Skip to Main Content
Robotics is a field of modern technology which requires knowledge in vast areas such as electrical engineering, mechanical engineering, computer science as well as finance. Nonlinearities and parametric uncertainties are unavoidable problems faced in controlling robots in industrial plants. Tracking control of a single link manipulator driven by a permanent magnet brushed DC motor is a nonlinear dynamics due to effects of gravitational force, mass of the payload, posture of the manipulator and viscous friction coefficient. Furthermore uncertainties arise because of changes of the rotor resistance with temperature and random variations of friction while operating. Due to this fact classical PID controller can not be used effectively since it is developed based on linear system theory. Neural network control schemes for manipulator control problem have been proposed by researchers; in which their competency is validated through simulation studies. On the other hand, actual real time applications are rarely established. Instead of simulation studies, this paper is aimed to implement neural network controller in real time for controlling a DC motor driven single link manipulator. The work presented in this paper is concentrating on neural NARMA L2 control and its improvement called to as Smoothed NARMA L2 control. As proposed by K. S Narendra and Mukhopadhyay, Narma L2 control is one of the popular neural network architectures for prediction and control. The real time experimentation showed that the Smoothed NARMA L2 is effective for controlling the single link manipulator for both point-to-point and continuous path motion control.