This contribution considers a new realization of the cognitive stabilizer, which is an adaptive stabilization control method based on a cognition-based framework. It is assumed, that the model of the system to be controlled is unknown. Only the knowledge about the system inputs, outputs, and equilibrium points are the preliminaries assumed within this approach. A new improved realization of the cognitive stabilizer is designed in this contribution using 1) a neural network estimating suitable inputs according to the desired outputs, 2) Lyapunov stability criterion according to a certain Lyapunov function, and 3) an optimization method to determine the desired system outputs with respect to the system energy. The proposed cognitive stabilizer is able to stabilize an unknown nonlinear MIMO system at arbitrary equilibrium point of it. Suitable control input can be designed automatically to guarantee the stability of motion of the system during the whole process although the changing of the system behavior or the environment. Numerical examples are shown to demonstrate the successful application and performance of this method.

This content is only available via PDF.
You do not currently have access to this content.