UDC 004.896
METHOD OF HYBRID CONTROL IN INTELLIGENT SYSTEMS BASED ON PID AND PID-FUZZY-CONTROLLERS
V. V. Ignatyev, PhD (technical sciences), Head of the Department of the Design Buгeau of Modeling and Controlling Systems of Southern Federal University, Taganrog; This email address is being protected from spambots. You need JavaScript enabled to view it.
O. B. Spiridonov, PhD (technical sciences), Director of the Design Buгeau of Modeling and Controlling Systems of Southern Federal University, Taganrog; This email address is being protected from spambots. You need JavaScript enabled to view it.
V. M. Kureychik, doctor of engineering; Professor of the Department of Computer Aided Design Systems of Southern Federal University, Taganrog; This email address is being protected from spambots. You need JavaScript enabled to view it.
A. V. Kovalev, doctor of engineering, assistant professor, Head of the Engineering Center of Instrument Making of Radio and Microelectronics of Southern Federal University, Taganrog; This email address is being protected from spambots. You need JavaScript enabled to view it.
A. S. Ignatyeva, postgraduate student of the Department of Computer Aided Design Systems of Southern Federal University, Taganrog; This email address is being protected from spambots. You need JavaScript enabled to view it.
The aim of the work is development of a method of hybrid control based on PID and PID-FUZZY-controllers, that allows to connect formalizable and non-formalizable knowledge while designing modern automated and automatic control systems of technological process. To achieve the aim of the work, the approach to technical object control is developed using an adaptive system of neuro-fuzzy inference. The main control elements of the developed adaptive system of neuro-fuzzy inference are PID- and PID-FUZZY-controllers as well as classical and fuzzy control models developed on their basis. The interaction of two models is provided by the developed hybrid control system. As a result of the interaction of two models, the base of fuzzy controller rules is automatically formed based on the knowledge of the object obtained by its control with the help of classical controller, that allows to completely exclude the participation of expert in the design and adjustment of fuzzy controller parameters. In the developed adaptive system of neuro-fuzzy inference, the signal of deviation, signal of deviation differential and signal of control in the classical model are used as data for creation a hybrid network. Signals of deviation and control in a fuzzy model with already automatically generated rules of fuzzy inference are used as data to verify a created hybrid network in order to detect the fact of its retraining. Thus, the application of hybrid control method based on the adaptive system of neuro-fuzzy inference with the use of PID and PID-FUZZY-controllers allows to provide effective control of a technical object in the conditions of uncertainty.
Key words: automation, control, hybrid systems, adaptive system, model, PID controller, FUZZY-controller, base of fuzzy rules, neuro-fuzzy inference, training.