Billet temperature soft sensor model of reheating furnace based on RVM method

Autor: Shukai Qin, Yanhui Liu, Xiaozhi Liu, Yinghua Yang
Rok vydání: 2011
Předmět:
Zdroj: 2011 Chinese Control and Decision Conference (CCDC).
DOI: 10.1109/ccdc.2011.5968923
Popis: Billet temperature soft sensor model is always necessary because of lack of accurate online instrument. In this paper, a new soft sensor modeling method is proposed to predict the billet temperature of reheating furnace based on relevance vector machine (RVM). The proposed method has sparser solutions and better model generalization ability, while the uncertainty of model forecast can be given. The prediction model between billet temperature variable and process variable is established by using actual data from a steel plant. The simulation results show that the proposed method has higher prediction accuracy, and a certain practical significance to the on-site production of reheating furnace.
Databáze: OpenAIRE