Conventional regression methods are generally unable to analyse extremely complicated processes involving a considerable number of independent variables with poorly understood interaction. These methods use a defined equation for which the parameters of this equation have to be determined. It is however questionable whether any arbitrarily chosen equation is the best. This study aims to implement the powerful neural network architecture for a comprehensive data bank. The HTRI data bank contains a large and unique set of experimental data for cooling water fouling. Only a selection of the data bank is being used at the present time, due to the large number of independent variables investigated in this experimental study.
M. R. Malayeri and H. Müller-Steinhagen, "Analysis of Fouling Data Based on Prior Knowledge" in "Heat Exchanger Fouling and Cleaning: Fundamentals and Applications", Paul Watkinson, Hans Müller-Steinhagen, and M. Reza Malayeri Eds, ECI Symposium Series, Volume RP1 (2003). http://dc.engconfintl.org/heatexchanger/20