A Neural-Fuzzy Approach for Fault Diagnosis of Hybrid Dynamical Systems: Demonstration on Three-Tank System

A Neural-Fuzzy Approach for Fault Diagnosis of Hybrid Dynamical Systems: Demonstration on Three-Tank System

This work is part of the diagnostic field of hybrid dynamic systems (HDS) whose objective is to ensure proper operation of industrial facilities. The study is initially oriented to the modelling approach dedicated to hybrid dynamical systems (HDS). The objective is to look for an adequate model enco...

Full description

Bibliographic Details
Main Authors: Achbi Mohammed Said, Kechida Sihem, Mhamdi Lotfi, Dhouibi Hedi
Format: Article
Language:English
Published: Sciendo 2021-03-01
Series:Acta Mechanica et Automatica
Subjects:
hybrid dynamic systems
modelling
residual generation and evaluation
monitoring
fault diagnosis
neural-fuzzy approach
Online Access:https://doi.org/10.2478/ama-2021-0001
id doaj-94a14deea8e74ddf9f9cf282dfcef93c
record_format Article
spelling doaj-94a14deea8e74ddf9f9cf282dfcef93c2021-09-06T19:41:07ZengSciendoActa Mechanica et Automatica 2300-53192021-03-011511810.2478/ama-2021-0001A Neural-Fuzzy Approach for Fault Diagnosis of Hybrid Dynamical Systems: Demonstration on Three-Tank SystemAchbi Mohammed Said0Kechida Sihem1Mhamdi Lotfi2Dhouibi Hedi3Laboratoire d’Automatique et Informatique de Guelma (LAIG), Université 8 Mai 1945 Guelma, BP 401, Guelma24000, AlgérieLaboratoire d’Automatique et Informatique de Guelma (LAIG), Université 8 Mai 1945 Guelma, BP 401, Guelma24000, AlgérieLaboratory of Automatic Signal and Image Processing (LARATSI), National School of Engineers of Monastir, University of Monastir, 5019, TunisiaLaboratory of Automatic Signal and Image Processing (LARATSI), National School of Engineers of Monastir, University of Monastir, 5019, TunisiaThis work is part of the diagnostic field of hybrid dynamic systems (HDS) whose objective is to ensure proper operation of industrial facilities. The study is initially oriented to the modelling approach dedicated to hybrid dynamical systems (HDS). The objective is to look for an adequate model encompassing both aspects (continuous and event). Then, fault diagnosis technique is synthesised using artificial intelligence (AI) techniques. The idea is to introduce a hybrid version combining neural networks and fuzzy logic for residual generation and evaluation. The proposed approach is then validated on three tank system. The modelling and diagnosis approaches are developed using MATLAB/Simulink environment.https://doi.org/10.2478/ama-2021-0001hybrid dynamic systemsmodellingresidual generation and evaluationmonitoringfault diagnosisneural-fuzzy approach
collection DOAJ
language English
format Article
sources DOAJ
author Achbi Mohammed Said
Kechida Sihem
Mhamdi Lotfi
Dhouibi Hedi
spellingShingle Achbi Mohammed Said
Kechida Sihem
Mhamdi Lotfi
Dhouibi Hedi
A Neural-Fuzzy Approach for Fault Diagnosis of Hybrid Dynamical Systems: Demonstration on Three-Tank System
Acta Mechanica et Automatica
hybrid dynamic systems
modelling
residual generation and evaluation
monitoring
fault diagnosis
neural-fuzzy approach
author_facet Achbi Mohammed Said
Kechida Sihem
Mhamdi Lotfi
Dhouibi Hedi
author_sort Achbi Mohammed Said
title A Neural-Fuzzy Approach for Fault Diagnosis of Hybrid Dynamical Systems: Demonstration on Three-Tank System
title_short A Neural-Fuzzy Approach for Fault Diagnosis of Hybrid Dynamical Systems: Demonstration on Three-Tank System
title_full A Neural-Fuzzy Approach for Fault Diagnosis of Hybrid Dynamical Systems: Demonstration on Three-Tank System
title_fullStr A Neural-Fuzzy Approach for Fault Diagnosis of Hybrid Dynamical Systems: Demonstration on Three-Tank System
title_full_unstemmed A Neural-Fuzzy Approach for Fault Diagnosis of Hybrid Dynamical Systems: Demonstration on Three-Tank System
title_sort neural-fuzzy approach for fault diagnosis of hybrid dynamical systems: demonstration on three-tank system
publisher Sciendo
series Acta Mechanica et Automatica
issn 2300-5319
publishDate 2021-03-01
description This work is part of the diagnostic field of hybrid dynamic systems (HDS) whose objective is to ensure proper operation of industrial facilities. The study is initially oriented to the modelling approach dedicated to hybrid dynamical systems (HDS). The objective is to look for an adequate model encompassing both aspects (continuous and event). Then, fault diagnosis technique is synthesised using artificial intelligence (AI) techniques. The idea is to introduce a hybrid version combining neural networks and fuzzy logic for residual generation and evaluation. The proposed approach is then validated on three tank system. The modelling and diagnosis approaches are developed using MATLAB/Simulink environment.
topic hybrid dynamic systems
modelling
residual generation and evaluation
monitoring
fault diagnosis
neural-fuzzy approach
url https://doi.org/10.2478/ama-2021-0001
work_keys_str_mv AT achbimohammedsaid aneuralfuzzyapproachforfaultdiagnosisofhybriddynamicalsystemsdemonstrationonthreetanksystem
AT kechidasihem aneuralfuzzyapproachforfaultdiagnosisofhybriddynamicalsystemsdemonstrationonthreetanksystem
AT mhamdilotfi aneuralfuzzyapproachforfaultdiagnosisofhybriddynamicalsystemsdemonstrationonthreetanksystem
AT dhouibihedi aneuralfuzzyapproachforfaultdiagnosisofhybriddynamicalsystemsdemonstrationonthreetanksystem
AT achbimohammedsaid neuralfuzzyapproachforfaultdiagnosisofhybriddynamicalsystemsdemonstrationonthreetanksystem
AT kechidasihem neuralfuzzyapproachforfaultdiagnosisofhybriddynamicalsystemsdemonstrationonthreetanksystem
AT mhamdilotfi neuralfuzzyapproachforfaultdiagnosisofhybriddynamicalsystemsdemonstrationonthreetanksystem
AT dhouibihedi neuralfuzzyapproachforfaultdiagnosisofhybriddynamicalsystemsdemonstrationonthreetanksystem
_version_ 1717767014000361472

Similar Items