부산대학교 도서관

To effectively monitor the variety of distributions of neutron flux, fuel power or temperatures in thereactor core, usually the ex-core and in-core neutron detectors are employed. The thermocouples fortemperature measurement are installed in the coolant inlet or outlet of the respective fuel assemblies. Itis necessary to reconstruct the measurement information of the whole reactor position. However, thereading of different types of detector in the core reflects different aspects of the 3D power distribution. The feasibility of reconstruction the core three-dimension power distribution by using different combinations of in-core, ex-core and thermocouples detectors is analyzed in this paper to synthesize theuseful information of various detectors. A comparison of multilayer perceptron (MLP) network and radialbasis function (RBF) network is performed. RBF results are more extreme precision but also moresensitivity to detector failure and uncertainty, compare to MLP networks. This is because that localizedneural network could offer conservative regression in RBF. Adding random disturbance in trainingdataset is helpful to reduce the influence of detector failure and uncertainty. Some convolution neuralnetworks seem to be helpful to get more accurate results by use more spatial layout information, thoughrelative researches are still under way