Fault-tolerant Q-learning for discrete-time linear systems with actuator and sensor faults using input-output measured data

This study presents a novel output feedback Q-learning algorithm specifically designed for fault-tolerant control in real-time applications, circumventing the necessity for explicit system models or detailed actuator and sensor fault information. A significant benefit of this algorithm is its capabi...

Full description

Saved in:
Bibliographic Details
Main Authors: Mohammadrasoul Kankashvar, Sajad Rafiee, Hossein Bolandi
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:Franklin Open
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2773186325000490
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849423554914811904
author Mohammadrasoul Kankashvar
Sajad Rafiee
Hossein Bolandi
author_facet Mohammadrasoul Kankashvar
Sajad Rafiee
Hossein Bolandi
author_sort Mohammadrasoul Kankashvar
collection DOAJ
description This study presents a novel output feedback Q-learning algorithm specifically designed for fault-tolerant control in real-time applications, circumventing the necessity for explicit system models or detailed actuator and sensor fault information. A significant benefit of this algorithm is its capability to simultaneously achieve optimality and stabilize systems with both actuator and sensor faults. Unlike traditional methods, it learns online using input-output data from the faulty system, bypassing the need for full-state measurements. We develop a unique expression of the Fault-Tolerant Q-function (FTQF) in the input-output format and derive a model-free optimal output feedback fault-tolerant control (FTC) policy. Furthermore, the algorithm's real-time implementation process is detailed, showing its adaptability in acquiring optimal output feedback FTC policies without prior knowledge of system dynamics or faults. The proposed method remains unaffected by excitation noise bias, even without a discount factor, and guarantees closed-loop stability and convergence to optimal solutions. Validation through numerical simulations on an F-16 autopilot aircraft underscores its effectiveness.
format Article
id doaj-art-d40e344ef4e142bbb911ac843d6bcc81
institution Kabale University
issn 2773-1863
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series Franklin Open
spelling doaj-art-d40e344ef4e142bbb911ac843d6bcc812025-08-20T03:30:32ZengElsevierFranklin Open2773-18632025-06-011110025910.1016/j.fraope.2025.100259Fault-tolerant Q-learning for discrete-time linear systems with actuator and sensor faults using input-output measured dataMohammadrasoul Kankashvar0Sajad Rafiee1Hossein Bolandi2Corresponding author.; Department of Control Systems Engineering, Iran University of Science and Technology, Tehran 1684613114, IranDepartment of Control Systems Engineering, Iran University of Science and Technology, Tehran 1684613114, IranDepartment of Control Systems Engineering, Iran University of Science and Technology, Tehran 1684613114, IranThis study presents a novel output feedback Q-learning algorithm specifically designed for fault-tolerant control in real-time applications, circumventing the necessity for explicit system models or detailed actuator and sensor fault information. A significant benefit of this algorithm is its capability to simultaneously achieve optimality and stabilize systems with both actuator and sensor faults. Unlike traditional methods, it learns online using input-output data from the faulty system, bypassing the need for full-state measurements. We develop a unique expression of the Fault-Tolerant Q-function (FTQF) in the input-output format and derive a model-free optimal output feedback fault-tolerant control (FTC) policy. Furthermore, the algorithm's real-time implementation process is detailed, showing its adaptability in acquiring optimal output feedback FTC policies without prior knowledge of system dynamics or faults. The proposed method remains unaffected by excitation noise bias, even without a discount factor, and guarantees closed-loop stability and convergence to optimal solutions. Validation through numerical simulations on an F-16 autopilot aircraft underscores its effectiveness.http://www.sciencedirect.com/science/article/pii/S2773186325000490Reinforcement learningFault-tolerant controlActuator faultsSensor faultsOutput feedbackQ-learning
spellingShingle Mohammadrasoul Kankashvar
Sajad Rafiee
Hossein Bolandi
Fault-tolerant Q-learning for discrete-time linear systems with actuator and sensor faults using input-output measured data
Franklin Open
Reinforcement learning
Fault-tolerant control
Actuator faults
Sensor faults
Output feedback
Q-learning
title Fault-tolerant Q-learning for discrete-time linear systems with actuator and sensor faults using input-output measured data
title_full Fault-tolerant Q-learning for discrete-time linear systems with actuator and sensor faults using input-output measured data
title_fullStr Fault-tolerant Q-learning for discrete-time linear systems with actuator and sensor faults using input-output measured data
title_full_unstemmed Fault-tolerant Q-learning for discrete-time linear systems with actuator and sensor faults using input-output measured data
title_short Fault-tolerant Q-learning for discrete-time linear systems with actuator and sensor faults using input-output measured data
title_sort fault tolerant q learning for discrete time linear systems with actuator and sensor faults using input output measured data
topic Reinforcement learning
Fault-tolerant control
Actuator faults
Sensor faults
Output feedback
Q-learning
url http://www.sciencedirect.com/science/article/pii/S2773186325000490
work_keys_str_mv AT mohammadrasoulkankashvar faulttolerantqlearningfordiscretetimelinearsystemswithactuatorandsensorfaultsusinginputoutputmeasureddata
AT sajadrafiee faulttolerantqlearningfordiscretetimelinearsystemswithactuatorandsensorfaultsusinginputoutputmeasureddata
AT hosseinbolandi faulttolerantqlearningfordiscretetimelinearsystemswithactuatorandsensorfaultsusinginputoutputmeasureddata