Analyzing the Performance of Integrated Collector Storage Solar Water Heater using Neuronal Approach

Abstract

One way to directly benefit from solar energy is through solar thermal systems that produce hot water. These systems function similarly to greenhouses, where sun rays are absorbed by absorbers and then used to reheat fluid that flows through a heating device. Ongoing research aims to improve the efficiency of these systems to achieve more effective models. A news method for data processing and modeling is the neural method, which operates similarly to biological neural networks. This technique allows for accurate models with a minimal number of parameters and can process even nonlinear and multivariable phenomena by learning from representative experimental data. This work aims to develop a strategy based on artificial neural networks to calculate the relevant parameters of a solar system and characterize a solar water heater, specifically focusing on the self-storage sensor that converts sunlight into thermal energy. By embracing the potential of neural networks in solar technology, this initiative not only seeks to refine parameter calculations but also to elevate the overall operational performance of solar water heaters, contributing to the ongoing advancement of sustainable energy solutions.