An Improved Kernel Entropy Component Analysis for Damage Detection Under Environmental and Operational Variations

Environmental effects often trigger false alarms in vibration-based damage detection methods used for structural health monitoring (SHM). While conventional techniques like Principal Component Analysis (PCA) and cointegration have been somewhat effective in addressing this issue, challenges such as...

Full description

Saved in:
Bibliographic Details
Main Authors: Shuigen Hu, Jian Yang, Jiezhong Huang, Dongsheng Li, Cheng Li
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/5/1332
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850052637647437824
author Shuigen Hu
Jian Yang
Jiezhong Huang
Dongsheng Li
Cheng Li
author_facet Shuigen Hu
Jian Yang
Jiezhong Huang
Dongsheng Li
Cheng Li
author_sort Shuigen Hu
collection DOAJ
description Environmental effects often trigger false alarms in vibration-based damage detection methods used for structural health monitoring (SHM). While conventional techniques like Principal Component Analysis (PCA) and cointegration have been somewhat effective in addressing this issue, challenges such as measurement noise, nonlinear behavior, and non-Gaussian data distribution continue to affect their performance. To address these limitations, a novel damage detection method combining Variational Mode Decomposition (VMD) and Dynamic Kernel Entropy Component Analysis (DKECA) is proposed. The proposed method initially uses the VMD technique to remove seasonal patterns and noise from the modal frequencies. Subsequently, a DKECA model is constructed based on a time-delay data matrix, and the principal components that maximize the Rényi entropy in the high-dimensional space are selected. Using these principal components, a damage detector developed from the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mi>T</mi><mn>2</mn></msup></mrow></semantics></math></inline-formula> statistic is used to determine damage indices for SHM. The effectiveness of the proposed method is verified through both a simulated 7-DOF model and real-world data from the Z24 bridge, with comparative studies highlighting its advantages over existing techniques.
format Article
id doaj-art-e2551afa36624301b8807d3d3af6b75b
institution DOAJ
issn 1424-8220
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-e2551afa36624301b8807d3d3af6b75b2025-08-20T02:52:45ZengMDPI AGSensors1424-82202025-02-01255133210.3390/s25051332An Improved Kernel Entropy Component Analysis for Damage Detection Under Environmental and Operational VariationsShuigen Hu0Jian Yang1Jiezhong Huang2Dongsheng Li3Cheng Li4Anhui Provincial International Joint Research Center of Data Diagnosis and Smart Maintenance on Bridge Structures, Chuzhou 239099, ChinaDepartment of Civil and Intelligent Construction Engineering, Shantou University, Shantou 515063, ChinaDepartment of Civil and Intelligent Construction Engineering, Shantou University, Shantou 515063, ChinaDepartment of Civil and Intelligent Construction Engineering, Shantou University, Shantou 515063, ChinaKey Laboratory for Health and Safety of Bridge Structures, Wuhan 430034, ChinaEnvironmental effects often trigger false alarms in vibration-based damage detection methods used for structural health monitoring (SHM). While conventional techniques like Principal Component Analysis (PCA) and cointegration have been somewhat effective in addressing this issue, challenges such as measurement noise, nonlinear behavior, and non-Gaussian data distribution continue to affect their performance. To address these limitations, a novel damage detection method combining Variational Mode Decomposition (VMD) and Dynamic Kernel Entropy Component Analysis (DKECA) is proposed. The proposed method initially uses the VMD technique to remove seasonal patterns and noise from the modal frequencies. Subsequently, a DKECA model is constructed based on a time-delay data matrix, and the principal components that maximize the Rényi entropy in the high-dimensional space are selected. Using these principal components, a damage detector developed from the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mi>T</mi><mn>2</mn></msup></mrow></semantics></math></inline-formula> statistic is used to determine damage indices for SHM. The effectiveness of the proposed method is verified through both a simulated 7-DOF model and real-world data from the Z24 bridge, with comparative studies highlighting its advantages over existing techniques.https://www.mdpi.com/1424-8220/25/5/1332structural health monitoringdamage detectionenvironmental and operational variationvariational mode decompositionprincipal component analysisgaussian process regression
spellingShingle Shuigen Hu
Jian Yang
Jiezhong Huang
Dongsheng Li
Cheng Li
An Improved Kernel Entropy Component Analysis for Damage Detection Under Environmental and Operational Variations
Sensors
structural health monitoring
damage detection
environmental and operational variation
variational mode decomposition
principal component analysis
gaussian process regression
title An Improved Kernel Entropy Component Analysis for Damage Detection Under Environmental and Operational Variations
title_full An Improved Kernel Entropy Component Analysis for Damage Detection Under Environmental and Operational Variations
title_fullStr An Improved Kernel Entropy Component Analysis for Damage Detection Under Environmental and Operational Variations
title_full_unstemmed An Improved Kernel Entropy Component Analysis for Damage Detection Under Environmental and Operational Variations
title_short An Improved Kernel Entropy Component Analysis for Damage Detection Under Environmental and Operational Variations
title_sort improved kernel entropy component analysis for damage detection under environmental and operational variations
topic structural health monitoring
damage detection
environmental and operational variation
variational mode decomposition
principal component analysis
gaussian process regression
url https://www.mdpi.com/1424-8220/25/5/1332
work_keys_str_mv AT shuigenhu animprovedkernelentropycomponentanalysisfordamagedetectionunderenvironmentalandoperationalvariations
AT jianyang animprovedkernelentropycomponentanalysisfordamagedetectionunderenvironmentalandoperationalvariations
AT jiezhonghuang animprovedkernelentropycomponentanalysisfordamagedetectionunderenvironmentalandoperationalvariations
AT dongshengli animprovedkernelentropycomponentanalysisfordamagedetectionunderenvironmentalandoperationalvariations
AT chengli animprovedkernelentropycomponentanalysisfordamagedetectionunderenvironmentalandoperationalvariations
AT shuigenhu improvedkernelentropycomponentanalysisfordamagedetectionunderenvironmentalandoperationalvariations
AT jianyang improvedkernelentropycomponentanalysisfordamagedetectionunderenvironmentalandoperationalvariations
AT jiezhonghuang improvedkernelentropycomponentanalysisfordamagedetectionunderenvironmentalandoperationalvariations
AT dongshengli improvedkernelentropycomponentanalysisfordamagedetectionunderenvironmentalandoperationalvariations
AT chengli improvedkernelentropycomponentanalysisfordamagedetectionunderenvironmentalandoperationalvariations