Neuro-adaptive dynamic integral sliding mode control design with output differentiation observer for uncertain higher order MIMO nonlinear systems

摘要: This paper proposes a practical design method for the robust control of class MIMO nonlinear plants operating under model uncertainties and matched disturbances where only available information feedback are outputs plant. A neural networks based dynamic integral sliding mode (NNDISMC) with output differentiator observer is developed considered class. NNDISMC approach utilizes differentiation higher derivative estimation to estimate functions which assumed unknown. Having estimated unknown derivatives uncertain functions, an manifold on states designed law proposed confirms enforcement across from very start process. The overall robustness controller guaranteed by using networks, in closed loop. loop stability analysis presented detail, asymptotic convergence system equilibrium confirmed. plays significant role electromechanical systems, such as robotic manipulators, unmanned air vehicles underwater vehicles. simulation results manipulator demonstrate effectiveness method.