A neural network model for analysis and optimization of processes

Abstract

Artificial neural networks based on a feedforward architecture and trained bv the backpropagation technique were applied to analysis and improvement of a separation process. Various neural network topologies have been tested and compared. The Powell method was used to train the network by minimising the sum of squares of residuals as well as GDR algorithm. The performance of the network have been analysed. The obtained results show the applicability the neural networks structure with and without hidden layer. These results ilustrate the feasibility of using a neural network as a data analyser and as an optimisation tool.