Predicting Liquid-Vapor (LV) composition at distillation column

Abstract

This paper will present the development of nonlinear model of distillation column using neural networks approach. The model is accomplished in Nonlinear Auto Regressive with exogenous input (NARX) structure.This distillation column has two input and two output variables. The input variables are heat duty on the reboiler (Qr), and reflux flowrate (L), while the output variables are mole fraction of distillate (Xd) and molefraction bottm product (Xb). The training as well as validation data were generated using Amplitude Pseudo Random Binary Signal (APRBS) as excitation signal. The structure of neaural networks is feedforwardnetworks, which consists of three layers: input, hidden and output layer. Levenberg-Marquardt algorithm is used as learning algorithm to adjust the weight matrices of the networks. The results show that NN softsensor base on flow rate correlation is easy to build, fast response, no need special instrumentations, better of reliability compare to analyzer reliability, cheaper, low operational cost, low maintenance cost, and has goodRoot Mean Square Error (RMSE).

Keywords

• NN sot senspr
• predicting LV-composition
• distillation column