Open AccessResearch on Diagnosis of Loss of Flow Accidents in Nuclear Reactor Coolant System
Author(s) -
Liming Qin,
Xiaohua Yang,
Jie Liu,
Jian Ma
Publication year - 2022
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2242/1/012032
Subject(s) - nuclear power plant , loss of coolant accident , coolant , reliability engineering , nuclear power , counterfactual thinking , nuclear reactor , bayesian network , computer science , fault (geology) , nuclear engineering , engineering , mechanical engineering , artificial intelligence , ecology , philosophy , physics , epistemology , seismology , nuclear physics , biology , geology
The reactor coolant system is one of the most important systems in a nuclear power plant. The safe and stable operation of the reactor coolant system is related to the safety of the nuclear power plant. With the rapid development of nuclear power technology, it is particularly important to ensure the safety of nuclear power plants. This paper takes the third-generation reactor AP1000 as the research object, firstly analyzes the typical accidents of the coolant system, and establishes a three-layer fault model, and then introduces the counterfactual reasoning method to take the Loss of Flow Accident as an example to identify the accident, and compares it with the traditional data-driven The Bayesian network diagnosis method was compared with the Bayesian network diagnosis method, and finally the accident was diagnosed by the simulation software Pctran. The results show that the method can accurately identify the fault and is better than the Bayesian method, which can provide decision support for accident handling and ensure the safety of the reactor.