Comparative study of modelling the thermal efficiency of a novel straight through evacuated tube collector with MLR, SVR, BP and RBF methods

Abstract

Data-based methods are useful for accurate modelling of solar thermal systems. In this work, several artificial neural network (ANN) techniques are proposed to predict the thermal performance of an all-glass straight through evacuated tube solar collector. These are compared to support vector regression analysis. Extensive experimental data sets were collected for training the ANN models. Solar radiation intensity, ambient temperature, wind speed, mass flow rate and collector inlet temperature were selected as the input layer to predict the thermal efficiency of the solar collector. The prediction precision of the ANN models was compared to the multiple linear regression and support vector regression model using different criteria. The Radial Basis Function (RBF) neural network method gave the best prediction accuracy followed by the Back Propagation (BP) model. The sensitivity of the model to changes in the input variables (solar radiation intensity, collector inlet temperature, fluid flow rate and wind speed) was also investigated showing the largest dependency on solar radiation.