Robust Stability Analysis of Positive Lure System with Neural Network Feedback

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hedesh, Hamidreza Montazeri, Wafi, Moh. Kamalul, Shafai, Bahram, Siami, Milad
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911191028203520
author Hedesh, Hamidreza Montazeri
Wafi, Moh. Kamalul
Shafai, Bahram
Siami, Milad
author_facet Hedesh, Hamidreza Montazeri
Wafi, Moh. Kamalul
Shafai, Bahram
Siami, Milad
contents This paper investigates the robustness of the Lur'e problem under positivity constraints, drawing on results from the positive Aizerman conjecture and robustness properties of Metzler matrices. Specifically, we consider a control system of Lur'e type in which not only the linear part includes parametric uncertainty but also the nonlinear sector bound is unknown. We investigate tools from positive linear systems to effectively solve the problems in complicated and uncertain nonlinear systems. By leveraging the positivity characteristic of the system, we derive an explicit formula for the stability radius of Lur'e systems. Furthermore, we extend our analysis to systems with neural network (NN) feedback loops. Building on this approach, we also propose a refinement method for sector bounds of NNs. This study introduces a scalable and efficient approach for robustness analysis of both Lur'e and NN-controlled systems. Finally, the proposed results are supported by illustrative examples.
format Preprint
id arxiv_https___arxiv_org_abs_2505_18912
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Robust Stability Analysis of Positive Lure System with Neural Network Feedback
Hedesh, Hamidreza Montazeri
Wafi, Moh. Kamalul
Shafai, Bahram
Siami, Milad
Systems and Control
Artificial Intelligence
93D09, 93D20, 93C10, 68T07
B.1.3; G.1; I.2; I.2.3; I.2.8; I.2.1; J.2
This paper investigates the robustness of the Lur'e problem under positivity constraints, drawing on results from the positive Aizerman conjecture and robustness properties of Metzler matrices. Specifically, we consider a control system of Lur'e type in which not only the linear part includes parametric uncertainty but also the nonlinear sector bound is unknown. We investigate tools from positive linear systems to effectively solve the problems in complicated and uncertain nonlinear systems. By leveraging the positivity characteristic of the system, we derive an explicit formula for the stability radius of Lur'e systems. Furthermore, we extend our analysis to systems with neural network (NN) feedback loops. Building on this approach, we also propose a refinement method for sector bounds of NNs. This study introduces a scalable and efficient approach for robustness analysis of both Lur'e and NN-controlled systems. Finally, the proposed results are supported by illustrative examples.
title Robust Stability Analysis of Positive Lure System with Neural Network Feedback
topic Systems and Control
Artificial Intelligence
93D09, 93D20, 93C10, 68T07
B.1.3; G.1; I.2; I.2.3; I.2.8; I.2.1; J.2
url https://arxiv.org/abs/2505.18912