Title :
A prediction method based on CBR and ARMAX model and its application
Author_Institution :
Mech. & Electr. Eng. Dept., Guangdong Univ. of Sci. & Technol., Dongguan, China
Abstract :
This paper introduces a prediction method based on CBR and ARMAX model. CBR is applicable to solve the problems that the traditional field methods are difficult to solve. ARMAX model is a traditional model used widely in the predicting field. The combined method is suitable for predicting the nonlinear system that a single predicting method cannot well solve. The hit rate reaches 89.37% by the predicting experiments of a blast furnace with errors ranging from -0.05 to 0.05. And also, the hit rate is higher than the single predicting method.
Keywords :
blast furnaces; case-based reasoning; production engineering computing; silicon; ARMAX model; CBR model; blast furnace; case based reasoning; nonlinear system; prediction method; silicon content forecasting; Blast furnaces; Forecasting; Heating; Metals; Object oriented modeling; Predictive models; Silicon; ARMAX model; CBR; combined model; the predicting of silicon content;
Conference_Titel :
Control and Decision Conference (CCDC), 2015 27th Chinese
Conference_Location :
Qingdao
Print_ISBN :
978-1-4799-7016-2
DOI :
10.1109/CCDC.2015.7162537
