Six degree-of-freedom maneuvering simulation of an experimental model undergoing severe maneuvers using recursive neural networks

Author(s):  
William Faller ◽  
William Smith ◽  
Richard Nigon ◽  
Thomas Huang
Author(s):  
Dan Zhang ◽  
Zhen Gao

Optimizing the performances of parallel manipulators by adjusting the structure parameters can be a difficult and time-consuming exercise especially when the parameters are multifarious and the objective functions are too complex. Artificial intelligence approaches can be investigated as the effective criteria to address this issue. In this paper, genetic algorithms and artificial neural network are implemented as the intelligent optimization criteria of global stiffness and dexterity for spatial six degree-of-freedom (DOF) parallel manipulator. The objective functions of global stiffness and dexterity are calculated and deduced according to the kinetostatic model. Neural networks are utilized to model the solutions of performance indices. Multi-objective optimization is developed by Pareto-optimal solution. The effectiveness of the proposed methodology is proved by simulation.


2021 ◽  
pp. 107754632199731
Author(s):  
He Zhu ◽  
Shuai He ◽  
Zhenbang Xu ◽  
XiaoMing Wang ◽  
Chao Qin ◽  
...  

In this article, a six-degree-of-freedom (6-DOF) micro-vibration platform (6-MVP) based on the Gough–Stewart configuration is designed to reproduce the 6-DOF micro-vibration that occurs at the installation surfaces of sensitive space-based instruments such as large space optical loads and laser communications equipment. The platform’s dynamic model is simplified because of the small displacement characteristics of micro-vibrations. By considering the multifrequency line spectrum characteristics of micro-vibrations and the parameter uncertainties, an iterative feedback control strategy based on a frequency response model is designed, and the effectiveness of the proposed control strategy is verified by performing integrated simulations. Finally, micro-vibration experiments are performed with a 10 kg load on the platform. The results of these micro-vibration experiments show that after several iterations, the amplitude control errors are less than 3% and the phase control errors are less than 1°. The control strategy presented in this article offers the advantages of a simple algorithm and high precision and it can also be used to control other similar micro-vibration platforms.


Sign in / Sign up

Export Citation Format

Share Document