The passive method for parametric identification in adaptive process control using neural network technology
Abstract
The passive method for parametric identification in adaptive process control using neural network technology
Incoming article date: 20.05.2024The 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