Steam generator is the key equipment in the secondary loop system of nuclear reactor, and its internal flow and heat transfer directly affect the efficiency of nuclear power conversion. The high precision numerical model is an effective method to analyze the 3D temperature field in the steam generator, but the computational efficiency of the traditional high resolution numerical model can not meet the needs of practical applications. In order to improve the computational efficiency, a reduced order model of heat transfer problem is constructed by using the Proper Orthogonal Decomposition (POD) decomposition method. The model takes the typical numerical solutions as samples, and then establishes the mapping relationship between the boundary conditions and the reduced order system to realize the rapid reconstruction of the three-dimensional temperature field. The test examples of steam generator heat transfer tube show that compared with the full-order model, this reduced order model can achieve 3~4 orders of magnitude acceleration effect.

Steam generator,Flow heat transfer,Model reduction,Accelerated calculation,Neural network