Intelligent Control of an Industrial Debutanizer Column

Abstract

A debutanizer column located at a refinery in Malaysia produces LPG as its top product and light naphtha as its bottom product. Control of the product compositions of the column is very important to maintain the desired purities. The current control design of the debutanizer column is based on the classical proportional integral derivative approach, which has been found to be less effective in controlling the variations in the column as the process is characterized by strong nonlinear and uncertain dynamics. Here, intelligent control based on an adaptive neurofuzzy inference system (ANFIS) is investigated and compared against an artificial neural network, for the special case of limited training data of the industrial debutanizer column. The ANFIS-based controller outperforms the other control configurations for both set point tracking and disturbance rejection cases and has better generalization performance even when trained with limited data samples.

Machine Learning an Intelligent Approach in Process Industries: A Perspective and Overview

“…This study is advantageous to assess intelligence of various ML methods and proclaim its utilization in various task in oil and gas industries. Anmol et al [73] compared the performance of adaptive neuro-fuzzy inference system (ANFIS) and ANN for the controlling the purity of top and bottom products obtained from debutanizer of Malaysian Refinery by developing controllers. In this study, the authors selected NARX-NN type of network and LM algorithm for training purposes with transig and purlin as transfer function in ANN, whereas subtracting clustering method was used along with hybrid algorithm for optimization in ANFIS.…”

“…Algorithm/method Objective Findings Year [73] Hybrid and LM To control the composition of top and bottom product using ANFIS.…”