Abstract
A debutanizer column is an integral part of any petroleum refinery. Online composition monitoring of debutanizer column outlet streams is highly desirable in order to maximize the production of liquefied petroleum gas. In this article, data-driven models for debutanizer column are developed for real-time composition monitoring. The dataset used has seven process variables as inputs and the output is the butane concentration in the debutanizer column bottom product. The input–output dataset is divided equally into a training (calibration) set and a validation (testing) set. The training set data were used to develop fuzzy inference, adaptive neuro fuzzy (ANFIS) and regression tree models for the debutanizer column. The accuracy of the developed models were evaluated by simulation of the models with the validation dataset. It is observed that the ANFIS model has better estimation accuracy than other models developed in this work and many data-driven models proposed so far in the literature for the debutanizer column.
Highlights
Today, in a wide array of processes, it is difficult to achieve continuous online monitoring
A debutanizer column is an integral part of any petroleum refinery
Online composition monitoring of debutanizer column outlet streams is highly desirable in order to maximize the production of liquefied petroleum gas
Summary
In a wide array of processes, it is difficult to achieve continuous online monitoring. The prime reason is the low reliability or unavailability of hardware sensors. This results in huge revenue loss to the industry due to lowquality products which could have been otherwise prevented in presence of continuous monitoring. In order to counter this problem, various industries are incorporating soft sensor models to achieve quality monitoring. The debutanizer column lacks real-time monitoring system for the butane (C4) composition. For the prediction of the bottom product composition of the debutanizer column, various models have been reported in the past. Significant among them are backpropagation neural network (Fortuna et al 2005; Pani et al 2016), partial least square (PLS; Ge and Song 2010; Zheng et al 2016), support vector regression (SVR; Ge and Song 2010), principal component regression (PCR; Ge et al 2014), supervised latent factor analysis (Ge 2016; Yao and Ge 2017), probabilistic regression (Yuan et al 2015) and state-dependent ARX (Bidar et al 2017) techniques for modeling of debutanizer column
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
