: 103066, https://doi.org/10.1016/j.pnucene.2019.103066.Search in Google Scholar
Schmidhuber, J. and Hochreiter, S. (1997). Long short-term memory. Neural. Comput. 9: 1735–1780, https://doi.org/10.1162/neco.1997.9.8.1735.Search in Google Scholar PubMed
Shin, J.H., Kim, J.M., and Lee, S.J. (2021). Abnormal state diagnosis model tolerant to noise in plant data. Nucl. Eng. Technol. 53: 1181–1188, https://doi.org/10.1016/j.net.2020.09.025.Search in Google Scholar
Tan, S., Cheng, S., Wang, K., Liu, X., Cheng, H., and Wang, J. (2023). The development of micro and small modular reactor in the future energy market. Front. Energy. Res. 11: 1149127, https://doi.org/10.3389/fenrg.2023.1149127.Search in Google Scholar
Wang, Y., Chen, W., Zhang, L., Zhao, X., Gao, Y., and Dinavahi, V. (2024). Small modular reactors: an overview of modeling, control, simulation, and applications. IEEE Access 12: 39628–39650, https://doi.org/10.1109/ACCESS.2024.3351220.Search in Google Scholar
Yang, J. and Kim, J. (2018). An accident diagnosis algorithm using long short-term memory. Nucl. Eng. Technol. 50: 582–588, https://doi.org/10.1016/j.net.2018.03.010.Search in Google Scholar
Yao, Y., Wang, J., Xie, M., Hu, L., and Wang, J. (2020). A new approach for fault diagnosis with full-scope simulator based on state information imaging in nuclear power plant. Ann. Nucl. Energy 141: 107274, https://doi.org/10.1016/j.anucene.2019.107274.Search in Google Scholar
Yoon, S.J., Rabiti, C., and Sackett, J. (2014). EBR-II data digitization. INL/EXT-14-32937, report, Idaho national lab (INL), Idaho Falls, ID (United States).10.2172/1196549Search in Google Scholar
Zaremba, W. (2014). Recurrent neural network regularization. arXiv preprint, https://doi.org/10.48550/arXiv.1409.2329.Search in Google Scholar
Zhang, C., Chen, P., Jiang, F., Xie, J., and Yu, T. (2023). Fault diagnosis of nuclear power plant based on sparrow search algorithm optimized CNN-LSTM neural network. Energies 16: 2934, https://doi.org/10.3390/en16062934.Search in Google Scholar
© 2025 Walter de Gruyter GmbH, Berlin/Boston
Articles in the same Issue
- Frontmatter
- Study on the diffusion behavior of rhenium in CTAB-modified bentonite
- Optimization and range expansion of IRIS reactor accident diagnosis model based on LSTM neural network
- Thermal integrity assessment of the limiter for Pakistan Spherical Tokamak (PST)
- The effect of ambient temperature variation on the spectrometric performance of NaI (Tl) scintillation detector; an experimental study
- Calendar of events
Articles in the same Issue
- Frontmatter
- Study on the diffusion behavior of rhenium in CTAB-modified bentonite
- Optimization and range expansion of IRIS reactor accident diagnosis model based on LSTM neural network
- Thermal integrity assessment of the limiter for Pakistan Spherical Tokamak (PST)
- The effect of ambient temperature variation on the spectrometric performance of NaI (Tl) scintillation detector; an experimental study
- Calendar of events
