×

You are using an outdated browser Internet Explorer. It does not support some functions of the site.

Recommend that you install one of the following browsers: Firefox, Opera or Chrome.

Contacts:

+7 961 270-60-01
ivdon3@bk.ru

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

A.G. Shumikhin, R.R. Islamov, D.K. Kornilitsin

Incoming article date: 20.05.2024

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