Artificial Neural Network Simulation of Energetic Performance for Sorption Thermal Energy Storage Reactors

Sorption thermal heat storage is a promising solution to improve the development of renewable energies and promote rational use energy both for industry households. These systems store through physico-chemical sorption/desorption reactions that are also termed hydration/dehydration. Their introduction market requires assess their performances, usually analysed by numerical simulation overall system. To address this, physical models commonly developed used. However, based on such time-consuming which does not allow yearly simulations. Artificial neural network (ANN)-based models, known computational efficiency, may overcome this issue. Therefore, main objective study investigate an ANN model simulate sorption system, instead using model. The trained experimental results in order evaluate approach actual systems. By recurrent (RNN) Deep Learning Toolbox MATLAB, good accuracy reached, predicted close results. root mean squared error prediction temperature difference during process less than 3K hydration dehydration, maximal being, respectively, about 90K 40K.