A novel modeling approach to optimize oxygen-steam ratios in coal gasification process

被引：59

作者：

Arabloo, Milad ^{[1
]}

Bahadori, Alireza ^{[2
]}

Ghiasi, Mohammad M. ^{[3
]}

Lee, Moonyong ^{[4
]}

Abbas, Ali ^{[5
]}

Zendehboudi, Sohrab ^{[6
]}

机构：

[1] Islamic Azad Univ, Young Researchers & Elites Club, North Tehran Branch, Tehran, Iran

[2] So Cross Univ, Sch Environm Sci & Engn, Lismore, NSW 2480, Australia

[3] NIGC, SPGC, Asaluyeh, Iran

[4] Yeungnam Univ, Sch Chem Engn, Gyeungsan, South Korea

[5] Univ Sydney, Sch Chem & Biomol Engn, Sydney, NSW 2006, Australia

[6] MIT, Dept Chem Engn, Cambridge, MA 02139 USA

来源：

FUEL | 2015年 / 153卷

关键词：

Coal gasification; Oxygen-steam ratio; Low carbon emission; Support vector machine; SUPPORT VECTOR MACHINE; NEURAL-NETWORKS; COST ESTIMATION; PVT PROPERTIES; PREDICTION;

D O I：

10.1016/j.fuel.2015.02.083

中图分类号：

TE [石油、天然气工业]; TK [能源与动力工程];

学科分类号：

0807 ; 0820 ;

摘要：

Coal gasification operation appears to be an essential element in the advanced energy systems, where the reaction between oxygen, steam and coal results in production of syngas (e.g., a mixture of carbon monoxide and hydrogen) under elevated pressure and temperature conditions. An efficient design for gasification process is expected if proper oxygen/steam rations are selected such that a thermal balance is established between the exothermic and endothermic reactions, leading to yield maximization of desired products in most cases. In this article, a rigorous modeling approach using support vector machine (SVM) algorithm is developed to estimate optimum oxygen-steam ratios required to balance the released heat and heat requirement in coal gasification process. An acceptable match between modeling outputs and real data is noticed so that the average absolute error is lower than 1.0%. (C) 2015 Elsevier Ltd. All rights reserved.

引用

页码：1 / 5

页数：5

共 44 条

[1] A comparative study of K-Nearest Neighbour, Support Vector Machine and Multi-Layer Perceptron for Thalassemia screening [J].

Amendolia, SR ;

Cossu, G ;

Ganadu, ML ;

Golosio, B ;

Masala, GL ;

Mura, GM .

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2003, 69 (1-2) :13-20

[2]

[Anonymous], 2002, Least Squares Support Vector Machines, DOI DOI 10.1142/5089

[3]

[Anonymous], 1998, ISIS TECH REP

[4]

[Anonymous], 2000, The Nature of Statistical Learning Theory

[5] Application of constrained multi-variable search methods for prediction of PVT properties of crude oil systems [J].

Arabloo, Milad ;

Amooie, Mohammad-Amin ;

Hemmati-Sarapardeh, Abdolhossein ;

Ghazanfari, Mohammad-Hossein ;

Mohammadi, Amir H. .

FLUID PHASE EQUILIBRIA, 2014, 363 :121-130

[6] Toward a predictive model for estimating dew point pressure in gas condensate systems [J].

Arabloo, Milad ;

Shokrollahi, Amin ;

Gharagheizi, Farhad ;

Mohammadi, Amir H. .

FUEL PROCESSING TECHNOLOGY, 2013, 116 :317-324

[7] Application of least square support vector machines in the prediction of aeration performance of plunging overfall jets from weirs [J].

Baylar, Ahmet ;

Hanbay, Davut ;

Batan, Murat .

EXPERT SYSTEMS WITH APPLICATIONS, 2009, 36 (04) :8368-8374

[8]

Bhattacharya M., 2012, ISRN CERAM, V2012, P1, DOI [10.5402/2012/741042, DOI 10.5402/2012/741042]

[9] Decision support with neural networks in the management of research and development: Concepts and application to cost estimation [J].

Bode, J .

INFORMATION & MANAGEMENT, 1998, 34 (01) :33-40

[10] Utilization of support vector machine to calculate gas compressibility factor [J].

Chamkalani, Ali ;

Zendehboudi, Sohrab ;

Chamkalani, Reza ;

Lohi, Ali ;

Elkamel, Ali ;

Chatzis, Ioannis .

FLUID PHASE EQUILIBRIA, 2013, 358 :189-202

← 1 2 3 4 5 →