The Self-Tuning Neural Speed Regulator Applied to DC Servo Motor
ICNC '07 Proceedings of the Third International Conference on Natural Computation - Volume 03
Identification and control of dynamical systems using neural networks
IEEE Transactions on Neural Networks
Backpropagation neural nets with one and two hidden layers
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
This study utilizes the direct neural control (DNC) applied to a DC motor belt-driven speed control system. The proposed neural controller of model reference adaptive control strategy is treated as a speed regulator to keep the belt-driven servo system in constant speed. This study uses experiment data to built dynamic model of DC servo motor belt-driven servomechanism, and design the appropriate reference model. A tangent hyperbolic function is used as the activation function, and the back propagation error is approximated by a linear combination of error and error differential. The proposed speed regulator keeps motor in constant speed with high convergent speed, and simulation results show that the proposed method is available to the belt-driven speed control system, and keep the motor in accurate speed.