Modeling the total heat transfer coefficient of a nuclear research reactor cooling system by different methods

Abstract

In this work, the thermal model of Triga Mark-II Nuclear research reactor working at Istanbul Technical University (ITU) Energy Institute was created. Thermal model includes mathematical equations expressing the change of water inlet-outlet temperatures of reactor tank, heat exchanger and cooling tower depending on time. By using the thermal model, the mass flow rates of the first and second cooling circuits that can affect the power of the reactor's cooling system were examined. At the same time, an equation based on NTU was generated to estimate the total heat transfer coefficient. To add originality and innovation to the study, the total heat transfer coefficient was modeled using Machine Learning Algorithms (Multilayer Perceptron, Support Vector Machine, M5P Model Tree). Model data obtained by utilizing the thermal model and machine learning were compared. As a result, the mass flow rate at which the reactor works efficiently was determined as 6.57–8.5 kg/h for the 1st cooling circuit and 11.5–13 kg/h for the 2nd cooling circuit. SVM (Puk Kernel) is the method with the least error (RMSE: 0.223) among NTU equation, Thermal model and Machine learning algorithms.