Forecast of Regional Fly Ash Production and Sales Based on BP Neural Network

Article Preview

Abstract:

With the improvement of utilization technology of fly ash, the fly ash is gradually changing from waste to important resources. Therefore, the forecast of regional fly ash production and sales is becoming more and more important to power plant operation. This paper selects Beijing-Tianjin-Tangshan area, Zhangjiakou area, Southeastern Coastal area, Western area this four typical region of China, using the 2010-2013 quarter production and sales data of fly ash as the original data sequence in the four region to build a BP neural network model for network for 2014-2015 prediction analysis. From the prediction results we can conclude that prediction accuracy conforms to the required standard, indicating that the prediction model is valid.

You might also be interested in these eBooks

Info:

Periodical:

Advanced Materials Research (Volumes 1044-1045)

Pages:

1749-1752

Citation:

Online since:

October 2014

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2014 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

* - Corresponding Author

[1] Tan Xuelian, Shen Yiqing, Zhao Handi. Analysis of the comprehensive utilization of fly ash policy in China [J]. Comprehensive Utilization of Fly Ash. 2014 (01).

Google Scholar

[2] Tan Xiuhui, Bai Yanping. BP MATLAB network prediction of stock market in financial [J]. Economist. 2009 (12).

Google Scholar

[3] Li Chilin, Hu Xiaohui. Prediction for logistics demand in Wuhan city circle based on BP neural network [J]. Journal of Wuhan University of Technology (information and Management Engineering Edition). 2009 (05).

Google Scholar

[4] Xu Xin, Xiao Sha. The coal demand prediction based on artificial neural network [J]. Market Modernization. 2008 (09).

Google Scholar

[5] D.L. Yu, D.W. Yu. A new structure adaptation algorithm for RBF networks and its application [J]. 2007(16)91-100.

Google Scholar

[6] Jarkko Tikka. Input Selection for Radial Basis Function Networks by Constrained Optimization [C]. ICANN, 2007(1)239-248.

DOI: 10.1007/978-3-540-74690-4_25

Google Scholar