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

Hussein, Al Jlibawi A.; Othman, Mohammad Lutfi; Aris, Ishak; Noor, Bahari S. Moh; Al-Huseiny, Muayed S.

doi:10.1109/access.2021.3134931

Cited by 8 publications

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, because refining processes are complicated and don't work in a straight line, the results are often less than ideal. Machine learning (ML) techniques, on the other hand, have changed the oil business by giving people powerful ways to get useful information from huge amounts of data (Al Jlibawi et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Intelligent Petroleum Processing: A Short Review on Applying AI/ML to Petroleum Products Optimization

Alzahawy,

Issa

2024

Preprint

View full text Add to dashboard Cite

Improving the quality of petroleum products and refining processes through the use of artificial intelligence and machine learning techniques is the topic of this article. It shows that expert knowledge and conventional empirical models can't get you where you want to go in a refining process. To effectively capture complex interactions and forecast fuel qualities, machine learning techniques such as principal component analysis (PCA), support vector machines (SVM), artificial neural networks (ANN), and partial least squares (PLS) are suggested. Gasoline and other petroleum products, as well as property prediction, process control, product quality, and operational efficiency in refineries, can all be improved with the help of machine learning applied to spectral or distillation curve data. An exciting new direction in optimizing operations, meeting environmental norms, and precisely estimating gasoline quality is offered by advanced machine learning algorithms.

show abstract

Section: Introductionmentioning

confidence: 99%

Intelligent Petroleum Processing: A Short Review on Applying AI/ML to Petroleum Products Optimization

Alzahawy,

Issa

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…; reference [8] makes an assessment of refinery efficiency using linear programming; references [9][10][11][12][13][14] present studies related to planning and scheduling; and reference [15] investigates the efficiency of the process of crude oil dewatering and desalting. Fuzzy modeling was another modeling technique employed in petroleum refining and renewable energy systems for the selection of the optimum working situations that produce a preferable efficiency with a very good veracity [16][17][18][19][20][21][22][23][24][25][26][27][28][29].…”

Section: Introductionmentioning

confidence: 99%

Modeling the Production Process of Fuel Gas, LPG, Propylene, and Polypropylene in a Petroleum Refinery Using Generalized Nets

Stratiev,

Dimitriev,

Stratiev

et al. 2023

Mathematics

View full text Add to dashboard Cite

The parallel processes involved in the production of refinery fuel gas, liquid petroleum gas (LPG), propylene, and polypropylene, occurring in thirteen refinery units, are modeled by the use of a Generalized Net (GN) apparatus. The modeling of the production of these products is important because they affect the energy balance of petroleum refinery and the associated emissions of greenhouse gases. For the first time, such a model is proposed and it is a continuation of the investigations of refinery process modelling by GNs. The model contains 17 transitions, 55 places, and 47 types of tokens, and considers the orders of fuel gas for the refinery power station, refinery process furnaces, LPG, liquid propylene, and 6 grades of polypropylene. This model is intended to be used as a more detailed lower-level GN model in a higher-level GN model that facilitates and optimizes the process of decision making in the petroleum refining industry.

show abstract

“…Petroleum refining economics favor increased production of light oil products (boiling below 360 • C) at the expense of decreased production of heavy oils (boiling above 360 • C) [1,2]. The yields of light oil products depend not only on the characteristics of the crude oil processed and the conversion level in the heavy oil conversion units, such as fluid catalytic cracking, hydrocracking, and thermal cracking (visbreaking, or coking), but also on the efficiency of the distillation columns separating the light oils from the heavy oils [3][4][5][6]. The efficiency of the distillation column performance is typically controlled by examination of the amount of light oil content remaining in the heavy oil and the amount of heavy oil remaining in the light oil [7].…”

Section: Introductionmentioning

confidence: 99%

Validation of Diesel Fraction Content in Heavy Oils Measured by High Temperature Simulated Distillation and Physical Vacuum Distillation by Performance of Commercial Distillation Test and Process Simulation

et al. 2022

View full text Add to dashboard Cite

A gas chromatography high temperature simulation distillation (HTSD: ASTM D 7169), and physical vacuum distillation (ASTM D 1160) were employed to characterize H-Oil vacuum distillates, straight run vacuum distillates, and hydrotreated vacuum distillates with the aim to determine their content of diesel fraction and evaluate the possible higher extraction of diesel fraction from the heavy oils. The ASTM D 7169 reported about six times as high diesel fraction content in H-Oil heavy distillates as that reported by the ASTM D 1160 method. Performing a commercial distillation column test along with a simulation of the column operation using data of both ASTM methods and a software process simulator revealed that the HTSD is the more valid method for proper determination of the diesel fraction content in heavy oils. The software process simulation of the commercial distillation column operation suggests that the HTSD could be considered as a true boiling point distillation method for heavy oils. The separation of the diesel fraction from the H-Oil heavy distillates quantified by the HTSD could deliver oil refining profit improvement in the amount of six digits USD per year.

show abstract

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

Cited by 8 publications

References 31 publications

Intelligent Petroleum Processing: A Short Review on Applying AI/ML to Petroleum Products Optimization

Intelligent Petroleum Processing: A Short Review on Applying AI/ML to Petroleum Products Optimization

Modeling the Production Process of Fuel Gas, LPG, Propylene, and Polypropylene in a Petroleum Refinery Using Generalized Nets

Validation of Diesel Fraction Content in Heavy Oils Measured by High Temperature Simulated Distillation and Physical Vacuum Distillation by Performance of Commercial Distillation Test and Process Simulation

Contact Info

Product

Resources

About