Applications of artificial neural-networks for energy systems

Artificial neural networks offer an alternative way to tackle complex and i ll-defined problems. They can learn from examples, are fault tolerant in th e sense that they are able to handle noisy and incomplete data, are able to deal with non-linear problems, and once trained can perform predictions an d generalisations at high speed. They have been used in diverse application s in control, robotics, pattern recognition, forecasting, medicine, power s ystems, manufacturing, optimisation, signal processing, and social/psycholo gical sciences. They are particularly useful in system modelling, such as i n implementing complex mapping and system identification. This paper presen ts various applications of neural networks in energy problems in a thematic rather than a chronological or any other way. Artificial neural networks h ave been used by the author in the field of solar energy; for modelling and design of a solar steam generating plant, for the estimation of a paraboli c-trough collector's intercept factor and local concentration ratio and for the modelling and performance prediction of solar water-heating systems. T hey have also been used for the estimation of heating-loads of buildings, f or the prediction of air flows in a naturally ventilated test room and for the prediction of the energy consumption of a passive solar building. In al l such models, a multiple hidden-layer architecture has been used. Errors r eported when using these models are well within acceptable limits, which cl early suggests that artificial neural-networks can be used for modelling in other fields of energy production and use. The work of other researchers i n the field of energy is also reported. This includes the use of artificial neural-networks in heating, ventilating and air-conditioning systems, sola r radiation, modelling and control of power-generation systems, load-foreca sting and refrigeration. (C) 2000 Elsevier Science Ltd. All rights reserved .