Research on New Nonlinear Method Applied on Coal Calorific Value Prediction

Ke Lei Sun; Xiao Juan Zhu; Hua Ping Zhou

doi:10.4028/www.scientific.net/AMM.278-280.915

Paper Titles

Fire Positioning Based on Wireless Sensor Networks
p.888

Multifunction Simulator for Radar Test
p.893

Research and Development of a Test System for the Dynamic Performance Testing of Pneumatic Solenoid Valves
p.897

Research of Magnetic Grid Rail Splicing Technology Based on Phase Difference Detection Method
p.905

Research on New Nonlinear Method Applied on Coal Calorific Value Prediction
p.915

Research on the Wireless Monitoring System for Port Crane Structure Stress
p.920

The Automatic and Real Time Measurement of Tunnel Surrounding Rock Deformation
p.924

The Design and Implementation of PLC Monitoring System Based on OPC
p.930

The Design of SO₂ Sensor Node for Monitoring Table Grape Logistics
p.936

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 278-280Research on New Nonlinear Method Applied on Coal...

Research on New Nonlinear Method Applied on Coal Calorific Value Prediction

Abstract:

Based on research of the relationship between the industrial analysis of coal composition and the calorific value, a multiple linear regression - support vector machine model for predicting calorific value of coal is put forward. The training sample set is made up of the original industrial analysis data and calorific value. Then the preliminary predicted model is established based on multiple linear regression algorithm. At the same time, error compensation is achieved by the support vector machine amend sub-model. The final predicted value is the sum of the preliminary predicted model output and the error compensation. Experimental results demonstrate that the predicted accuracy of the integrated model is more accurate than the traditional predicted models.

You might also be interested in these eBooks

Advances in Mechatronics and Control Engineering

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 278-280)

Pages:

915-919

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.278-280.915

Citation:

Cite this paper

Online since:

January 2013

Authors:

Ke Lei Sun, Xiao Juan Zhu, Hua Ping Zhou

Keywords:

Calorific Value Prediction, Error Correction, Least Squares Support Vector Machines (Ls-SVM), Regression Analysis

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Xiaohong Wang, Dehui Wu. New method of comprehensive prediction for coal-fired calorific capacity. Coal Science and Technology. Vol. 34(2006), pp.16-18.

Google Scholar

[2] Maixi Lu, Cuihong Zhou. Coal Calorific Value Prediction with Linear Regression and Artificial Neural Network. Coal Science and Technology. Vol. 37(2009), pp.117-120.

Google Scholar

[3] Wenhao Jiang, Hongqi Wei, Tianzhang Qu, etc. Prediction of the calorific value for coal based on the SVM with parameters optimized by genetic algorithm. Thermal Power Generation. Vol. 40(2011), pp.14-19.

Google Scholar

[4] Balabin RM, Safieva RZ, Lomakina EI. Comparison of linear and nonlinear calibration models based on near infrared (NIR) spectroscopy data for gasoline properties prediction. Chemometr Intell Lab Syst (2007).

DOI: 10.1016/j.chemolab.2007.04.006

Google Scholar

[5] Dai L-K, Yao X-G. A least squares SVM algorithm for NIR gasoline octane number prediction. In: Intelligent control and automation, 2004. WCICA 2004; June 15-19, 2004. pp.3779-82.

DOI: 10.1109/wcica.2004.1343314

Google Scholar

[6] Balabin RM, Lomakina EI. Support vector machine regression - an alternative to neural networks (ANN) for analytical chemistry. Comparison of nonlinear methods on near infrared (NIR) spectroscopy data. Analyst (2011).

DOI: 10.1039/c0an00387e

Google Scholar