Automated control of complex metallurgical units based on the CBR method

Abstract

The paper considers the actual problem of human-machine control of complex technological units and complexes, which are characterized by a large variety of states, multidimensionality, variability, and uncertainty. Such units in the ferrous metallurgy include coke batteries, blast furnaces, steelmaking units (arc furnaces, oxygen converters), foundry and rolling complexes, rolling mills, main workshops and production facilities. The effectiveness of the model approach to the creation of control systems for such objects is shown to be insufficient for the XXI century. Alternative approaches based on the concept of best reasoning (CBR) are considered. In particular, they include full-scale model and full-scale approaches to the development of support systems and management decision-making. The well-known full-scale model procedures for applying the best reasoning (methods of typical situations and exemplary technological cycles) are presented. The authors propose a new CBR method of automated selection and implementation of control actions with the participation of process operators for process control systems. A modified CBR-cycle of control selection and the corresponding functional scheme of the software control system for a cyclic technological unit were developed. The improved CBR-cycle includes the following additional operations: correction of control decisions for selected cases; retrospective optimization of implemented control decisions; preservation of not only the best and optimized, but also erroneous decisions; updating of the case base; formation of solutions in unique or previously unreported situations. The structure of the case information model is formed on the example of software control of steel melting in the conditions of an oxygen converter shop. It includes three sections: data on the specific situation in the control system, parameters of the selected control actions, and results of steel melting. An example of the control program formation for the preparation and execution of the upcoming steel melting is based on the data of a pre-selected melting case in the conditions of a modern oxygen converter process.