| |
DTC-SVM Drive with ANN-based Speed Controller
| [View]
[Download]
|
| Author(s) |
Lech M. Grzesiak, Vincent Meganck, Jakub Sobolewski, Bartlomiej Ufnalski |
| Abstract |
The paper investigates possible advantages from
using an adaptive ANN (Artificial Neural Network)-based speed
controller in a DTC-SVM (Direct Torque Controlled-Space
Vector Modulated) drive. According to the model-free control
design concept, we prepared a neural network control system in
which the emulator of the object is no required at any stage. An
on-line trained ANN serves as a speed controller and does not
need a process model to predict future performance. To increase
the stability and convergence of the algorithm, we used the
Resilient backpropagation (Rprop) adaptive learning scheme,
which modifies the update values for each weight according to
the behaviour of the sequence of partial derivatives in each
dimension. Proposed control algorithm has been tested in
simulation and verified experimentally. The behaviour of the
drive has been compared to the one with classical PI speed
controller with fixed settings. |
| Download |
| Filename: | 211 |
| Filesize: | 2.32 MB |
|
| Type |
Members Only |
| Date |
Last modified 2006-02-08 by System |
| |
 |