STUDY OF THE PROCESS OF CONTROL OF HEAT TREATMENT OF IRON ORE ROLLS USING THE NEURAL NETWORK

Based on the analysis of existing methods for controlling the process of heat treatment of iron ore pellets on a conveyor-type machine, the need to develop new more accurate methods for controlling the regulatory parameters of technological zones is substantiated, taking into account the influence of neighboring zones on them. The possibility of supporting the regulatory parameters of technological zones with the use of artificial neural network technologies has been investigated. The structure of an artificial neural network for the technological zone has been determined, taking into account the relationship with neighboring zones, the physical and chemical properties of the pellets and the speed of movement of the conveyor belt carts during the technological zone. Computer simulation of the technological first drying zone was carried out, which is interconnected with the second drying zone and the cooling zone, which made it possible to create a model of the system, which ensured the stabilization of the temperature of the upper layer of the pellets in the first drying zone based on the neural network adaptation of the temperature parameters of the coolant of the gas-air flow.