Autor: |
Guotao WANG, Shaohua DONG, Shang LIU |
Předmět: |
|
Zdroj: |
International Journal of Simulation: Systems, Science & Technology; 2016, Vol. 17 Issue 43, p19.1-19.8, 8p |
Abstrakt: |
This paper creates a system for the demand forecasting of galvanized pipe with the algorithm of Support Vector Machine (SVM) in a pipe enterprise. Firstly, the paper analyzes the market demand about galvanized pipe of a pipe enterprise in Tianjin, one of China's top ten steel pipe production enterprise, with the algorithm of clustering analysis. Second, the paper studies the selection of prediction model parameters about SVM and pretreatment of demand data. Lastly, the demand of mature galvanized pipe is forecasted through SVM with Gaussian radial basis for kernel function. It shows that the forecast effect of SVM is better than traditional prediction methods. [ABSTRACT FROM AUTHOR] |
Databáze: |
Complementary Index |
Externí odkaz: |
|