TY - JOUR
T1 - Differential neural network identifier with composite learning laws for uncertain nonlinear systems
AU - Guarneros, Alejandro
AU - Salgado, Ivan
AU - Mera, Manuel
AU - Ahmed, Hafiz
N1 - Publisher Copyright:
Copyright © 2020 The Authors.
PY - 2020
Y1 - 2020
N2 - This manuscript describes the design and numerical implementation of a novel composite differential neural network aimed to estimate nonlinear uncertain systems. A differential neural network (DNN) with a composite feedback matrix approximates the structure of non-linear uncertain systems. The feedback matrix is assumed to belong to a convex set as well as the free parameters of the DNN (weights) at any instant of time. Therefore, l-different DNN works in parallel. A composite Lyapunov function finds the convex hull approximation of the set of DNN working together to improve the approximation capabilities of classical neural networks. The main result of this study shows the practical stability of the estimation error. Numerical simulations demonstrate the approximation capabilities of the composite DNN implemented in a Van Der Pol oscillator where the presence of high-frequency components makes difficult a classical DNN approximation.
AB - This manuscript describes the design and numerical implementation of a novel composite differential neural network aimed to estimate nonlinear uncertain systems. A differential neural network (DNN) with a composite feedback matrix approximates the structure of non-linear uncertain systems. The feedback matrix is assumed to belong to a convex set as well as the free parameters of the DNN (weights) at any instant of time. Therefore, l-different DNN works in parallel. A composite Lyapunov function finds the convex hull approximation of the set of DNN working together to improve the approximation capabilities of classical neural networks. The main result of this study shows the practical stability of the estimation error. Numerical simulations demonstrate the approximation capabilities of the composite DNN implemented in a Van Der Pol oscillator where the presence of high-frequency components makes difficult a classical DNN approximation.
KW - Composite Lyapunov function
KW - Differential neural networks
KW - Nonlinear systems
KW - Uncertain systems
UR - http://www.scopus.com/inward/record.url?scp=85108025518&partnerID=8YFLogxK
U2 - 10.1016/j.ifacol.2020.12.1976
DO - 10.1016/j.ifacol.2020.12.1976
M3 - Artículo de la conferencia
AN - SCOPUS:85108025518
SN - 1474-6670
VL - 53
SP - 7897
EP - 7902
JO - IFAC-PapersOnLine
JF - IFAC-PapersOnLine
T2 - 21st IFAC World Congress 2020
Y2 - 12 July 2020 through 17 July 2020
ER -