Optimization of Distribution Control System in Oil Refinery by Applying Hybrid Machine Learning Techniques

Ali Hussein Humod Al Jlibawi,Al Huseiny M Sattar Sajitt,Mohammad Lutfi Othman,Aris Ishak,Bahari S Moh Noor

doi:10.1109/access.2021.3134931

Ali Hussein Humod Al Jlibawi, Al Huseiny M Sattar Sajitt + Show 3 more

Open Access

https://doi.org/10.1109/access.2021.3134931

Copy DOI

Abstract

In this research, prediction of crude oil cuts from the first stage of refining process field is laid out using rough set theory (RST) based adaptive neuro-fuzzy inference system (ANFIS) soft sensor model to enhance the performance of oil refinery process. The RST was used to reduce the fuzzy rule sets of ANFIS model, and its features in the decision table. Also, discretisation methods were used to optimise the continuous data’s discretisation. This helps to predict the two critical variables of light naphtha product: Reid Vapor Pressure (RVP) and American Petroleum Institute gravity (API gravity), which detect the cut’s quality. Hence, a real-time process of Al Doura oil refinery is examined and the process data of refining crude oil from these two sources improve the knowledge provided by the data. The response variables represent the feedback measured value of cascade controller in the top of the splitter in crude distillation unit (CDU) in the rectifying section, which controls the reflux liquid’s flow towards the splitter’s head. The proposed adaptive soft sensor model succeeded to fit the results from laboratory tests, and a steady-state control system was achieved through an embedded virtual sensor. The predictive control system has been employed using cascade ANFIS controller in parallel with the soft sensor model to keep the purity of the distillate product in the stated range of the quality control of oil refinery. The results obtained from the proposed ANFIS based cascade control have no over/undershoots, and the rise time and settling time are improved by 26.65% and 84.63%, respectively than the conventional proportional-integral-derivative (PID) based cascade control. Furthermore, the results of prediction and control model are compared with those of other machine learning techniques.

Highlights

The petrochemical and oil refinery industries employ advanced control systems in order to improve the product quality and yield, thereby maximising the operation of the process by reducing the unnecessary expenses
This section presents the results of proposed adaptive neuro-fuzzy inference system (ANFIS) based embedded soft sensor model for predictions of Reid Vapor Pressure (RVP) and American Petroleum Institute gravity (API) of light naphtha from Al Doura oil refinery process
The two soft sensors model developed using ANFIS for the prediction of RVP and API of Al Doura oil refinery process is presented

Summary

Introduction

The petrochemical and oil refinery industries employ advanced control systems in order to improve the product quality and yield, thereby maximising the operation of the process by reducing the unnecessary expenses. The calculation of distillation splitter column in this paper is based on a real-time oil project to create a light naphtha processing plant for increasing the control systems' utility value. A mathematical model was introduced for simulation analysis of splitter distillation column with energy equilibrium (L-V) structure control system for feasibility study and design of petroleum project [4]. The process variables like temperature, pressure, flow rate, level and composition must be monitored and controlled in all the distillation processes. The uncontrolled independent variables are considered as interruptions and depend variable as other control objectives or process limitations These studies consider a linear model which fails to describe the real-time process nonlinearities. The main contributions of the proposed research work are as follows:

Objectives

Results

Conclusion