Determining steelmaking aim chemistry utilizing an iterative and knowledge-based approach

Abstract Development of knowledge-based systems for material design is a complex task, due to the interelationship of many factors in the steelmaking process. In addition, design specifications vary frequently and materials design knowledge is held in a largely intuitive undefined format. This paper discusses the first stage of a material design system which deals with the determination of the steelmaking aim chemistry. If an attempt is made to design aim chemistry based on the mathematical approach of utilizing the empirical models between various design parameters it would result in an unrealistic design because relationships between various design parameters are not always linear. Therefore applying the knowledge-based approach along with the mathematical approach to deal with this complex task is inevitable. The approach put forward in this paper is a hybrid one, where the knowledge base is applied at every stage of the design process to utilize expert as well as heuristic knowledge of metallurgists to obtain designs which are realistic and which take account of the various limitations and constraints encountered in steelmaking. The material design is also characterized by extensive utilization of the grade history database which contains performance data for various steel grades and thickness combinations. The inputs to the system are through interactive dialogue sessions and the basic inputs consist of the material standards, size, quantity, tonnage, end use and customers' special requirements. These basic inputs along with the numerous rules in the knowledge bases as well as mathematical modelling enable the effective design of steelmaking aim chemistry.