Application of an Artificial Intelligence and Neural networks for Modeling the Thermal Dynamics of a Water tank and Its Heating system using Home Central Air conditioners

Abstract

Artificial Intelligence and Neural networks (AI&NN) have been used for modeling the thermal dynamics of a water tank, its heating system with the help of central air conditioners. A temperature sensor, multilayer feed forward neural network, using a error back propagation training algorithm, has been applied to predict the water tank temperature and hot air temperature. Real weather data for a number of winter months, together with a validated central air conditioners model (based on the building central air conditioners), were used to train the network in order to generate a mapping between the easily measurable inputs (hot air temperature, water tank temperature, heating valve position) and the desired output. I.e. the predicted hot water temperature. The objective of this work was to investigate the potential of using an artificial intelligence and neural networks with singular value decomposition method (SVD) to predict the Hot water tank temperature to shut down the central air conditioners hot air temperature sensor. Early for checking the heat of water inside the manufactured water tank.

Key Words Artificial Intelligence and neural networks, singular value decomposition, Hot air temperature sensor, water tank temperature sensor, prediction.