Approach to adaptive neural net-based H∞ control design

An approach is investigated for the adaptive neural net-based H _∞ control design of a class of nonlinear uncertain systems. In the proposed framework, two multilayer feedforward neural networks are constructed as an alternative to approximate the nonlinear system. The neural networks are piecewisely interpolated to generate a linear differential inclusion model by which a linear state feedback H _∞ control law can be applied. An adaptive weight adjustment mechanism for the multilayer feedforward neural networks is developed to ensure H_∞ regulation performance. It is shown that finding the control gain matrices can be transformed into a standard linear matrix inequality problem and solved via a developed recurrent neural network