66608

Автор(ы): 

Автор(ов): 

3

Параметры публикации

Тип публикации: 

Статья в журнале/сборнике

Название: 

Differential neural network approximation of positive systems: An asymmetric barrier Lyapunov functions approach for learning laws design

DOI: 

10.1016/j.neucom.2021.06.056

Наименование источника: 

  • Neurocomputing

Обозначение и номер тома: 

Vol. 457

Город: 

  • Netherlands

Издательство: 

  • Elsevier BV

Год издания: 

2021

Страницы: 

128-140
Аннотация
The aim of this study is to design a non-parametric identifier based on Differential Neural Networks (DNNs) for a class of positive systems described by uncertain mathematical models. The inclusion of state constraints and the existence of equilibrium points outside the origin are considered in the design of the non-parametric identifier with the implementation of asymmetric barrier Lyapunov functions. The application of a stability analysis yields the design of learning laws for the weights adjustment. A class of hybrid learning laws depending on the relative difference of each state with respect to its corresponding component of the equilibrium point provides the ability of handling the positiveness of all the states, which is ensured considering he implementation of non-linear state dependent gains. A numerical example confirms the efficiency of the proposed state non-parametric identifier in the presence of bounded noises and perturbations affecting the dynamics of the evaluated positive systems. The example corresponds to a pharmaceutical compartmental system which reproduces the immunotherapy dynamics for the cancer treatment. The comparison of the proposed DDN approximated model with the classical non-barrier identifier confirms the ability of reproducing positive systems trajectories satisfying state constraints.

Библиографическая ссылка: 

Андрианова О.Г., Позняк А.С., Чаирез И.О. Differential neural network approximation of positive systems: An asymmetric barrier Lyapunov functions approach for learning laws design // Neurocomputing. 2021. Vol. 457. С. 128-140.