Artificial neural networks in modelling the Heat-up response of a solar steam generating plant

Abstract

An experimental solar steam generator, consisting of a parabolic trough collector, a high pressure steam circulation circuit, and a suitable flash vessel has been constructed and tested with respect to establishing its thermodynamic performance during heat-up. Preliminary tests demonstrated that the heat-up system response, and hence the heat-up energy requirement has a marked effect on performance. The most important parameters affecting this response are the dimensions, the inventory of the flash vessel, and the prevailing environmental conditions. Experimental data were obtained and used to train an artificial neural network in order to implement a mapping which may be useful to system designers. The trained network predicted well the response of the system, as indicated by an obtained statistical R-squared value of 0.999 and a maximum deviation between predicted and actual values confined to less than 3.9%. This degree of accuracy is acceptable in the design of such systems. This result is even more important, having in mind the fact that the system was tested during its heat-up, under transient conditions, which make it very difficult to model analytically.