Multilayer recurrent neural networks for real-time robust pole assignment

Robust pole assignment is an effective design method for linear control systems subject to parameter perturbation. In this paper, two multilayer recurrent neural networks are presented for robust pole assignment. One of them is called state-independent annealing neural network (SIANN) and the other is called state-dependent annealing neural network (SDANN). The proposed recurrent neural networks are composed of three layers and are shown to be capable of synthesizing linear control systems via robust pole assignment in real time. The SDANN is proven to converge for any design parameters. Moreover, the neural network converges exponentially to an optimal solution of the robust pole assignment problem and the perturbed closed-loop control system based on the neural network is globally exponentially stable with appropriate design parameters. These desirable properties make it possible to apply the neural network to slowly time-varying linear control systems. Simulation results are shown to illustrate the effectiveness, advantages, and operating characteristics of the proposed approach.