Development of an AI-based remaining trip time prediction system for nuclear power plants
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
In abnormal states of nuclear power plants (NPPs), operators undertake mitigation actions to restore a normal state and prevent reactor trips. However, in abnormal states, the NPP condition fluctuates rapidly, which can lead to human error. If human error occurs, the condition of an NPP can deteriorate, leading to reactor trips. Sudden shutdowns, such as reactor trips, can result in the failure of numerous NPP facilities and economic losses. This study develops a remaining trip time (RTT) prediction system as part of an operator support system to reduce possible human errors and improve the safety of NPPs. The RTT prediction system consists of an algorithm that utilizes artificial intelligence (AI) and explainable AI (XAI) methods, such as autoencoders, light gradient-boosting machines, and Shapley additive explanations. AI methods provide diagnostic information about the abnormal states that occur and predict the remaining time until a reactor trip occurs. The XAI method improves the reliability of AI by providing a rationale for RTT prediction results and information on the main variables of the status of NPPs. The RTT prediction system includes an interface that can effectively provide the results of the system.
Abstract
In abnormal states of nuclear power plants (NPPs), operators undertake mitigation actions to restore a normal state and prevent reactor trips. However, in abnormal states, the NPP condition fluctuates rapidly, which can lead to human error. If human error occurs, the condition of an NPP can deteriorate, leading to reactor trips. Sudden shutdowns, such as reactor trips, can result in the failure of numerous NPP facilities and economic losses. This study develops a remaining trip time (RTT) prediction system as part of an operator support system to reduce possible human errors and improve the safety of NPPs. The RTT prediction system consists of an algorithm that utilizes artificial intelligence (AI) and explainable AI (XAI) methods, such as autoencoders, light gradient-boosting machines, and Shapley additive explanations. AI methods provide diagnostic information about the abnormal states that occur and predict the remaining time until a reactor trip occurs. The XAI method improves the reliability of AI by providing a rationale for RTT prediction results and information on the main variables of the status of NPPs. The RTT prediction system includes an interface that can effectively provide the results of the system.
참고문헌 (14)
- K. H. Yoo, "Smart support system for diagnosing severe accidents in nuclear power plants", Nucl. Eng. Technol, 50(4), pp.562~569 (2018)
- H. J. Kim, "Development of a diagnostic algorithm for abnormal situations using long short-term memory and variational autoencoder", Ann. Nucl. Energy, 153, pp.108077~ (2021)
- J. H. Park, "A reliable intelligent diagnostic assistant for nuclear power plants using explainable artificial intelligence of GRUAE, LightGBM and SHAP", Nucl. Eng. Technol, 54(4), pp.1271~1287 (2022)
- H. J. Kim, "Long-term prediction of safety parameters with uncertainty estimation in emergency situations at nuclear power plants", Nucl. Eng. Technol, 55(5), pp.1630~1643 (2023)
- H. S. Jo, "Prediction of reactor trip variables using LSTM with attention mechanism in abnormal situations", International Symposium on Future I&C for Nuclear Power Plants (2021)
- M. A. Kramer, "Nonlinear principal component analysis using autoassociative neural networks", ALCHE J, 37(2), pp.233~243 (1991)
- G. Ke, "LightGBM : a highly efficient gradient boosting decision tree", Adv. Neural Inf. Process. Syst, 30, pp.3149~3157 (2017)
- D. Gunning, "DARPA’s explainable artificial intelligence(XAI)program", AI Mag, 40(2), pp.44~58 (2019)
- V. A. Dev, "Formation lithology classification using scalable gradient boosted decision trees", Comput. Chem. Eng, 128(2), pp.392~404 (2019)
- S. M. Lundberg, "A unified approach to interpreting model predictions", Adv. Neural Inf. Process. Syst, 30, pp.4765~4774 (2017)
- Equipment and Performance Upgrade of Compact Nuclear Simulator, "J. C. Park", KAERI, ~, pp.KAERI (1999), RR1967[DOI]
- M. Kuhn, "Applied Predictive Modeling" (2013), Springer
- S. García, "Data Preprocessing in Data Mining" (2015), Springer
- Y. G. Kim, "Consideration on the use of explainable AI in operator support system", Korea Nuclear Society Virtual Autumn Meeting (2020)