Robust control of uncertain nonlinear systems using adaptive regressive Neural-based deep learning technique

Abstract

In this paper, a novel adaptive Improved Global Regressive Neural Networks (Imp-GRNN) controller is developed, which provides novel improvement to the basic GRNN neural model. Proposed Imp-GRNN is designed to handle the multivariable uncertain nonlinear systems. The significant improvements of Imp-GRNN include the addition of a new output layer connected directly with the input layer via newly adaptable weights. Also, the Imp-GRNN input-hidden weights are designed to be adaptively auto-tuning instead of being static, as in most of the precedent adaptive neural controllers. Besides, a new smoothen coefficient σ is introduced to eradicate the requirement to set it beforehand or to adapt it online. The superiority of proposed Imp-GRNN method is proven quite perfect compared of GRNN and other advanced neural controllers as demonstrated via the two numerical benchmark test results.