Enregistré dans:
Détails bibliographiques
Auteurs principaux: Lan, Jianglin, Zhan, Siyuan, Patton, Ron, Zhao, Xianxian
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2403.16132
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914727374880768
author Lan, Jianglin
Zhan, Siyuan
Patton, Ron
Zhao, Xianxian
author_facet Lan, Jianglin
Zhan, Siyuan
Patton, Ron
Zhao, Xianxian
contents There is an emerging trend in applying deep learning methods to control complex nonlinear systems. This paper considers enhancing the runtime safety of nonlinear systems controlled by neural networks in the presence of disturbance and measurement noise. A robustly stable interval observer is designed to generate sound and precise lower and upper bounds for the neural network, nonlinear function, and system state. The obtained interval is utilised to monitor the real-time system safety and detect faults in the system outputs or actuators. An adaptive cruise control vehicular system is simulated to demonstrate effectiveness of the proposed design.
format Preprint
id arxiv_https___arxiv_org_abs_2403_16132
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Runtime Monitoring and Fault Detection for Neural Network-Controlled Systems
Lan, Jianglin
Zhan, Siyuan
Patton, Ron
Zhao, Xianxian
Systems and Control
Machine Learning
There is an emerging trend in applying deep learning methods to control complex nonlinear systems. This paper considers enhancing the runtime safety of nonlinear systems controlled by neural networks in the presence of disturbance and measurement noise. A robustly stable interval observer is designed to generate sound and precise lower and upper bounds for the neural network, nonlinear function, and system state. The obtained interval is utilised to monitor the real-time system safety and detect faults in the system outputs or actuators. An adaptive cruise control vehicular system is simulated to demonstrate effectiveness of the proposed design.
title Runtime Monitoring and Fault Detection for Neural Network-Controlled Systems
topic Systems and Control
Machine Learning
url https://arxiv.org/abs/2403.16132