Dynamic control model of BOF steelmaking process based on ANFIS and robust relevance vector machine

• Published in: Expert systems with applications Vol. 38; no. 12; pp. 14786 - 14798
• Main Authors: Han, Min, Zhao, Yao
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.11.2011
• Subjects: Adaptive-network-based fuzzy inference system (ANFIS); Basic converters; Basic oxygen furnace (BOF) steelmaking; Coolants; Dynamic control; Dynamic control model; Iron and steel making; Mathematical analysis; Mathematical models; Oxygen steel making; Robust relevance vector machine; Vectors (mathematics); Adaptive-network-based fuzzy inference system (ANFIS); Basic oxygen furnace (BOF) steelmaking; Robust relevance vector machine; Dynamic control model
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2011.05.071

► This study proposes a dynamic control model of basic oxygen furnace (BOF) steelmaking based on adaptive-network-based fuzzy inference system (ANFIS) and robust relevance vector machine (RRVM). The model consists of two parts. The first part utilizes ANFIS to calculate the required amounts of oxygen and coolant, which are control variables in BOF steelmaking, and the second part utilizes RRVM to predict the endpoint temperature and carbon content for the control of BOF steelmaking. The RRVM has better robustness than the classical RVM, thus obtaining higher prediction accuracy, which is helpful to the control of BOF steelmaking. Simulations on industrial data show that the proposed model yields satisfying results. This study concerns with the control of basic oxygen furnace (BOF) steelmaking process and proposes a dynamic control model based on adaptive-network-based fuzzy inference system (ANFIS) and robust relevance vector machine (RRVM). The model aims to control the second blow period of BOF steelmaking and consists of two parts, the first of which is to calculate the values of control variables, viz., the amounts of oxygen and coolant requirement, and the other is to predict the endpoint carbon content and temperature of molten steel. In the first part, an ANFIS classifier is primarily constructed to determine whether coolant should be added or not, then an ANFIS regression model is utilized to calculate the amounts of oxygen and coolant. In the second part, a novel robust relevance vector machine is presented to predict the endpoint. RRVM solves the problem of sensitivity to outlier characteristic of classical relevance vector machine, thus obtaining higher prediction accuracy. The key idea of the proposed RRVM is to introduce individual noise variance coefficient to each training sample. In the process of training, the noise variance coefficients of outliers gradually decrease so as to reduce the impact of outliers and improve the robustness of the model. Simulations on industrial data show that the proposed dynamic control model yields good results on the oxygen and coolant calculation as well as endpoint prediction. It is promising to be utilized in practical BOF steelmaking process.