Complex Approach to Synthesizing Neural Network Regulators for Unstable Nonlinear Control Objects

The use of neural network controllers in automatic control systems of complex nonlinear dynamic objects is an actual direction of development of modern control theory. The authors propose an approach based on the simultaneous synthesis of a neural network Lyapunov function with a controller that guarantees the stability of a closed-loop system. Unlike previous studies devoted to the synthesis of autonomous control systems, this paper presents a method for synthesizing tracking systems. An algorithm is also proposed to optimize the transient time. An example of controller synthesis for an unstable control object is considered