Toggle Main Menu Toggle Search

Open Access padlockePrints

Multi-objective Optimisation of Atmospheric Crude Distillation System Operations Based on Bootstrap Aggregated Neural Network Models

Lookup NU author(s): Funmi Osuolale, Dr Jie ZhangORCiD


Full text for this publication is not currently held within this repository. Alternative links are provided below where available.


This paper presents a new methodology for optimising the energy efficiency of a crude distillation unit without trading off the product quality and process throughput. It incorporates the second law of thermodynamics which indicates how well a system is performing compared to the optimum possible performance and hence gives a good indication of the actual energy use of a process. Bootstrap aggregated neural networks are used for enhanced model accuracy and reliability. In addition to the process operation objectives, minimising the model prediction confidence bound is incorporated in multi-objective optimisation to improve the reliability of the optimisation results. The economic analysis of the recoverable energy (sum of internal and external exergy losses) reveals the energy saving potential of the method. The proposed method will aid the design and operation of energy efficient crude distillation columns.

Publication metadata

Author(s): Osuolate FN, Zhang J

Editor(s): Gernaey,KV; Huusom,JK; Gani,R

Publication type: Conference Proceedings (inc. Abstract)

Publication status: Published

Conference Name: 12th International Symposium on Process Systems Engineering and the 25th European Symposium on Computer Aided Process Engineering

Year of Conference: 2015

Pages: 671-676

Print publication date: 27/05/2015

Online publication date: 10/06/2015

Acceptance date: 14/02/2015

ISSN: 1570-7946

Publisher: Elsevier


DOI: 10.1016/B978-0-444-63578-5.50107-9

Library holdings: Search Newcastle University Library for this item

Series Title: Computer-Aided Chemical Engineering

ISBN: 9780444634290