Optimization of inlet part of a microchannel ceramic heat exchanger using surrogate model coupled with genetic algorithm

High temperature resistance and corrosion resistance make ceramic materials available for heat exchangers operating under high temperature or harsh chemical conditions. And the importance of the effect of flow maldistribution on thermal-hydraulic performance of heat exchangers has been demonstrated by a lot of researches. In this work, the nonuniformity of fluid flow is focused on to improve the performance of a microchannel ceramic heat exchanger. The inlet part of a microchannel ceramic heat exchanger is optimized using surrogate model coupled with genetic algorithm. Specifically, 30 sample points are designed by Latin hypercube sampling method and calculated by computational fluid dynamics. Radial basis neural network is established with the sample data and employed to predict the specific fluid flow distribution within design space as a surrogate model. Specifically, the surrogate model predicts the specific flow distribution instead of a single target value of nonuniformity in previous surrogate model. The results indicate that such a method has a significant advantage over the previous surrogate model. The genetic algorithm is implemented to search for the optimal point. The nonuniformity of fluid flow is reduced by 68.2% and pressure drop is increased by 6.6% by the optimization, which means the uniformity of fluid flow in the heat exchanger is improved significantly with just a little cost of pressure drop.