Neural Network Control for a Spatial Parallel Manipulator Based on Differential-Algebraic Equations


Dang Danh Hoang†, Tran Xuan Minh†,*, Nguyen Van Quyen‡,*


† Thai Nguyen University of Technology, Vietnam.
‡ Hanoi University of Science and Technology, Vietnam.

Corresponding Author Email: tranxuanminh@tnut.edu.vn; quyen.nguyenvan@hust.edu.vn

This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Parallel manipulators are characterized as having closed-loop kinematic chains. Parallel robots have received increasing attention due to their inherent advantages over conventional serial mechanisms, such as high rigidity, high load capacity, high velocity, and high precision. The motion equations of parallel spatial manipulators are a system of complicated differential-algebraic equations. So the construction of enough accurate and relatively simple mechanical models is needed. The main content of this paper is to derive the inverse dynamics controllers based on the neural network control law for parallel robot manipulators. Finally, an illustrative example is presented a numerical simulation of the inverse dynamic controller for a 3-PRS Delta robot manipulator.