Fuzzy Sliding Mode Control for a Three-Links Spatial Robot Based on RBF Neural Network

To achieve the tracing control of a three-links spatial robot, a adaptive fuzzy sliding mode controller based on radial basis function neural network is proposed in this paper. The exponential sliding mode controller is divided into two parts: equivalent part and exponential corrective part. To realize the control without the model information of the system, a radial basis function neural network is designed to estimate the equivalent part. To diminish the chattering, a fuzzy controller is designed to adjust the corrective part according to sliding surface. The simulation studies have been carried out to show the tracking performance of a three-links spatial robot. Simulation results show the validity of the control scheme.

[1]  Faa-Jeng Lin,et al.  Robust Fuzzy Neural Network Sliding-Mode Control for Two-Axis Motion Control System , 2006, IEEE Transactions on Industrial Electronics.

[2]  Galip Cansever,et al.  Fuzzy sliding mode controller with neural network for robot manipulators , 2008, 2008 10th International Conference on Control, Automation, Robotics and Vision.

[3]  Mark W. Spong,et al.  Robot dynamics and control , 1989 .

[4]  S.A. Mohseni,et al.  Fuzzy neural networks controller for a chaotic nonlinear gyro using sliding-mode surfaces , 2008, 2008 IEEE International Symposium on Industrial Electronics.

[5]  Xiaojiang Mu.  Fuzzy neural sliding mode control based on genetic algorithm for multi-link robots , 2010, 2010 Chinese Control and Decision Conference.

[6]  Yu Chen,et al.  A Fuzzy-Neural Network Sliding Mode Control for Flexible Spacecraft , 2010, 2010 2nd International Conference on Information Engineering and Computer Science.

[7]  Feipeng Da,et al.  Fuzzy neural network sliding mode control for long delay time systems based on fuzzy prediction , 2008, Neural Computing and Applications.