Hysteresis compensation for giant magnetostrictive actuators using dynamic recurrent neural network

Hysteresis compensation for giant magnetostrictive actuators using dynamic recurrent neural network

According to the hysteresis characteristics of the giant magnetostrictive actuator (MA), a dynamic recurrent neural network (DRNN) is constructed as the inverse hysteresis model of the MA, and an on-line hysteresis compensation control strategy combining the DRNN inverse compensator and a proportion...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on magnetics 2006-04, Vol.42 (4), p.1143-1146
Hauptverfasser: Shuying Cao, Shuying Cao, Boweng Wang, Boweng Wang, Jiaju Zheng, Jiaju Zheng, Wenmei Huang, Wenmei Huang, Ling Weng, Ling Weng, Weili Yan, Weili Yan
Format: Artikel
Sprache:eng
Schlagworte:
Actuators
Compensation
Cross-disciplinary physics: materials science
rheology
Dynamic recurrent neural network (DRNN)
Dynamics
Exact sciences and technology
Frequency
Fuzzy control
Hysteresis
Inverse
inverse compensator
Inverse problems
Magnetic hysteresis
Magnetism
Magnetostriction
magnetostrictive actuator (MA)
Materials science
Other topics in materials science
PD control
Physics
Proportional control
Recurrent neural networks
Saturation magnetization
Strategy
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:According to the hysteresis characteristics of the giant magnetostrictive actuator (MA), a dynamic recurrent neural network (DRNN) is constructed as the inverse hysteresis model of the MA, and an on-line hysteresis compensation control strategy combining the DRNN inverse compensator and a proportional derivative (PD) controller is used for precision position tracking of the MA. Simulation results validate the excellent performances of the proposed strategy
ISSN:0018-9464
1941-0069
DOI:10.1109/TMAG.2006.871464