Identification and Adaptive Position and Speed Control of Permanent Magnet DC Motor with Dead Zone Characteristics Based on Support Vector Machines

In this paper a new type of neural networks known as Least Squares Support Vector Machines which gained a huge fame during the recent years for identification of nonlinear systems has been used to identify DC motor with nonlinear dead zone characteristics. The identified system after linearization in each time span, in an online manner provide the model data for Model Predictive Controller of position and speed in order to tracking the desired references trajectory. In this method all the cascaded controllers including current, speed and position has been automatically tuned based on the identified model. The offered method has been tested on the servodrive made specifically for this purpose, and all the results are practically examined and analyzed. The biggest advantage of this method is the self-tuning behavior which insulates the user for tuning any of the controller’s parameters. The online identification of the system provides the possibility to keep track of the changes in dynamics of the system as well as tackling the coulomb’s friction specifically in low speeds with accurate controlling of the speed and position for DC motors.