| Abstract |
This paper deals with the implementation of artificial neural network in control of DC drive. In the contribution four control systems are discussed. The first is a direct inverse control, then a neural feedforward control with PID controller. The third is a neural network predictive control and the last of them contains a conventional PID controller for future comparison of presented control systems. The DC drives were simulated in program MATLAB with Simulink toolbox, Neural network based control system design toolkit and Neural network toolbox. The main goal of the work was to find the simplest neural network structures with minimum number of neurons, but simultaneously good regulation characteristics are required. Despite used neural network, which is very simple it was achieved satisfactory results. Artificial neural networks are mainly used for complicated systems and processes, which are very difficult to control. |
