M.M Gouda and A.A. El-Samahy (Egypt)
Artificial neural networks, DC motor, speed control.
In this paper, an artificial neural network (ANN) is used as a speed controller for dc motor. A multi-layer feed-forward neural network using a Levenberg Marquardt backpropagation-training algorithm is applied. The desired speed, motor armature current, and the corresponding armature voltage are used to train the network in order to generate a mapping between the easily measurable inputs (motor speed, and armature current) and the armature voltage. ANN control algorithm is used to identify the inverse dynamics of the dc motor and its drive system. The effectiveness of the proposed controller is illustrated through the comparison, obtained by observing the system dynamic performances, when using Proportional and Integral (PI) controller. The simulation results confirm a very promising tracking control capability of the proposed controller under different disturbances.
Important Links:
Go Back
