Adaptive Neural Network-Based Backstepping Control of BLDC-Driven Robot Manipulators: An Operational Space Approach with Experimental Validation

Unver S., YILMAZ B. M., TATLICIOĞLU E., Saka I., SELİM E., Zergeroglu E.

IET Control Theory and Applications, cilt.19, sa.1, 2025 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 19 Sayı: 1
  • Basım Tarihi: 2025
  • Doi Numarası: 10.1049/cth2.70016
  • Dergi Adı: IET Control Theory and Applications
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Aerospace Database, Applied Science & Technology Source, Business Source Elite, Business Source Premier, Communication Abstracts, Compendex, Computer & Applied Sciences, INSPEC, Metadex, zbMATH, Directory of Open Access Journals, Civil Engineering Abstracts
  • Anahtar Kelimeler: actuator dynamics, adaptive control, Lyapunov methods, neural networks, nonlinear control, robot manipulators, task space
  • Manisa Celal Bayar Üniversitesi Adresli: Evet

Özet

This study concentrates on end effector tracking control of robotic manipulators actuated by brushless direct current (BLDC) motors, having parametric uncertainties in their kinematic, dynamical and electrical sub-systems. Specifically, an operational space controller formulation is proposed that does not rely on inverse kinematics calculations at position level and still ensures practical end effector tracking despite the presence of uncertainties related to the mechanical and electrical dynamics, and the kinematics of the robotic manipulator. Compensation for the uncertainties throughout the entire system is achieved via the use of neural network-based dynamical adaptations, and the overall stability of the closed-loop system is guaranteed via Lyapunov-based arguments. We would like to note that the work addresses the following problems: (i) incorporation of actuator dynamics into the error system in order to achieve increased efficiency, (ii) elimination of the need for position level inverse kinematics calculations for the controller formulation to remove the computational burden and (iii) compensation of the uncertainties throughout the entire subsystem. Experiment studies were carried out on a two degree of freedom planar robot manipulator equipped with BLDC motors to evaluate the effectiveness of the proposed formulation.