Early damage assessment in large-scale structures by innovative statistical pattern recognition methods based on time series modeling and novelty detection

Entezami, Alireza; Shariatmadar, Hashem; Mariani, Stefano

doi:10.1016/j.advengsoft.2020.102923

Cited by 63 publications

(23 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generally, a classical SHM strategy relies on analyzing dynamic information (e.g., acceleration time series [5,6], modal data [7,8], both of them [9], etc.) acquired from contact-based sensors [10,11].…”

Section: Introductionmentioning

confidence: 99%

Detection of Partially Structural Collapse Using Long-Term Small Displacement Data from Satellite Images

Entezami

Michele

Arslan

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

The development of satellite sensors and interferometry synthetic aperture radar (InSAR) technology has enabled the exploitation of their benefits for long-term structural health monitoring (SHM). However, some restrictions cause this process to provide a small number of images leading to the problem of small data for SAR-based SHM. Conversely, the major challenge of the long-term monitoring of civil structures pertains to variations in their inherent properties by environmental and/or operational variability. This article aims to propose new hybrid unsupervised learning methods for addressing these challenges. The methods in this work contain three main parts: (i) data augmentation by the Markov Chain Monte Carlo algorithm, (ii) feature normalization, and (iii) decision making via Mahalanobis-squared distance. The first method presented in this work develops an artificial neural network-based feature normalization by proposing an iterative hyperparameter selection of hidden neurons of the network. The second method is a novel unsupervised teacher–student learning by combining an undercomplete deep neural network and an overcomplete single-layer neural network. A small set of long-term displacement samples extracted from a few SAR images of TerraSAR-X is applied to validate the proposed methods. The results show that the methods can effectively deal with the major challenges in the SAR-based SHM applications.

show abstract

Section: Introductionmentioning

confidence: 99%

Detection of Partially Structural Collapse Using Long-Term Small Displacement Data from Satellite Images

Entezami

Michele

Arslan

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Once damage-sensitive features have been extracted from the dataset, the final step of a data-driven SHM method is to analyze the features themselves for decision-making, providing outcomes in terms of early damage detection, localization, and quantification. At this stage, different techniques can be adopted, including statistical distance metrics (e.g., the Mahalanobis distance [ 23 , 24 ] or the Kullback–Leibler divergence [ 10 , 21 , 25 ]), Bayesian approaches [ 26 , 27 ], artificial neural networks [ 28 , 29 ], principal component analysis [ 30 , 31 ], and clustering [ 32 , 33 , 34 ]. In spite of their applicability, they may not perform efficiently when damage-sensitive features are of a high-dimensional nature, namely in the presence of big data to process; this leads to a time-consuming and unreliable decision-making process [ 10 , 35 ].…”

Section: Introductionmentioning

confidence: 99%

Health Monitoring of Large-Scale Civil Structures: An Approach Based on Data Partitioning and Classical Multidimensional Scaling

Entezami

Sarmadi

Behkamal

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

A major challenge in structural health monitoring (SHM) is the efficient handling of big data, namely of high-dimensional datasets, when damage detection under environmental variability is being assessed. To address this issue, a novel data-driven approach to early damage detection is proposed here. The approach is based on an efficient partitioning of the dataset, gathering the sensor recordings, and on classical multidimensional scaling (CMDS). The partitioning procedure aims at moving towards a low-dimensional feature space; the CMDS algorithm is instead exploited to set the coordinates in the mentioned low-dimensional space, and define damage indices through norms of the said coordinates. The proposed approach is shown to efficiently and robustly address the challenges linked to high-dimensional datasets and environmental variability. Results related to two large-scale test cases are reported: the ASCE structure, and the Z24 bridge. A high sensitivity to damage and a limited (if any) number of false alarms and false detections are reported, testifying the efficacy of the proposed data-driven approach.

show abstract

“…Among data-driven approaches, we can distinguish supervised [11] and unsupervised [12,13,14,15,16] methods. Supervised methods employ labeled data referring both to the undamaged condition, assumed as baseline, and to the damage scenarios possibly affecting the structure.…”

Section: Introductionmentioning

confidence: 99%

Online structural health monitoring by model order reduction and deep learning algorithms

Rosafalco¹,

Torzoni²,

Manzoni³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Within a structural health monitoring (SHM) framework, we propose a simulationbased classification strategy to move towards online damage localization. The procedure combines parametric Model Order Reduction (MOR) techniques and Fully Convolutional Networks (FCNs) to analyze raw vibration measurements recorded on the monitored structure. First, a dataset of possible structural responses under varying operational conditions is built through a physics-based model, allowing for a finite set of predefined damage scenarios. Then, the dataset is used for the offline training of the FCN. Because of the extremely large number of model evaluations required by the dataset construction, MOR techniques are employed to reduce the computational burden. The trained classifier is shown to be able to map unseen vibrational recordings, e.g. collected on-the-fly from sensors placed on the structure, to the actual damage state, thus providing information concerning the presence and also the location of damage. The proposed strategy has been validated by means of two case studies, concerning a 2D portal frame and a 3D portal frame railway bridge; MOR techniques have allowed us to respectively speed up the analyses about 30 and 420 times. For both the case studies, after training the classifier has attained an accuracy greater than 85%.

show abstract

Early damage assessment in large-scale structures by innovative statistical pattern recognition methods based on time series modeling and novelty detection

Cited by 63 publications

References 50 publications

Detection of Partially Structural Collapse Using Long-Term Small Displacement Data from Satellite Images

Detection of Partially Structural Collapse Using Long-Term Small Displacement Data from Satellite Images

Health Monitoring of Large-Scale Civil Structures: An Approach Based on Data Partitioning and Classical Multidimensional Scaling

Online structural health monitoring by model order reduction and deep learning algorithms

Contact Info

Product

Resources

About