INTEGRATED APPLICATION OF SYNERGETIC APPROACH AND NEURAL NETWORK STRUCTURES TO THE PROBLEM OF ELECTRIC DRIVE INTELLECTUAL CONTROL SYSTEM SYNTHESIS

Abstract

The applicability of the artificial neural networks to the synthesis of the intellectual systems with the synergetic control law is considered. The key points of the synergetic approach to the system synthesis problem are stated. An example of the synergetic synthesis of the robot electrodrive control law under the conditions of its uncontrolled parametric variation and external disturbances is considered. An algorithm for synthesis of the neural network controller based on a predetermined synergetic control law is presented. The algorithm is based on the synergetic controller behavior simulated by an artificial neural network as a result of its training through harmonic signals of different frequencies. The key element of the proposed integrated approach to the synthesis of the intelligent control system is that it involves a combination of the self-organization unity principle and the training of the neural network at the preliminary stage. This ensures a subsequent stable system operation.