Application of an artificial neural network for modelling the thermal dynamics of a building's space and its heating system

Gouda, M. M., Danaher, Sean and Underwood, Chris (2002) Application of an artificial neural network for modelling the thermal dynamics of a building's space and its heating system. Mathematical and Computer Modelling of Dynamical Systems, 8 (3). pp. 333-344. ISSN 1387 3954

Full text not available from this repository. (Request a copy)

Abstract

Artificial neural networks (ANNs) have been used for modelling the thermal dynamics of a building's space, its water heating system and the influence of solar radiation. A multi-layer feed-forward neural network, using a Levenberg-Marquardt backpropagation-training algorithm, has been applied to predict the future internal temperature. Real weather data for a number of winter months, together with a validated building model (based on the building constructions data), were used to train the network in order to generate a mapping between the easily measurable inputs (outdoor temperature, solar irradiance, heating valve position and the building indoor temperature) and the desired output, i.e., the predicted indoor temperature. The objective of this work was to investigate the potential of using an ANN with singular value decomposition method (SVD) to predict the indoor temperature to shut down the heating system controller early for saving the energy consumption for heating inside the building.

Item Type:	Article
Uncontrolled Keywords:	Artificial neural networks, heating control, prediction, singular value decomposition
Subjects:	K200 Building
Department:	Faculties > Engineering and Environment > Mechanical and Construction Engineering
Depositing User:	Becky Skoyles
Date Deposited:	12 Feb 2015 12:49
Last Modified:	12 Oct 2019 22:55
URI:	http://nrl.northumbria.ac.uk/id/eprint/19435

Downloads