Optimization of plate-fin heat exchanger performance for heat dissipation of thermoelectric cooler

A plate-fin heat sink is usually used for the hot side of thermoelectric coolers. The plate-fin heat sink should be optimized to improve its heat dissipation capability and eventually elevate the thermoelectric cooler performance. In this paper, a heat dissipation model of the thermoelectric cooler hot side with a plate-fin sink is established, to explore the performances of the plate-fin sink with two types of fins (rectangular and V-type), two convective conditions (lateral and vertical) and three arrangements (single-row, double-row aligned, and double-row staggered). The results show that under vertical jet conditions, double-row aligned rectangular fins have the best heat dissipation capability for the thermoelectric cooler hot side. In order to optimize the fin geometry and maximize its overall performance, a multi-objective optimization of the fins was performed using a machine learning approach based on artificial neural networks (ANN) and non-dominated sorting genetic algorithm (NSGA-ІІ). The corresponding Pareto front is obtained and the technique for order preference by similarity to ideal solution (TOPSIS) method is applied to take the point. Compared with the base case at the same mass flow rate, the fins designed by this method resulted in a 23.3 % reduction in the mean temperature of the hot side.