The article considers the method for parametric identification of a model of steady-state modes of a technological process. The method essence is to use artificial neural networks. The input of each neural network is measured values of input and output process variables, and the output is a corresponding parameter value of the technological process model. The effectiveness of the method was assessed by conducting computational experiments on regression models with two factors and models of steady-state modes of technological processes in existing industries. The average relative error of the models does not exceed 0,43%. The method for parametric identification is applicable in adaptive control of steady-state modes of the technological process. One of advantages of the method is that with a specified form of mathematical description, training a neural network does not require statistical experimental values of process variables.

Keywords: the method for parametric identification, an artificial neural network, the model of steady-state modes of the technological process, adaptive control

The presented paper provides an overview of approaches to automation of the drying process in the fluidized bed mode. The technological process of drying potassium chloride in a fluidized bed apparatus at a potash plant is considered as an object of control. During the analysis of the control object, it was noted that, according to the generalized opinion of the technical staff of the production in question, standard control algorithms (PID controllers) are not effective enough in the task of automatic control of the thermal regime of the potassium chloride drying process. The control of the thermal regime in the production under consideration is carried out by the operational personnel in manual mode, by manipulating the flow rate of the drying agent. The need to simultaneously solve and take into account many different kinds of process control tasks in the drying compartment leads to the fact that the operator is physically unable to constantly ensure accurate maintenance of the thermal drying regime in accordance with the regulations in conditions of fluctuations in the consumption of wet crystallized, which reduces the quality of the drying process control and leads to overspending of fuel gas. Analysis of the conditions and results of the operation of the production in question showed that standard algorithms are not able to provide the required quality of process control. The use of more advanced methods and algorithms of automatic control is required. A review of literature sources shows that the solution to the existing problem can be found based on the use of algorithms that meet intelligent automatic control systems. One of the modern approaches to automation of complex, informationally weakly deterministic technological processes is the intellectualization of the control system. Intelligent control algorithms are considered to be built on the basis of models for the representation of expert knowledge. Such algorithms are able to maintain operability in conditions of non-stationarity of process variables and incompleteness of the observed information about its state." "The presented paper provides an overview of approaches to automation of the drying process in the fluidized bed mode. The technological process of drying potassium chloride in a fluidized bed apparatus at a potash plant is considered as an object of control. During the analysis of the control object, it was noted that, according to the generalized opinion of the technical staff of the production in question, standard control algorithms (PID controllers) are not effective enough in the task of automatic control of the thermal regime of the potassium chloride drying process. The control of the thermal regime in the production under consideration is carried out by the operational personnel in manual mode, by manipulating the flow rate of the drying agent. The need to simultaneously solve and take into account many different kinds of process control tasks in the drying compartment leads to the fact that the operator is physically unable to constantly ensure accurate maintenance of the thermal drying regime in accordance with the regulations in conditions of fluctuations in the consumption of wet crystallized, which reduces the quality of the drying process control and leads to overspending of fuel gas. Analysis of the conditions and results of the operation of the production in question showed that standard algorithms are not able to provide the required quality of process control. The use of more advanced methods and algorithms of automatic control is required. A review of literature sources shows that the solution to the existing problem can be found based on the use of algorithms that meet intelligent automatic control systems. One of the modern approaches to automation of complex, informationally weakly deterministic technological processes is the intellectualization of the control system. Intelligent control algorithms are considered to be built on the basis of models for the representation of expert knowledge. Such algorithms are able to maintain operability in conditions of non-stationarity of process variables and incompleteness of the observed information about its state.

Keywords: fluidized bed drying, potassium chloride, control, process automation, PID, intelligent control algorithmsfluidized bed drying, potassium chloride, control, process automation, PID, intelligent control algorithms