To improve the control precision of robotic manipulator, fuzzy support vector machines control method for robotic manipulator was presented based on genetic algorithm and least square algorithm. Fuzzy algorithm was used to decouple joints. Using support vector machines, fuzzy logical control of complete process and treatment of non-linear signal were realized. The parameters of controller were optimized by hybrid learning algorithm. First, least square algorithm was used for off-line optimization to form support vector machines control system. Then, genetic algorithm was used for on-line optimization to get the optimal performance parameters of support vector machines and the optimal fuzzy proportional parameters. Simulation results of a two-link manipulator demonstrated that the control method designed gets tracking effect with high precision.
[1]
Sheng-De Wang,et al.
Fuzzy support vector machines
,
2002,
IEEE Trans. Neural Networks.
[2]
Johan A. K. Suykens,et al.
Least Squares Support Vector Machine Classifiers
,
1999,
Neural Processing Letters.
[3]
Wang Yaonan.
On fuzzy support vector machine controller
,
2005
.
[4]
Wang Yong-hao.
The Fuzzy Support Vector Network Controller Based on Least Square Algorithms and Its Application
,
2007
.
[5]
Zhihong Man,et al.
Non-singular terminal sliding mode control of rigid manipulators
,
2002,
Autom..
[6]
Shen Hong-yuan.
Design of Temperature-humidity Control System for Tobacco Room Based on Fuzzy Con
,
2007
.