$\mathrm{H}_{\infty}$ Tracking Control Design for Nonlinear Uncertain Systems

The proposed work presents associate H-infinity adaptive control design exploitation back propagation neural networks associated radial basis operate for systems whose uncertainty has an indefinite structure. This design merges ideas from robust control theory like H-infinity control style, the Small Gain Theorem, associated L stability theory with Lyapunov stability theory and up to date theoretical achievements in adaptive control to develop an adaptation design for systems whose uncertainty satisfies a neighborhood carver certain. The technique permits an impression designer to shorten the adaptation standardization method, band limit the adaptation management signal, and treats unmatched uncertainty during a single style framework. During this paper the performance of H-infinity controller is compared by exploitation back propagation neural network and radial basis operate neural network. The achieved result shows that the controller with BPNN provided higher result as compared to controller with radial basis operates. These two comparisons are accomplished.