Application of Artificial Neural Network (ANN) in the Optimization of Crude Oil Refinery Process: New Port-Harcourt Refinery

Abstract

Background: Optimizing the process conditions of the crude distillation unit is a main challenge for each refinery. Optimization increases profit by producing the required range of distillates at maximum yield and at minimum cost. To achieve an acceptable control of product quality an artificial neural network (ANN) can be used. ANNs are used for engineering purposes, such as pattern recognition, forecasting, and data compression. In the petroleum refinery industry, ANN has been used as controller in for the crude distillation unit. The aim of the current study was to use ANN to optimize and achieve control of product quality of crude distillation unit of an oil refinery.
 Materials: The research was carried out using the following materials; The design flowchart and the operating data of the crude distillation unit of the New Port Harcourt refinery, Simulation software (HYSYS 2006.5) and Matlab for the ANN.
 Results: The ANN predicted the optimum operating conditions at which the atmospheric distillation unit (ADU) can operate with the least irreversibility and without changing the design and compromising the products quality. The corresponding exergy efficiency after optimization with ANN for the input variable combinations was 70.6% which was a great improvement because the exergy efficiency increased as compared to the base case of 51.9%.
 Conclusion: Optimization using ANN, improved the efficiency of the ADU with the least irreversibility and without changing the design and compromising the products quality.

Optimization and characterization of biodegradable film based on glutinous flour/glycerol/chitosan/ZnO using Response Surface Methodology (RSM) - Central Composite Design (CCD)

“…The positive and negative signs of the regression coefficients represent each variable's synergistic and antagonistic effects on the response. The model coefficients are represented by constant terms A, B and C (linear coefficients for the independent variables), AB, AC and BC (coefficients of interactive terms), and A 2 , B 2 and C 2 (coefficients of quadratic terms) [30].…”

Artificial neural network and response surface methodology for optimization of corrosion inhibition of mild steel in 1 M HCl by Musa paradisiaca peel extract

“…Here, the input layers are the concentration (g/L) and temperature (K); number of neurons are 7, 9, 10, 12, 13, 15, 20, 25 and 30; and the output layer is the inhibition efficiency (%). The network was trained using MSE algorithm at optimum neuron number, while training performance was done by randomly diving the dataset (sample) into three different samples; training (70%), validation (20%) and testing (15%), as earlier performed by Braimah [37] .…”

Designing an Efficient Surfactant–Polymer–Oil–Electrolyte System: A Multi-Objective Optimization Study

“…The polymer used, PEG 1500, was supplied by Sigma and has an average molecular weight of 1500. Finally, sodium chloride (NaCl) with a reagent grade purity of 99% was obtained from Panreac, in Spain [19][20][21].…”

“…This approach helps to analyze both the main effects and the interactions of independent variables, including both categorical and continuous components [19]. The factors that impact the process are referred to as independent variables, while the outcomes are referred to as dependent variables [20].…”