Neural network sliding mode direct-drive robot controller /
This paper develops a method for neural network control design with sliding modes in which robustness is inherent. Neural network control is formulated to become a class of variable structure system (VSS) control. Sliding modes are used to determine the best values for parameters in neural network l...
Shranjeno v:
| Main Authors: | , , , |
|---|---|
| Format: | Book Chapter |
| Jezik: | English |
| Teme: | |
| Sorodne knjige/članki: | Vsebovano v:
Microcomputer applications |
| Oznake: |
Označite
Brez oznak, prvi označite!
|
| Izvleček: | This paper develops a method for neural network control design with sliding modes in which robustness is inherent. Neural network control is formulated to become a class of variable structure system (VSS) control. Sliding modes are used to determine the best values for parameters in neural network learning rules, thereby robustness in learning control can be improved. A switching manifold is prescribed and the phase trajectory is required to satisfy both, the reaching condition, and the sliding condition for sliding modes. The derived equations of the adaptive sliding-mode controller were verified on a real industrial direct-drive 3 D.O.F. PUMA mechanism. The new neural network continuous sliding mode controller was successfully tested for trajectory tracking control tasks with respect to two criteria: convergence properties of the proposed control algorithm (high speed cyclic movement) and the adaptation capability of the algorithm for sudden changes in the manipulator dynamics. |
|---|---|
| Opis knjige/članka: | Invited paper for special issue on robotics. |
| Fizični opis: | str. 3-12. |
| ISSN: | 0820-0750 |