NEURO-SYSTEM OF AIMING AND STABILIZING WITH A REGULATOR ON THE BASIS OF STANDARD MODEL MODEL REFERENCE CONTROLLER

• Date: 2015
• Main Authors: Kuznetsov, B. I., Vasilets, T. E., Varfolomiyev, O. O.
• Format: Article
• Language: Ukrainian
• Published: National Technical University "Kharkiv Polytechnic Institute" and Аnatolii Pidhornyi Institute of Power Machines and Systems of NAS of Ukraine 2015
• Subjects: neural network control; aiming and stabilization system; nonlinear dynamic object; neuro-controller on the basis of standard model; Model Reference Controller; 681.5.01.23
• Online Access: http://eie.khpi.edu.ua/article/view/2074-272X.2015.4.06
• Journal Title: Electrical Engineering & Electromechanics

The aim of this work is the synthesis of neural network aiming and stabilization system for the special equipment of moving objects with neuro-controller on the basis of standard model and performance comparison of the neural network system with the neural network predictive control. Build a block diagram of the neural network aiming and stabilization system, based on the subject control principle with PD-regulator in the position loop and with neuro-controller on the basis of standard model in the in the velocity loop. The neuro-controller on the basis of standard model Model Reference Controller is synthesized in the MATLAB Neural Network Toolbox and system simulation is performed. The studies show that the transient state variables of the system are oscillatory. Therefore, the neuro-controller with the prediction NN Predictive Controller should be used for aiming and stabilizing system to provide high dynamic characteristics achieved at the cost of higher complexity and computational cost.