摘要详情

ID / 提交时间

88 / 2024-08-28 16:00:21

标题

Simulation and Solution of Nuclear Reactor Accident Conditions Based on Latin Hypercube Sampling and Physics-Informed Neural Networks

关键字

nuclear reactor accidents, LOCA, LHS, PINNs

主题及专题

TRACK 5: NUCLEAR ENGINEERING

状态

全文录用

作者

Yufei Xie / School of Automation, Wuhan University of Technology；Sino-German College of Intelligent Manufacturing, Shenzhen Technology University

Wenlin Wang / Sino-German College of Intelligent Manufacturing； Shenzhen Technology University

Guohua Wu / Sino-German College of Intelligent Manufacturing； Shenzhen Technology University

Yang Yu / Nuclear Power Institute of China；National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology

Ping An / Nuclear Power Institute of China

Fengchen Guo / Nuclear Power Institute of China

Haichuan Zhang / Sino-German College of Intelligent Manufacturing； Shenzhen Technology University

Shengfeng Luo / Sino-German College of Intelligent Manufacturing； Shenzhen Technology University

摘要

In Loss of Coolant Accident (LOCA) scenarios, the reactor core temperature may rise sharply, potentially causing fuel damage and radioactive material release. This paper proposes a method combining Latin Hypercube Sampling (LHS) and Physics-Informed Neural Networks (PINNs) for simulating and solving LOCA conditions in nuclear reactor accidents. By generating high-quality parameter space training samples using LHS and training the PINNs model under physical constraints, the method effectively simulates the complex fluid behavior under LOCA conditions. Evaluation results of the model show an average absolute error (MAE) of 0.054, a root mean square error (RMSE) of 0.132, and a coefficient of determination (R²) of 0.85, validating the effectiveness of the proposed method in complex conditions.