Design and experimental validation of a piezoelectric actuator tracking control based on fuzzy logic and neural compensation
Fuzzy Sets and Systems 464 : (2023) // Article ID 108449
Abstract
This work proposes two control feedback-feedforward algorithms, based on fuzzy logic in combination with neural networks, aimed at reducing the tracking error and improving the actuation signal of piezoelectric actuators. These are frequently used devices in a wide range of applications due to their high precision in micro- and nanopositioning combined with their mechanical stiffness. Nevertheless, the hysteresis is one the main phenomenon that degrades the performance of these actuators in tracking operations. The proposed control schemes were tested experimentally in a commercial piezoelectric actuator. They were implemented with a dSPACE 1104 device, which was used for signal generation and acquisition purposes. The performance of the proposed control schemes was compared to conventional structures based on proportional-integral-derivative and fuzzy logic in feedback configuration. Experimental results show the advantages of the proposed controllers, since they are capable of reducing the error to significant magnitude orders.