Deakin University

File(s) under permanent embargo

Prediction interval-based neural network modelling of polystyrene polymerization reactor - a new perspective of data-based modelling

conference contribution
posted on 2023-10-26, 04:23 authored by Anwar HosenAnwar Hosen, Abbas KhosraviAbbas Khosravi, Saeid Nahavandi, Douglas CreightonDouglas Creighton
In this paper, prediction interval (PI)-based modelling techniques are introduced and applied to capture the nonlinear dynamics of a polystyrene batch reactor system. Traditional NN models are developed using experimental datasets with and without disturbances. Simulation results indicate that traditional NNs cannot properly handle disturbances in reactor data and demonstrate a poor forecasting performance, with an average MAPE of 22% in the presence of disturbances. The lower upper bound estimation (LUBE) method is applied for the construction of PIs to quantify uncertainties associated with forecasts. The simulated annealing optimization technique is employed to adjust NN parameters for minimization of an innovative PI-based cost function. The simulation results reveal that the LUBE method generates quality PIs without requiring prohibitive computations. As both calibration and sharpness of PIs are practically and theoretically satisfactory, the constructed PIs can be used as part of the decision-making and control process of polymerization reactors. © 2014 The Institution of Chemical Engineers.



2041 - 2051


San Francisco, California

Start date


End date





Also published in Chemical Engineering Research and Design v.92, 2014 p.2041-2051.

Publication classification

E1 Full written paper - refereed; E Conference publication

Copyright notice

2014, Elsevier

Title of proceedings

WCECS 2012 : Proceedings of the 2012 World Congress on Engineering & Compuer Science