With the development of economy, people's living standards improving, people growing awareness of protecting environment and demanding for electricity, they prompt our country to increase nuclear power plants. At the same time, people propose higher of the safety and reliability on nuclear power equipment. Reactor coolant system (RCS) in the nuclear power plant directly affects whether the core of nuclear power plant heat can be smooth exported and radioactive can be inclusive, which play an important role of the security of the entire nuclear power plant. So, it is great significance to analysis to RCS.

In the paper, RCS has been analyzed and typical fault of RCS have been set through PCTRAN simulation software. On this basis, this paper is access to all the typical fault characteristic data. Two kinds of neural network radial basis function (RBF) and fuzzy neural network (FNN) method are used for fault diagnosis and comparative analysis. LOCA, single pump fault, loss of flow accident are set for simulation experiment authentication. Simulation experiment in many parameters shows that BP network's hidden layer nodes is less than RBF neural network, but convergence rate of BP network is faster; BP neural network for accuracy of fault diagnosis is higher than RBF;FNN for fault identification is faster than neural networks.

Key words: nuclear safety; reactor coolant system; fault analysis; neural network


Research on Fault Diagnosis of Reactor Coolant Accident in Nuclear Power Plant Based on Radial Basis Function and Fuzzy Neural Network

Division / Sponsors: 
Power Division & Nuclear Engineering Division (NED)

Power Conference
Paper Proceedings: https://asmedigitalcollection.asme.org/POWER/POWER2020/volume/83747

International Conference on Nuclear Engineering
Paper Proceedings: https://asmedigitalcollection.asme.org/ICONE/ICONE2020/volume/83761

POWER-ICONE - Virtual Conference

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.