Neural network continuous sliding-mode robot control /
In this paper a method for neural network control design with sliding modes in which robustness is inherent is shown. Neural network control is formulated to be a class of variable structure system control. Sliding-mode is used to determine best values for parameters in neural network learning rules...
Shranjeno v:
Main Authors: | , , , |
---|---|
Format: | Book Chapter |
Jezik: | English |
Teme: | |
Sorodne knjige/članki: | Vsebovano v:
Advanced robotics |
Oznake: |
Označite
Brez oznak, prvi označite!
|
Izvleček: | In this paper a method for neural network control design with sliding modes in which robustness is inherent is shown. Neural network control is formulated to be a class of variable structure system control. Sliding-mode is used to determine 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 demanded to satisfy both, the reaching condition and the sliding condition modes. Derived equations of the adaptive continuous neural-network sliding mode controller were verified on a real 3 D.O.F.PUMA mechanism. The new controller was successfully tested for trajectory tracking control tasks with respect to two criteria: convergence properties of the proposed control algorithm and adaptation capability of the algorithm for sudden load changes in manipulator dynamics. |
---|---|
Opis knjige/članka: | Soavtorji: Karel Jezernik, Andreja Rojko, Suzana Uran. |
Fizični opis: | Str. 383-386. |
ISBN: | 0952445476 |