A Coke Quality Prediction Model Based on Support Vector Machine

Hong Jun Chen; Jin Feng Bai

doi:10.4028/www.scientific.net/AMR.690-693.3097

Paper Titles

Research and Prediction of Yellow Soil Moisture Content in Guizhou Province Based on ARIMA Model
p.3076

Energy Analysis and Optimization of Methyl Chlorosilane Separation
p.3082

The Optimization of CO₂ Huff and Puff Well Location in Ultra-Low Permeability Reservoir
p.3086

Prediction of the Flow, Reaction and Heat Transfer for Glass Furnace Firing Petroleum Coke
p.3090

A Coke Quality Prediction Model Based on Support Vector Machine
p.3097

Research on Materials Corrosion Failure Model of Liquefied Natural Gas (LNG) Cylinder for Vehicle
p.3102

Simulation Studies on the Influence of Impact Velocity on the PELE Penetrated and Broken Reinforced Concrete
p.3108

The Failure Finite Element Analysis of Pump Collision with Valve in the Oil Well Pump
p.3112

The Main Structure Design and Motion Simulation of Spreaders Based on Virtual Prototype Technology
p.3116

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 690-693A Coke Quality Prediction Model Based on Support...

A Coke Quality Prediction Model Based on Support Vector Machine

Abstract:

Due to the complexity of coking coal, as well as the mixed nature of some single coal procured, the error is significantly larger to predict coke quality only through coal conventional indicators. Thus the coking enterprises urgently need a coke prediction method using many blend coal-related data. In view of the complexity of coking, there are some limitations as to the regression prediction method and neural network learning methods. On the base of the conventional indicators of single coal and coal rock indicators, the paper utilizes support vector machine to predict the cold and hot strength of coke. The experiments show that the accurate prediction of this method can meet the requirements of enterprises.

You might also be interested in these eBooks

Materials Design, Processing and Applications

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 690-693)

Pages:

3097-3101

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.690-693.3097

Citation:

Cite this paper

Online since:

May 2013

Authors:

Hong Jun Chen, Jin Feng Bai

Keywords:

Coal Conventional Indicators, Coal Rock Indicators, Neural Network (NN), Robust Regression, Support Vector Machine (SVM)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Nicholas J. Manton, Jim Williamson, Gerry S. Riley. Changes in Slagging Behaviour with Composition for Blended Coals. Impact of Mineral Impurities in Solid Fuel Combustion 2002, pp.297-308

DOI: 10.1007/0-306-46920-0_22

Google Scholar

[2] Predicting the yield of coking byproducts on the basis of elementary and petrographic analysis of the coal batch. Original Russian Text © M.B. Golovko, I.D. Drozdnik, D.V. Miroshnichenko, Yu.S. Kaftan, 2012, published in Koks i Khimiya, 2012, No. 6, p.9–18.

DOI: 10.3103/s1068364x12060038

Google Scholar

[3] C.-W. Hsu， C.-J. Lin．A comparison of methods for multi-class support vector machines，IEEE Transactions on Neural Networks, 13(2), (2002)

Google Scholar

[4] Vapnik V N. The nature of statistical learning theory［M］．NewYork: Springer，2005.

Google Scholar

[5] Burges C J C. A Tutorial on support vector machines for pattern recognition［J］. Data Mining and Knowledge Discovery，2003，2( 2) : 121-167.

Google Scholar

[6] Bo-yuan Yao, De-ping Li. Features and correct application of coal vitrinite reflectance index. Journal of Coal Science and Engineering (China)September 2012, Volume 18, Issue 4

DOI: 10.1007/s12404-012-0412-5

Google Scholar