An intelligent approach for the modeling and experimental optimization of molecular hydrodesulfurization over AlMoCoBi catalyst

被引:35
作者
Al-Jamimi, Hamdi A. [1 ]
Bagudu, Aliyu [1 ]
Saleh, Tawfik A. [2 ]
机构
[1] King Fahd Univ Petr & Minerals, Informat & Comp Sci Dept, Dhahran 31261, Saudi Arabia
[2] King Fahd Univ Petr & Minerals, Chem Dept, Dhahran 31261, Saudi Arabia
关键词
Environmental protection; Energy engineering; Hydrodesulfurization; Support vector machine; Genetic algorithm; ARTIFICIAL NEURAL-NETWORK; SUPPORT VECTOR MACHINE; ADSORPTIVE DESULFURIZATION; RESERVOIR CHARACTERIZATION; COMPRESSIBILITY FACTOR; PREDICTION; PERFORMANCE; CARBON;
D O I
10.1016/j.molliq.2018.12.144
中图分类号
O64 [物理化学(理论化学)、化学物理学];
学科分类号
070304 ; 081704 ;
摘要
The accurate prediction of sulfur content is an essential role to ensure proper operation and product quality control in the hydrodesulfurization process (HDS) for environmental protection. Machine learning (ML) techniques have proven their predictive capability in solving challenging problems in the petroleum industry. In this work, an optimized support vector machine (SVM) model was constructed to predict the degradation of the sulfur content in the HDS process. To improve the predictive ability of the models, a genetic algorithm (GA) was used to select the SVM optimal parameters when building the (GA-SVM) model. Thus, a catalyst consisting of alumina modified with 15% molybdenum, 5% cobalt and 2% of bismuth (AlMoCoBi) was prepared by a thermal process and its catalytic performance for HDS was evaluated using a batch reactor. The experimental results demonstrated that our proposed model has promising potential with correlations of R-2 = 0.99 being achieved during the testing stages of the prediction of the sulfur concentration. The experimental validation demonstrates that the predicted values obtained from the (GA-SVM) model correspond closely with the experimental results with average experimental errors of <5%. This proves that the AlMoCoBi catalyst holds great promise for obtaining the sulfur-clean production of fuels. (C) 2019 Elsevier B.V. All rights reserved.
引用
收藏
页码:376 / 384
页数:9
相关论文
共 31 条
[1]   Adsorptive desulfurization and denitrogenation using metal-organic frameworks [J].
Ahmed, Imteaz ;
Jhung, Sung Hwa .
JOURNAL OF HAZARDOUS MATERIALS, 2016, 301 :259-276
[2]  
Akande K.O., 2016, APPL COMPUT INTELL S, V2016
[3]   A hybrid particle swarm optimization and support vector regression model for modelling permeability prediction of hydrocarbon reservoir [J].
Akande, Kabiru O. ;
Owolabi, Taoreed O. ;
Olatunji, Sunday O. ;
AbdulRaheem, AbdulAzeez .
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING, 2017, 150 :43-53
[4]   Investigating the effect of correlation-based feature selection on the performance of support vector machines in reservoir characterization [J].
Akande, Kabiru O. ;
Owolabi, Taoreed O. ;
Olatunji, Sunday O. .
JOURNAL OF NATURAL GAS SCIENCE AND ENGINEERING, 2015, 22 :515-522
[5]   Supervised machine learning techniques in the desulfurization of oil products for environmental protection: A review [J].
Al-Jamimi, Hamdi A. ;
Al-Azani, Sadam ;
Saleh, Tawfik A. .
PROCESS SAFETY AND ENVIRONMENTAL PROTECTION, 2018, 120 :57-71
[6]   Integrated cluster analysis and artificial neural network modeling for steam-assisted gravity drainage performance prediction in heterogeneous reservoirs [J].
Amirian, Ehsan ;
Leung, Juliana Y. ;
Zanon, Stefan ;
Dzurman, Peter .
EXPERT SYSTEMS WITH APPLICATIONS, 2015, 42 (02) :723-740
[7]   Improving the prediction of petroleum reservoir characterization with a stacked generalization ensemble model of support vector machines [J].
Anifowose, Fatai ;
Labadin, Jane ;
Abdulraheem, Abdulazeez .
APPLIED SOFT COMPUTING, 2015, 26 :483-496
[8]   Recent advances in the application of computational intelligence techniques in oil and gas reservoir characterisation: a comparative study [J].
Anifowose, Fatai ;
Adeniye, Suli ;
Abdulraheem, Abdulazeez .
JOURNAL OF EXPERIMENTAL & THEORETICAL ARTIFICIAL INTELLIGENCE, 2014, 26 (04) :551-570
[9]   An intelligent approach to predict gas compressibility factor using neural network model [J].
Azizi, Navid ;
Rezakazemi, Mashallah ;
Zarei, Mohammad Mehdi .
NEURAL COMPUTING & APPLICATIONS, 2019, 31 (01) :55-64
[10]  
Bergstra J, 2012, J MACH LEARN RES, V13, P281