Performance prediction of a solar thermal energy system using artificial neural networks

This paper describes in details an application of artificial neural networks (ANNs) to predict the performance of a solar thermal energy system (STES) used for domestic hot water and space heating application. Experiments were conducted on the STES under a broad range of operating conditions during different seasons and Canadian weather conditions in Ottawa, over the period of March 2011 through December 2012 to assess the system performance. These experimental data were utilised for training, validating and testing the proposed ANN model. The model was applied to predict various performance parameters of the system, namely the preheat tank stratification temperatures, the heat input from the solar collectors to the heat exchanger, the heat input to the auxiliary propane-fired tank, and the derived solar fractions. The back-propagation learning algorithm with two different variants, the Levenberg–Marguardt (LM) and scaled conjugate gradient (SCG) algorithms were used in the network. It was found that the optimal algorithm and topology were the LM and the configuration with 10 inputs, 20 hidden and 8 output neurons/outputs, respectively. eheat tank temperature and solar fraction predictions agreed very well with the experimental values using the testing data sets. The ANNs predicted the preheat water tank stratification temperatures and the solar fractions of the STES within less that ±3% and ±10% errors, respectively. sults confirmed the effectiveness of this method and provided very good accuracy even when the input data are distorted with different levels of noise. Moreover, the results of this study demonstrate that the ANN approach can provide high accuracy and reliability for predicting the performance of complex energy systems such as the one under investigation. Finally, this method can also be exploited as an effective tool to develop applications for predictive performance monitoring system, condition monitoring, fault detection and diagnosis of STES.