Abstract
The application of machine learning in the nuclear field has been considered for the prediction of neutron irradiation embrittlement of reactor pressure vessel (RPV) steels in recent years. In this study, the RPV irradiation surveillance data are summarized and the integration of physical mechanisms with machine learning is investigated. It is found that the experimental results of the fusion model outperform the single machine learning models or physics formulas. In addition, the data amount of the RPV dataset is enhanced using the variational auto-encoder (VAE) model. Then a combined model of VAE and physical formula guided multilayer perceptron (VPMLP) is proposed, and its advantages in terms of prediction accuracy and generalization ability are experimentally demonstrated.
This work was supported by National Natural Science Foundation of China (No. 12205188), Natural Science Foundation of Shanghai (No. 22ZR1428700), and China National Nuclear Corporation (No. CNNC-LCKY-202236).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Brillaud, C., Hedin, F., Houssin, B.: A comparison between French surveillance program results and predictions of irradiation embrittlement. In: Stoller, R.E., Garner, F.A., Henager, C.H., Iagata, N. (eds.) Effects of Radiation on Materials: 13th International Symposium, ASTM STP 956, Philadelphia, PA, pp. 420–447. American Society for Testing and Materials (1987)
Eason, E.D., Odette, G.R., Nanstad, R.K., et al.: A physically-based correlation of irradiation-induced transition temperature shifts for RPV steels. J. Nucl. Mater. 433(1–3), 240–254 (2013)
Ferreño, D., Serrano, M., Kirk, M., et al.: Prediction of the transition-temperature shift using machine learning algorithms and the plotter database. Metals 12(2), 186 (2022)
Jing, K., Kai, S., Xiaoxi, M., et al.: Research on prediction model of irradiation embrittlement of RPV materials based on artificial neural network. Nucl. Power Eng. 41(6), 92–95 (2020)
Kirk, M.: Summary of work to develop the transition temperature shift equation used in ASTM standard guide e900–15. In: International Review of Nuclear Reactor Pressure Vessel Surveillance Programs, West Conshohocken, PA, pp. 432–456. ASTM International (2018)
Kirk, M., Hashimoto, Y., Nomoto, A.: Application of a machine learning approach based on nearest neighbors to extract embrittlement trends from RPV surveillance data. J. Nucl. Mater. 568, 153886 (2022)
Kolluri, M., Martin, O., Naziris, F., et al.: Structural materias research on parameters influencing the material properties of RPV steels for safe long-term operation of PWR NPPs. Nucl. Eng. Des. 406, 112236 (2023)
Liu, Y.C., Wu, H., Mayeshiba, T., et al.: Machine learning predictions of irradiation embrittlement in reactor pressure vessel steels. NPJ Comput. Mater. 8(1), 85 (2022)
Montáns, F.J., Chinesta, F., Gómez-Bombarelli, R., et al.: Data-driven modeling and learning in science and engineering. Comptes Rendus Mécanique 347(11), 845–855 (2019)
Soneda, N., Nomoto, A.: Characteristics of the new embrittlement correlation method for the Japanese reactor pressure vessel steels. J. Eng. Gas Turbines Power 132(10), 102918 (2010)
Wang, H., Villanueva, W., Chen, Y., et al.: Thermo-mechanical behavior of an ablated reactor pressure vessel wall in a nordic BWR under in-vessel core melt retention. Nucl. Eng. Des. 379, 111196 (2021)
Xu, C., Liu, X., Wang, H., et al.: A study of predicting irradiation-induced transition temperature shift for RPV steels with xgboost modeling. Nucl. Eng. Technol. 53(8), 2610–2615 (2021)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Jin, P., Chen, L., Chen, H., Kong, L., Li, Z. (2024). Machine Learning-Driven Reactor Pressure Vessel Embrittlement Prediction Model. In: Liu, F., Sadanandan, A.A., Pham, D.N., Mursanto, P., Lukose, D. (eds) PRICAI 2023: Trends in Artificial Intelligence. PRICAI 2023. Lecture Notes in Computer Science(), vol 14325. Springer, Singapore. https://doi.org/10.1007/978-981-99-7019-3_9
Download citation
DOI: https://doi.org/10.1007/978-981-99-7019-3_9
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-7018-6
Online ISBN: 978-981-99-7019-3
eBook Packages: Computer ScienceComputer Science (R0)