Abstract
The goal of emergency operation in nuclear power plants (NPPs) is to ensure the integrity of reactor core as well as containment building under undesired initiating events. In this operation, operators perform the situation awareness, the confirmation of automatic actuation of safety systems, and the manual operations to cool down the reactor according to the operating procedures. This study aims to develop an autonomous operation agent that can reduce the pressure and temperature of primary system. The agent applies the Soft Actor-Critic (SAC) algorithm, which is a kind of deep reinforcement algorithm for optimizing stochastic actions. With the SAC, the agent is trained to find actions to meet the pressure and temperature curve criteria and the cooling rate. In addition, the test using a compact nuclear simulator demonstrates that the agent can cool down the reactor by manipulating the necessary systems in compliance with the constraints.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wood, R.T., Neal, J.S., Ray Brittain, C., Mullens, J.A.: Autonomous control capabilities for space reactor power systems. In: AIP Conference Proceedings, vol. 699, no. 1. American Institute of Physics (2004)
Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85–117 (2015)
Lee, D., Seong, P.H., Kim, J.: Autonomous operation algorithm for safety systems of nuclear power plants by using long-short term memory and function-based hierarchical framework. Ann. Nucl. Energy 119, 287–299 (2018)
Lee, D., Arigi, A.M., Kim, J.: Algorithm for autonomous power-increase operation using deep reinforcement learning and a rule-based system. IEEE Access 8, 196727–196746 (2020)
Arulkumaran, K., Deisenroth, M.P., Brundage, M., Bharath, A.A.: Deep reinforcement learning: a brief survey. IEEE Signal Process. Mag. 34(6), 26–38 (2017)
Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, pp. 1861–1870 (2018)
Park, J., Jung, W.: A study on the systematic framework to develop effective diagnosis procedures of nuclear power plants. Reliab. Eng. Syst. Saf. 84(3), 319–335 (2004)
KHNP: APR1400 Design Description. Korea Hydro & Nuclear Power Co., Ltd. (2014)
KAREI: Advanced Compact Nuclear Simulator Textbook. Nuclear Training Center in Korea Atomic Energy Research Institute (1990)
Acknowledgments
This work was supported in part by the Basic Science Research Program through the National Research Foundation of Korea (NRF), funded by the Ministry of Science, ICT & Future Planning under Grant N01190021-06, and in part by the Korean Government, Ministry of Science and ICT under Grant NRF-2018M2B2B1065651.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Lee, D., Kim, J. (2021). Autonomous Emergency Operation of Nuclear Power Plant Using Deep Reinforcement Learning. In: Ahram, T.Z., Karwowski, W., Kalra, J. (eds) Advances in Artificial Intelligence, Software and Systems Engineering. AHFE 2021. Lecture Notes in Networks and Systems, vol 271. Springer, Cham. https://doi.org/10.1007/978-3-030-80624-8_65
Download citation
DOI: https://doi.org/10.1007/978-3-030-80624-8_65
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-80623-1
Online ISBN: 978-3-030-80624-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)