Ruban S. Automation of control processes of thermal treatment of iron-ore pellets with use of predictive ANFIS models.

The purpose is to improve process control of thermal treatment of iron-ore pellets at the conveyor induration furnace for the reduction of specific consumption of energy resources, increase productivity of induration furnace, improving the quality characteristics of the final product by automating the process using the methods of intellectual identity based on neuro-fuzzy modeling and predictive control methods. Methods: system identification, correlation and regression analysis, systems analysis, artificial intelligence (neural networks, fuzzy logic), control theory, in particular, model predictive control theory, numerical methods for solving of optimization problems, simulation. Novelty: the dynamic models of thermal treatment of iron-ore pellets in technological zones of conveyor induration furnace for identification of process operating conditions using neuro-fuzzy predictors with comprehensive capabilities are improved; a new approach to automation of control process of thermal treatment of pellets based on the combination of the intellectual identification using autoregressive ANFIS-models and methods of model predictive control is proposed. Results: new methods, techniques and algorithms of automated predictive control of pellets thermal treatment at the conveyor induration furnace with the use of neuro-fuzzy models incorporated into the design institutes. Industry: automation of control processes.