Adaptive system of fuzzy-logical regulation by temperature mode of a drum boiler

Abstract

The article discusses the creation of an adaptive system for managing dynamic objects based on neuro-fuzzy technology. This technology is used to actively identify and create temperature control algorithms for the superheated steam of a drum boiler in the presence of disturbances associated with a change in load. To solve this problem, the use of a fuzzy-logical controller is proposed. The rule base of this regulator is defined. A technique is proposed for determining the optimal number of neurons and the number of hidden layers. The neuro-fuzzy model of the controller is presented in the form of a multilayer neural network without feedback, which is characterized by a simple implementation in practice. The use of a fuzzy-logical controller gives the automatic control system the ability to maintain technological parameters at a given level in the presence of external disturbing influences, and also makes it possible to efficiently control the process.