Analysis of neural networks on the basis of vapour-pressure curves of n-fatty alcohols

In this paper the use of neuronal networks according to the backpropagation-error-algorithm for the description of the vapour-pressure curves of fatty alcohols is reported. The used methodology, won experiences as well as the achieved results are presented. An essential finding of this study is that neuronal networks present a very good tool for the mathematical description of functions with nonlinear characteristics. Thus, simplified mathematical models of chemical apparatus can be developed on the basis of existing experimental data. They can be used subsequently for process control and optimization.