Adaptive neural network control of hexapod for aerospace application

International Scientific and Practical Conference on Innovations in Engineering and Technology

工业技术;自然科学

Zhukov, Y.A.^1 ; Korotkov, E.B.^1 ; Moroz, A.V.^1 ; Zhukova, V.V.^2 ; Abramov, A.M.^3

Baltic State Technical University VOENMEH, Russia^1

Peter the Great St.Petersburg Polytechnic University, Russia^2

Novgorod State University, ul. B. St. Petersburgskaya, 41, Veliky Novgorod

173003, Russia^3

关键词: Adaptive neural network control;    Adaptive neural networks;    Design and Development;    Desired trajectories;    Engineering applications;    Ministry of Education;    Parallel manipulators;    Precision mechanisms;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/441/1/012001/pdf
DOI  :  10.1088/1757-899X/441/1/012001

来源: IOP

【 摘 要 】

This research is a part of the work implemented by BSTU "Voenmeh" under the financial support of the Ministry of Education and Science of the Russian Federation for design and development of a precision mechanism with the parallel kinematics called "Hexapod". Based on the Stewart platform Hexapod as a positioning system with the parallel kinematics has many advantages in comparison with the serial kinematics mechanism. In engineering applications, very precise motion of parallel manipulators to track the desired trajectory has received a great deal of attention. The inverse kinematics problem of the hexapod is described, on the basis of which the desired trajectories are formed. The simulation model of hexapod dynamics implemented in the Matlab Simulink environment is shown. In this paper provides adaptive neural networks algorithm of the hexapods control with on-line tuning synaptic weights of network. Our results show an advantage of applying of the investigated algorithm in the problem of tracking control of the space applications hexapod.