Modelling and Optimal Operation of a Crude Oil Hydrotreating Process with Atmospheric Distillation Unit Utilising Stacked Neural Networks

Muhsin, WAS; Zhang, J

doi:10.1016/B978-0-444-63965-3.50415-3

Modelling and Optimal Operation of a Crude Oil Hydrotreating Process with Atmospheric Distillation Unit Utilising Stacked Neural Networks

Lookup NU author(s): Wissam Muhsin, Dr Jie Zhang ORCiD

Downloads

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

Abstract

Data-driven modelling and optimisation of a crude distillation process with crude oilhydrotreating (HDT) using stacked neural network are presented in this paper. HDT ofcrude oil is a new process that has not been considered widely in the literature. Processoptimisation should be conducted to improve the operation efficiency of HDT process. Inthis paper, stacked neural networks are used to model crude oil HDT process and toimprove model prediction accuracy and reliability. A crude oil HDT process with crudedistillation unit (CDU) simulated using Aspen HYSYS software is used as a case study.The application results show that accurate models for crude oil HDT process with CDUcan be developed from process operational data using stacked neural networks. One ofthe most important findings from this paper is that stacked networks can generate moreaccurate and reliable predictions than single networks, which in turn leads to reliableoptimisation results. Goal-attainment method for multi-objective optimisation is used.The obtained optimisation results are validated on Aspen HYSYS simulation and theeffectiveness of the proposed scheme is demonstrated.