Prediction of the performance of a solar thermal energy system using adaptive neuro-fuzzy inference system

Abstract

This study investigates the applicability of adaptive neuro-fuzzy inference system (ANFIS) approach for predicting the performance parameters of a solar thermal energy system (STES). Experiments were conducted on the STES during the summer season and for different Canadian weather conditions in Ottawa. The experimental data were used for training and testing the ANFIS network model. The model was then optimised. The predicted values were found to be in very good agreement with the experimental values with mean relative error less than 0.18% and 3.26% for the preheat tank stratification temperatures and the solar fractions, respectively. The results demonstrate that the ANFIS approach can provide high accuracy and reliability for predicting the performance of thermal energy systems.