Robust Tracking Control of Piezo-Actuated Nanopositioning Stage Using Improved Inverse LSSVM Hysteresis Model and RST Controller

Nanopositioning technology is widely used in high-resolution applications. It often uses piezoelectric actuators due to their superior characteristics. However, exhibit a hysteresis phenomenon that limits positioning accuracy. To compensate for the effect, developing an accurate model of very important. This task challenging, requiring some considerations multivalued mapping loops and generalization capabilities model. challenge can be dealt with by machine learning-based model, whose inverse efficiently design feedforward controller compensation. this approach depends on accuracy type data train Thus, prediction behavior may not guaranteed presence disturbances. In paper, compensator then combined robust feedback enhance robustness nanopositioning control system. The proposed based operators, least square support vector (LSSVM) method, particle swarm optimization (PSO) algorithm. controller, RST employed develop control. Our main contribution introduction hybrid capable compensating at same time, eliminating remaining modeling errors rejecting performance evaluated through MATLAB simulation, as well real-time experiments. experimental results our demonstrate tracking compared PID-LSSVM controller.