2018
DOI: 10.1177/1475921718800306
|View full text |Cite
|
Sign up to set email alerts
|

Data-driven damage diagnosis under environmental and operational variability by novel statistical pattern recognition methods

Abstract: Feature extraction by time-series analysis and decision making through distance-based methods are powerful and efficient statistical pattern recognition techniques for data-driven structural health monitoring. The motivation of this article is to propose an innovative residual-based feature extraction approach based on AutoRegressive modeling and a novel statistical distance method named as Partition-based Kullback–Leibler Divergence for damage detection and localization by using randomly high-dimensional dama… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
5

Citation Types

0
56
0

Year Published

2019
2019
2022
2022

Publication Types

Select...
6
2
1

Relationship

4
5

Authors

Journals

citations
Cited by 77 publications
(56 citation statements)
references
References 41 publications
0
56
0
Order By: Relevance
“…1 Data-driven damage detection methods can provide a reliable solution to detect structural damage. [10][11][12][13] In the past decades, many data-driven methods using machine learning techniques have been developed for structural damage detection. [14][15][16] Feature extraction is typically a key element in these developed damage detection methods, and extracting appropriate damage-sensitive features is one of the critical components of specific damage detection problems.…”
Section: Introductionmentioning
confidence: 99%
“…1 Data-driven damage detection methods can provide a reliable solution to detect structural damage. [10][11][12][13] In the past decades, many data-driven methods using machine learning techniques have been developed for structural damage detection. [14][15][16] Feature extraction is typically a key element in these developed damage detection methods, and extracting appropriate damage-sensitive features is one of the critical components of specific damage detection problems.…”
Section: Introductionmentioning
confidence: 99%
“…Due to the direct use of measured data, the modern or data‐based methods are usually developed from the concept of statistical pattern recognition. Feature extraction and statistical decision making are two key parts of any data‐based method that significantly affect the SHM results 9 …”
Section: Introductionmentioning
confidence: 99%
“…Additionally, to deal with the randomly high-dimensional damage-sensitive features under environmental and operational variability, Entezami et al [46] proposed a feature extraction approach based on an AR model residual and a statistical distance method named partition-based Kullback Leibler Divergence (KLD) for damage detection. Zhou et al [47] combined a vector time-dependent autoregressive (TAR) model with a least squares support vector machine to identify the structural parameters for linear time-varying structural systems.…”
Section: Introductionmentioning
confidence: 99%