A Newton-Raphson and BP neural network Hybrid Algorithm for Forward Kinematics of Parallel Manipulator

Haiqiang Zhang, Hairong Fang, Bingshan Jiang, Fuqun Zhao, Tong Zhu

2019 · 12 citations · 14 references

Concepts

Abstract

In this paper, we introduce a novel redundantly actuated 2RPU-2SPR parallel manipulator and present an efficient hybrid algorithm based on the Newton-Raphson and BP neural network (NR-BP) that allows us to solve the forward kinematics(where P denotes the active prismatic joint). Firstly, the inverse kinematics solution for such manipulator is deduced in detail; however, the forward kinematics is mathematically intractable. To deal with such problem, the forward kinematics is solved in terms of the proposed hybrid algorithm. Simulation examples have been conducted to verify the proposed algorithm and results illustrate that the proposed algorithm is effective and can achieve with high efficiency and good accuracy. It is demonstrated that the proposed algorithm can be applied to the forward kinematics of other parallel manipulator as well.

References

14