Simulation and optimization of pulsating heat pipe flat-plate solar collectors using neural networks and genetic algorithm: a semi-experimental investigation

This research study presents an investigation on the behavior of a Pulsating Heat Pipe Flat-Plate Solar Collector (PHPFPSC) by artificial neural network method and an optimization of the parameters of the collector by genetic algorithm. In this study, several experiments were performed to study the effects of various evaporator lengths, filling ratios, inclination angles, solar radiation, and input chilled water temperature between 9:00 A.M. to 5:00 P.M., and the output temperature of the water tank, which was the output of the system, was also measured. According to the input and output information, multilayer perceptron neural network was trained and used to predict the behavior of the system. A two-layer neural network with a unipolar sigmoid activation function and a 6-20-1 structure was obtained as the network with the highest performance. The trained network was validated with experimental data and used to evaluate the objective function to maximize the thermal efficiency of the system. Also, a continuous genetic algorithm was developed to optimize the system efficiency. An initial population size of 700 and a mutation rate of 4 % were obtained as the best values. Furthermore, at the evaporator length of 1.08, filling ratio of 56.94 %, and inclination angle of 25.01, the maximum thermal efficiency of the system was 61.4 %. The effect of the input water temperature of the water tank on the optimal values of optimization variables was examined. The results indicated that an increase in the temperature of the input water of the water tank leads to a decrease in the thermal efficiency of the system. A comparison of the results of this study with previous research indicates that the use of heat pipes in solar collectors can increase the efficiency of solar collectors up to 4 %. According to the results, the use of neural networks, as an input–output model, is a proper way to predict the complicated behavior of these systems. Also, genetic algorithm is an efficient method for solving non-linear optimization problems.