Application of Recurrent Neural Networks in Closed Loop Tracking Systems for Controlling Essentially Nonlinear Objects
Sergey V. Feofilov, Dmitry Khapkin · 2021 3rd International Conference on Control Systems, Mathematical Modeling, Automation and Energy Efficiency (SUMMA) · 2021
This paper describes the development of neural controllers based on recurrent neural networks for essentially nonlinear control objects. An algorithm for the synthesis of direct and inverse neural controllers is proposed.