ICT2014 Abstracts

 A geometrical shape factor was investigated for optimum thermoelectric properties of a novel thermoelectric module. The cooling power, electrical energy consumption and coefficient of performance were analysed using simulation with different current values passing though thermoelectric elements for varying temperature differentiation between both sides. The dramatic increase in the cooling power density was obtained since it is inversely proportional to the length of thermoelectric legs. An artificial neural network model for each thermoelectric property was also developed using input-output relations. Prediction of performance of thermoelectric cooling material with artificial neural network was also carried out using simulation results obtained from finite element method as a training data. A total of 357 input vectors for thermoelectric properties obtained from the 4 TEC modules modelled using the FEM analysis were available in the training set to a back propagation neural network. The models including the shape factor have a good prediction capability and agreement with simulation results [1]. The correlation of the models was found to be 99% and overall prediction error was in the range of 0.299 and 0.015 which is within acceptable limits. The simulations and predictions results were compared with the experimental data obtained from a prototype TEC module. These results will be presented.

[1] N. Derebasi, F. Guldiken, O. Caylak, H. Kilic¹, E. N. Ozmutlu, Proceedings of the Second International Conference on Water, Energy and the Environment, paper 314, Kusadası, Turkey  September, 2013,