Prediction Of Thermal Performance Of Designed Different Obstacles On Absorber Plates In Solar Air Collectors By Support Vector Machine

OpenAlex İngilizce

In this study, energy performance of a new flat plate solarair collector (SAHs) with different obstacles at fin shape and rectangle Type Iand Type II wasinvestigated. The measured parameters were the inlet and outlet temperatures,the absorbing plate temperatures, the ambient temperature, and the solarradiation. Further, the measurements were performed atdifferent values of mass flow rate of air (0.0074, 0.0052, 0.0016 kg/s). The thermal efficiency was calculated based on the measurements Theresults obtained were trained and tested with the support vector machine (SVM) whichis one of the regression analyse methods. 10-fold cross-validation methodwas used to evaluate the regression performance. The best regressionanalysis result was obtained using cubic SVM method in which R2 was0.88 in the Type II air collector. Comparisonbetween predicted and experimental results indicates that the proposed SVMmodel can be used for estimating the efficiency of SAHs with reasonableaccuracy.