| Abstract
| - A nonlinear control strategy involving a geometric feedback controller utilizing linearized modelsand neural networks, approximating the higher order terms, is presented. Online adaptation ofthe network is performed using steepest descent with a dead zone function. Closed-loop Lyapunovstability analysis for this system has been proven, where it was shown that the output trackingerror was confined to a region of a ball, the size of which depends on the accuracy of the neuralnetwork models. The proposed strategy is applied to two case studies for set-point tracking anddisturbance rejection. The results show good tracking comparable to that when the actual modelof the plant is utilized and better than that obtained when the linearized models or neuralnetworks are used alone. A comparison was also made with the conventional proportional−integral−derivative approach.
|
