LMI-based neurocontroller for guaranteed cost control of uncertain time-delay systems

This paper considers the application of neural networks for the guaranteed cost control problem of discrete-time uncertain systems that have both state and input delays. In order to guarantee the stability of the closed-loop delay systems with the neurocontroller, the linear matrix inequality (LMI) condition is established, while the neurocontroller is used to reduce the cost of the uncertain time-delay systems caused by the LMI design parameter. The novel contribution is that the neurocontroller is substituted for the additive gain perturbations. It is newly shown that although the neurocontroller is included in the uncertain discrete-time delay systems, the robust stability for the closed-loop systems and the reduction of the cost are attained. Finally, a numerical example is given to verify the efficiency.