Strategy to coordinate actions through a plant parameter prediction model during startup operation of a nuclear power plant
2
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
The development of automation technology to reduce human error by minimizing human intervention is accelerating with artificial intelligence and big data processing technology, even in the nuclear field. Among nuclear power plant operation modes, the startup and shutdown operations are still performed manually and thus have the potential for human error. As part of the development of an autonomous operation system for startup operation, this paper proposes an action coordinating strategy to obtain the optimal actions. The lower level of the system consists of operating blocks that are created by analyzing the operation tasks to achieve local goals through soft actor-critic algorithms. However, when multiple agents try to perform conflicting actions, a method is needed to coordinate them, and for this, an action coordination strategy was developed in this work as the upper level of the system. Three quantification methods were compared and evaluated based on the future plant state predicted by plant parameter prediction models using long short-term memory networks. Results confirmed that the optimal action to satisfy the limiting conditions for operation can be selected by coordinating the action sets. It is expected that this methodology can be generalized through future research.
Abstract
The development of automation technology to reduce human error by minimizing human intervention is accelerating with artificial intelligence and big data processing technology, even in the nuclear field. Among nuclear power plant operation modes, the startup and shutdown operations are still performed manually and thus have the potential for human error. As part of the development of an autonomous operation system for startup operation, this paper proposes an action coordinating strategy to obtain the optimal actions. The lower level of the system consists of operating blocks that are created by analyzing the operation tasks to achieve local goals through soft actor-critic algorithms. However, when multiple agents try to perform conflicting actions, a method is needed to coordinate them, and for this, an action coordination strategy was developed in this work as the upper level of the system. Three quantification methods were compared and evaluated based on the future plant state predicted by plant parameter prediction models using long short-term memory networks. Results confirmed that the optimal action to satisfy the limiting conditions for operation can be selected by coordinating the action sets. It is expected that this methodology can be generalized through future research.
참고문헌 (24)
- Stuart Bennett, "The past of pid controllers", Annu. Rev. Control, 25, pp.43~53 (2001)
- Autonomous Control of Nuclear Power Plants, "H. Basher", ~, pp.ORNL (2003), TM–2003[DOI]
- R. E. Uhrig, "Multi-agent-based anticipatory control for enhancing the safety and performance of gen4 NPPs during long-term semiautonomous operation", Prog. Nucl. Energy, 43(1-4), pp.113~120 (2003)
- Richard T. Wood, "An autonomous control framework for advanced reactors", Nuclear Engineering and Technology, 49(5), pp.896~904 (2017), 한국원자력학회
- J. T. Kim, "Development of advanced I&C in nuclear power plants: ADIOS and ASICS", Nucl. Eng. Des, 207(1), pp.105~119 (2001)
- S. J. Lee, "Development of automated operating procedure system using fuzzy colored petri nets for nuclear power plants", Ann. Nucl. Energy, 31(8), pp.849~869 (2004)
- M. Boroushaki, "An intelligent nuclear reactor core controller for load following operations, using recurrent neural networks and fuzzy systems", Ann. Nucl. Energy, 30(1), pp.63~80 (2003)
- S.J. Lee, "Development of an integrated decision support system to aid the cognitive activities of operators in main control rooms of nuclear power plants", 2007 IEEE Symposium on Computational Intelligence in Multi-Criteria Decision-Making, pp.146~152 (2007)
- M. H. Hsieh, "A decision support system for identifying abnormal operating procedures in a nuclear power plant", Nucl. Eng. Des, 249, pp.413~418 (2012)
- 김재민, "Abnormality diagnosis model for nuclear power plants using two-stage gated recurrent units", Nuclear Engineering and Technology, 52(9), pp.2009~2016 (2020), 한국원자력학회[DOI]
- 김종현, "Conceptual design of autonomous emergency operation system for nuclear power plants and its prototype", Nuclear Engineering and Technology, 52(2), pp.308~322 (2020), 한국원자력학회
- 성풍현, "Advanced MMIS Toward Substantial Reduction in Human Errors in NPPs", Nuclear Engineering and Technology, 45(2), pp.125~140 (2013), 한국원자력학회
- Safety and Operational Status of Nuclear Power Plants in Korea, vol. 21, "KINS", ~, pp.KINS (2020), ER-035
- D. Lee, "Algorithm for autonomous power-increase operation using deep reinforcement learning and a rule-based system", IEEE Access ume, 8, pp.196727~196746 (2020)
- J. M. Kim, "Autonomous startup operation for nuclear power plants using a reinforcement learning algorithm", International Symposium on Future I&C for Nuclear Power Plants (2021)
- T. Haarnoja, "Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor", International Conference on Machine Learning (ICML), pp.1861~1870 (2018)
- S. Hochreiter, "Long short-term memory", Neural Comput, 9(8), pp.1735~1780 (1997)
- R. S. Sutton, "Reinforcement Learning: an Introduction" (2018), The MIT Press
- D. Lee, "Comparison of deep reinforcement learning and PID controllers for automatic cold shutdown operation", Energies, 15(8), pp.2834~ (2022)
- J. Bae, "Real-time prediction of nuclear power plant parameter trends following operator actions", Expert Syst. Appl, 186, pp.115848~ (2021)
- KAERI, "Advanced Compact Nuclear Simulator Textbook" (1990)
- Diederik P. Kingma, "Adam: A Method for Stochastic Optimization", arXiv preprint arXiv:1412.6980, ~ (2014)
- D. M. Guisi, "Reinforcement learning with multiple shared rewards", Procedia Comput. Sci, 80, pp.855~864 (2016)
- G. Dulac-Arnold, "Challenges of Real-World Reinforcement Learning", arXiv preprint arXiv:1904.12901, ~ (2019)