Loading...

Adaptive neural network tracking control of a hybrid stepper motor in microstep operation, RBF compared to MLP

Bastani, Y ; Sharif University of Technology | 2005

196 Viewed
  1. Type of Document: Article
  2. Publisher: 2005
  3. Abstract:
  4. In this paper, a radial basis function neural network-based (RBFNN) adaptive inverse controller for real-time position tracking control of a two phase hybrid stepper motor in microstep mode is presented and compared with a conventional fixed gain stand-alone PID controller. Also it is compared to the same neuro-controller using feed forward backpropagation neural networks (FFBP) presented by the same author showing superior performance of RBFNN to FFBP neural networks. A radial basis neural network is used as a controller in the adaptive inverse control method combining with a closed loop PID controller to ensure system's initial robustness and closed loop stability and improves the performance of the controller. Experimental results are provided for various types of trajectories to be tracked by the motor, comparing neuro-controllers with a conventional fixed gain stand-alone PID controller and show the improvement of the controller performance from 80% decrease in the Mean Squared Error (MSE) up to 99.7% decrease of the MSE for different trajectories. Furthermore trajectories were tracked with the maximum error of 0.02 up to 0.06 degrees. Also the robustness of the method is confirmed through experimental results comparing neuro-controllers and the conventional PID controller by varying the load's inertia and disturbance torques. For this reason two methods were examined. First using the same neuro-controllers and in the second method, neuro-Controllers were adapted by new training data according to new working conditions. © 2005 IEEE
  5. Keywords:
  6. Neural networks ; Stability ; Tracking (position) ; Trajectories ; Neuro-controllers ; PID controllers ; Radial basis network-based (RBFNN) ; Stepping motors
  7. Source: IEEE International Conference on Mechatronics and Automation, ICMA 2005, Niagara Falls, ON, 29 July 2005 through 1 August 2005 ; 2005 , Pages 1334-1339 ; 0780390458 (ISBN)
  8. URL: https://www.researchgate.net/publication/290544492_Adaptive_neural_network_tracking_control_of_a_hybrid_stepper_motor_in_microstep_operation_RBF_compared_to_MLP