A Unified Surrogate Framework for Data-Driven Reliability Analysis of Mechanical Systems from Low to Multi-DOF

This paper proposes a unified reliability analysis framework for mechanical and structural systems equipped with Tuned Mass Dampers (TMDs), encompassing single-degree-of-freedom (1-DOF), two-degrees-of-freedom (2-DOF), and ten-degrees-of-freedom (10-DOF) configurations. The methodology integrates fo...

Full description

Saved in:
Bibliographic Details
Main Authors: Lun Shao, Alexandre Saidi, Abdel-Malek Zine, Mohamed Ichchou
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Vibration
Subjects:
Online Access:https://www.mdpi.com/2571-631X/8/1/7
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849339627180130304
author Lun Shao
Alexandre Saidi
Abdel-Malek Zine
Mohamed Ichchou
author_facet Lun Shao
Alexandre Saidi
Abdel-Malek Zine
Mohamed Ichchou
author_sort Lun Shao
collection DOAJ
description This paper proposes a unified reliability analysis framework for mechanical and structural systems equipped with Tuned Mass Dampers (TMDs), encompassing single-degree-of-freedom (1-DOF), two-degrees-of-freedom (2-DOF), and ten-degrees-of-freedom (10-DOF) configurations. The methodology integrates four main components: (i) probabilistic uncertainty modeling for mass, damping, and stiffness, (ii) Latin Hypercube Sampling (LHS) to efficiently explore parameter variations, (iii) Monte Carlo simulation (MCS) for estimating failure probabilities under stochastic excitations, and (iv) machine learning models, including Random Forest (RF), Gradient Boosting (GB), Extreme Gradient Boosting (XGBoost), and Neural Networks (NNs), to predict structural responses and failure probabilities. The results demonstrate that ensemble methods, such as RF and XGBoost, provide high accuracy and can effectively identify important features. Neural Networks perform well for capturing nonlinear behavior, although careful tuning is required to prevent overfitting. The framework is further extended to a 10-DOF structure, and the simulation results confirm that machine learning-based models are highly effective for large-scale reliability analysis. These findings highlight the synergy between simulation methods and data-driven models in enhancing the reliability of TMD systems under uncertain inputs.
format Article
id doaj-art-69c6d43bcbad43d9b76981dcf6e36ae0
institution Kabale University
issn 2571-631X
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Vibration
spelling doaj-art-69c6d43bcbad43d9b76981dcf6e36ae02025-08-20T03:44:05ZengMDPI AGVibration2571-631X2025-02-0181710.3390/vibration8010007A Unified Surrogate Framework for Data-Driven Reliability Analysis of Mechanical Systems from Low to Multi-DOFLun Shao0Alexandre Saidi1Abdel-Malek Zine2Mohamed Ichchou3Laboratory of Tribology and Dynamics of Systems, Ecole Centrale Lyon, 69130 Ecully, FranceComputer Science Laboratory for Image Processing and Information Systems, Ecole Centrale Lyon, 69134 Ecully, FranceInstitut Camille Jordan, Ecole Centrale de Lyon, 69134 Ecully, FranceLaboratory of Tribology and Dynamics of Systems, Ecole Centrale Lyon, 69130 Ecully, FranceThis paper proposes a unified reliability analysis framework for mechanical and structural systems equipped with Tuned Mass Dampers (TMDs), encompassing single-degree-of-freedom (1-DOF), two-degrees-of-freedom (2-DOF), and ten-degrees-of-freedom (10-DOF) configurations. The methodology integrates four main components: (i) probabilistic uncertainty modeling for mass, damping, and stiffness, (ii) Latin Hypercube Sampling (LHS) to efficiently explore parameter variations, (iii) Monte Carlo simulation (MCS) for estimating failure probabilities under stochastic excitations, and (iv) machine learning models, including Random Forest (RF), Gradient Boosting (GB), Extreme Gradient Boosting (XGBoost), and Neural Networks (NNs), to predict structural responses and failure probabilities. The results demonstrate that ensemble methods, such as RF and XGBoost, provide high accuracy and can effectively identify important features. Neural Networks perform well for capturing nonlinear behavior, although careful tuning is required to prevent overfitting. The framework is further extended to a 10-DOF structure, and the simulation results confirm that machine learning-based models are highly effective for large-scale reliability analysis. These findings highlight the synergy between simulation methods and data-driven models in enhancing the reliability of TMD systems under uncertain inputs.https://www.mdpi.com/2571-631X/8/1/7structural reliabilitytuned mass dampermachine learningmulti-degree-of-freedomsurrogate modeling
spellingShingle Lun Shao
Alexandre Saidi
Abdel-Malek Zine
Mohamed Ichchou
A Unified Surrogate Framework for Data-Driven Reliability Analysis of Mechanical Systems from Low to Multi-DOF
Vibration
structural reliability
tuned mass damper
machine learning
multi-degree-of-freedom
surrogate modeling
title A Unified Surrogate Framework for Data-Driven Reliability Analysis of Mechanical Systems from Low to Multi-DOF
title_full A Unified Surrogate Framework for Data-Driven Reliability Analysis of Mechanical Systems from Low to Multi-DOF
title_fullStr A Unified Surrogate Framework for Data-Driven Reliability Analysis of Mechanical Systems from Low to Multi-DOF
title_full_unstemmed A Unified Surrogate Framework for Data-Driven Reliability Analysis of Mechanical Systems from Low to Multi-DOF
title_short A Unified Surrogate Framework for Data-Driven Reliability Analysis of Mechanical Systems from Low to Multi-DOF
title_sort unified surrogate framework for data driven reliability analysis of mechanical systems from low to multi dof
topic structural reliability
tuned mass damper
machine learning
multi-degree-of-freedom
surrogate modeling
url https://www.mdpi.com/2571-631X/8/1/7
work_keys_str_mv AT lunshao aunifiedsurrogateframeworkfordatadrivenreliabilityanalysisofmechanicalsystemsfromlowtomultidof
AT alexandresaidi aunifiedsurrogateframeworkfordatadrivenreliabilityanalysisofmechanicalsystemsfromlowtomultidof
AT abdelmalekzine aunifiedsurrogateframeworkfordatadrivenreliabilityanalysisofmechanicalsystemsfromlowtomultidof
AT mohamedichchou aunifiedsurrogateframeworkfordatadrivenreliabilityanalysisofmechanicalsystemsfromlowtomultidof
AT lunshao unifiedsurrogateframeworkfordatadrivenreliabilityanalysisofmechanicalsystemsfromlowtomultidof
AT alexandresaidi unifiedsurrogateframeworkfordatadrivenreliabilityanalysisofmechanicalsystemsfromlowtomultidof
AT abdelmalekzine unifiedsurrogateframeworkfordatadrivenreliabilityanalysisofmechanicalsystemsfromlowtomultidof
AT mohamedichchou unifiedsurrogateframeworkfordatadrivenreliabilityanalysisofmechanicalsystemsfromlowtomultidof