Author Type

Graduate Student

Date of Award

1996

Document Type

Thesis

Publication Status

Version of Record

Submission Date

October 2026

Thesis/Dissertation Advisor [Chair]

Zilouchian, Ali

Abstract

Inferential analysis using neural networks technology is being proposed for the Ras Tanura Refinery crude fractionation section. Plant data for a three month operation period is analyzed in order to construct a neural network model with backpropagation training algorithm. The proposed neural network model can predict various properties associated with crude oil products. The simulation results for modeling Naphtha 95% cut point and Naphtha Reid vapor pressure properties are analyzed. A fuzzy neural network model is also proposed that takes into account the fuzziness in both process variables and the corresponding product quality parameter. The training algorithm is derived based on the backpropagation technique. The results of the proposed study can ultimately enhance the on-line prediction of crude oil product quality parameters for crude fractionation processes in the Ras Tanura Oil Refinery.

Extent

116 p.

Comments

College of Engineering and Computer Science|FAU Electronic Theses and Dissertations Collection|Thesis (M.S.)--Florida Atlantic University, 1996.|College of Engineering and Computer Science

Identifier

FADT15302

Format

pdf

Download

Share

COinS