An approach to intelligent control of complex industrial processes: an example of ferrous metal industry

This paper proposes an original approach to the design of intelligent control systems for complex time-varying (nonstationary) objects in which industrial processes are repeatedly reproduced over a certain period of time. Such reproduction allows accumulating data and knowledge about control programs, conditions and results of their implementation, and the trajectories of controlled variables. The motion of a controlled object is decomposed into perturbed and unperturbed motions. The unperturbed programmed motion of the object is described using expert systems and the concept of case-based reasoning (CBR); the perturbed motion of the object, using artificial neural networks.