Neural Network Control for Robot Manipulator

The basic issue discussed in the engineering work is to get acquainted with the structure and construction of neural networks and the principle of their operation. The whole process was discussed as well as selected methods of learning neural networks. The next part of the work presents a review of artificial neural networks in the direction of their application to control nonlinear systems used in automation. In the next chapter the model of nonlinear system was describes in detail. A manipulator simulator was created in the Matlab / Simulink program. Two controllers: a neural controller and the most commonly used PID controller have been implemented to control a nonlinear system. Controllers were evaluated for the quality of work and compared the influence of a given regulators on the control of a nonlinear system in terms of selected criteria.