A hybrid model formulation for a distillation column and the on-line optimisation study

Wavelet-based neural networks are employed to simplify the model of a disti llation column. The idea is to use a simplified hybrid model of the column for the purpose of on-line optimisation of the unit. The hybrid model consi sts of a neural network part plus a mechanistic model part. This highly sim plifies the model while preserving the accuracy of the model together with the availability of the required internal variables of the model. The emplo yed wavelet-based neural networks (i.e. wave-nets) are briefly explained. T hen, results of the approximation capability of the wave-net model and the on-line optimisation of the column with the aid of the hybrid model are pre sented. (C) 1999 Elsevier Science Ltd. All rights reserved.