Experimental Analysis of the Thermoelectric Cooler Performance using Artificial Neural Network

Abstract

this paper presents the results of a comparison between the experimental work results and artificial neural network for the analysis of the thermoelectric cooler performance. It is implemented using Matlab using the real data obtained from the experimental works. The artificial intelligence techniques are intensively used as an alternatives to classical techniques to model real systems. The experimental work carried out to investigate the performance of the thermoelectric cooler under the effect of the pulsating forced convective air flow at different rates of input electrical power in a rectangular cross -sectional channel. The experiments were performed over a range of pulsating flow frequencies at a constant mass flow rate. The results showed that the thermoelectric cooler performance is strongly affected by pulsation frequency at different values of input power values. Comparing the experimental results with the neural network model it showed a good matching.