PREDICTION OF THERMAL PERFORMANCE OF DESIGNED DIFFERENT OBSTACLES ON ABSORBER PLATES IN SOLAR AIR COLLECTORS BY SUPPORT VECTOR MACHINE

Abstract

In this study, energy performance of a new flat plate solar air collector (SAHs) with different obstacles at fin shape and rectangle Type I and Type II was investigated. The measured parameters were the inlet and outlet temperatures, the absorbing plate temperatures, the ambient temperature, and the solar radiation. Further, the measurements were performed at different values of mass flow rate of air (0.0074, 0.0052, 0.0016 kg/s). The thermal efficiency was calculated based on the measurements The results obtained were trained and tested with the support vector machine (SVM) which is one of the regression analyse methods. 10-fold cross-validation method was used to evaluate the regression performance. The best regression analysis result was obtained using cubic SVM method in which R2 was 0.88 in the Type II air collector. Comparison between predicted and experimental results indicates that the proposed SVM model can be used for estimating the efficiency of SAHs with reasonable accuracy.