An Expert Control System for the Coal Blending Process in an Iron and Steel Plant

Abstract

Two important aspects of the control of the coal blending process in the iron and steel industry are computation of the target percentage of each type of coal to be blended and the blending of the different types of coal in the target ratio. This paper presents an expert control system with a two-level configuration for the coal blending process. First, based on statistical data and knowledge of the process, highly accurate mathematical models are constructed to predict the quality of blended coal and coke. Based on the knowledge representation, rule models are established to compute the target percentages and modify the mathematical models. Then, an algorithm for computing the target percentages is proposed that combines the mathematical models and rule models and uses a forward chaining strategy. Finally, a distributed control system is constructed for the blending of coal in accordance with the target percentages. The results of actual runs show that the expert control system provides an effective way to control the coal blending process.