Title :
Analysis and Application of Steel Harden Ability Forecasting Model Based on Support Vector Machine
Author :
Guo, Hui ; Wang, Ling ; Liu, Heping
Author_Institution :
Inf. Eng. Sch., Univ. of Sci. & Technol., Beijing
Abstract :
Harden ability is a heat treat property of steel. Harden-ability is mainly determined by chemical composition and organization structure of steel. Support vector machine is a novel machine learning method, which is powerful for the problem characterized by small sample, nonlinearity, high dimension and local minima, and has high generalization. In this paper, harden-ability of steel based on support vector machine is proposed and compared with neural network. Theoretical and simulation analysis indicate that the support vector machine model is better in performance
Keywords :
chemical analysis; forecasting theory; hardening; heat treatment; learning (artificial intelligence); metallurgical industries; steel; support vector machines; heat treat property; machine learning; steel chemical composition; steel harden ability forecasting model; steel organization structure; support vector machine; Chemical technology; Electronic mail; Heat engines; Learning systems; Neural networks; Power engineering and energy; Predictive models; Steel; Support vector machines; Technology forecasting; chemical composition; harden ability; neural network; support vector machine;
Conference_Titel :
Intelligent Control and Automation, 2006. WCICA 2006. The Sixth World Congress on
Conference_Location :
Dalian
Print_ISBN :
1-4244-0332-4
DOI :
10.1109/WCICA.2006.1713474