scholarly journals Learning Damage Representations with Sequence-to-Sequence Models

Sensors ◽  
2022 ◽  
Vol 22 (2) ◽  
pp. 452
Author(s):  
Qun Yang ◽  
Dejian Shen
Keyword(s):  
Damage Detection ◽  
Health Monitoring ◽  
Research Community ◽  
Regions Of Interest ◽  
Data Driven ◽  
Economic Losses ◽  
Shake Table ◽  
Learning Models ◽  
Shake Table Tests ◽  
Damage States

Natural hazards have caused damages to structures and economic losses worldwide. Post-hazard responses require accurate and fast damage detection and assessment. In many studies, the development of data-driven damage detection within the research community of structural health monitoring has emerged due to the advances in deep learning models. Most data-driven models for damage detection focus on classifying different damage states and hence damage states cannot be effectively quantified. To address such a deficiency in data-driven damage detection, we propose a sequence-to-sequence (Seq2Seq) model to quantify a probability of damage. The model was trained to learn damage representations with only undamaged signals and then quantify the probability of damage by feeding damaged signals into models. We tested the validity of our proposed Seq2Seq model with a signal dataset which was collected from a two-story timber building subjected to shake table tests. Our results show that our Seq2Seq model has a strong capability of distinguishing damage representations and quantifying the probability of damage in terms of highlighting the regions of interest.

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

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1646
Author(s):  
Alireza Entezami ◽  
Hassan Sarmadi ◽  
Behshid Behkamal ◽  
Stefano Mariani
Keyword(s):  
Multidimensional Scaling ◽  
Damage Detection ◽  
Health Monitoring ◽  
Large Scale ◽  
Environmental Variability ◽  
Data Driven ◽  
High Dimensional ◽  
Data Driven Approach ◽  
Low Dimensional ◽  
High Dimensional Datasets

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.

scholarly journals Identification and Compensation Technique of Non-Uniform Temperature Field for Lamb Wave-and Multiple Sensors-Based Damage Detection

Sensors ◽  
2019 ◽  
Vol 19 (13) ◽  
pp. 2930 ◽  
Author(s):  
Hu Sun ◽  
Junyan Yi ◽  
Yu Xu ◽  
Yishou Wang ◽  
Xinlin Qing
Keyword(s):  
Temperature Field ◽  
Structural Health Monitoring ◽  
Damage Detection ◽  
Health Monitoring ◽  
Lamb Wave ◽  
Temperature Compensation ◽  
Data Driven ◽  
Uniform Temperature ◽  
Uniform Temperature Field ◽  
Compensation Technique

Lamb wave-based damage detection for large-scale composites is one of the most prosperous structural health monitoring technologies for aircraft structures. However, the temperature has a significant effect on the amplitude and phase of the Lamb wave signal so that temperature compensation is always the focus problem. Especially, it is difficult to identify the damage in the aircraft structures when the temperature is not uniform. In this paper, a compensation method for Lamb wave-based damage detection within a non-uniform temperature field is proposed. Hilbert transform and Levenberg-Marquardt optimization algorithm are developed to extract the amplitude and phase variation caused by the change of temperature, which is used to establish a data-driven model for reconstructing the reference signal at a certain temperature. In the temperature compensation process, the current Lamb wave signal of each exciting-sensing path under the estimated structural condition is substituted into the data-driven model to identify an interpolated initial temperature field, which is further processed by an outlier removing algorithm to eliminate the effect of damage and get the actual non-uniform temperature field. Temperature compensation can be achieved by reconstructing the reference signals within the identified non-uniform temperature field, which are used to compare with the current acquired signals for damage imaging. Both simulation and experiment were conducted to verify the feasibility and effectiveness of the proposed non-uniform temperature field identification and compensation technique for Lamb wave-based structural health monitoring.

Full-Scale Structural and Nonstructural Building System Performance during Earthquakes: Part II – NCS Damage States

2016 ◽  
Vol 32 (2) ◽  
pp. 771-794 ◽  
Author(s):  
Elide Pantoli ◽  
Michelle C. Chen ◽  
Xiang Wang ◽  
Rodrigo Astroza ◽  
Hamed Ebrahimian ◽  
...  
Keyword(s):  
Full Scale ◽  
System Level ◽  
Economic Losses ◽  
Shake Table Tests ◽  
Nonstructural Components ◽  
Financial Investment ◽  
Nonstructural Systems ◽  
Damage States ◽  
Broad Variety ◽  
Unique Dataset

Nonstructural components and systems (NCSs) provide little to no load bearing capacity to a building; however, they are essential to support its operability. As a result, 75–85% of the initial building financial investment is associated with these elements. The vulnerability of NCSs even during low intensity earthquakes is repeatedly exposed, resulting in large economic losses, disruption of building functionality, and concerns for life safety. This paper describes and classifies damage to NCSs observed during landmark shake table tests of a full-scale five-story reinforced concrete building furnished with a broad variety of NCSs. This system-level test program provides a unique dataset due to the completeness and complexity of the investigated NCSs. Results highlight that the interactions between disparate nonstructural systems, in particular displacement compatibility, as well as the interactions between the NCSs and the building structure often govern their seismic performance.

scholarly journals Stayed-Cable Bridge Damage Detection and Localization Based on Accelerometer Health Monitoring Measurements

2015 ◽  
Vol 2015 ◽  
pp. 1-11 ◽  
Author(s):  
Mosbeh R. Kaloop ◽  
Jong Wan Hu
Keyword(s):  
Structural Health Monitoring ◽  
Damage Detection ◽  
Health Monitoring ◽  
Model Identification ◽  
Main Idea ◽  
Response Spectra ◽  
Structural Health ◽  
Damage States ◽  
Bridge Damage ◽  
Detection And Localization

In situ damage detection and localization using real acceleration structural health monitoring technique are the main idea of this study. The statistical and model identification time series, the response spectra, and the power density of the frequency domain are used to detect the behavior of Yonghe cable-stayed bridge during the healthy and damage states. The benchmark problem is used to detect the damage localization of the bridge during its working time. The assessment of the structural health monitoring and damage analysis concluded that (1) the kurtosis statistical moment can be used as an indicator for damage especially with increasing its percentage of change as the damage should occur; (2) the percentage of change of the Kernel density probability for the model identification error estimation can detect and localize the damage; (3) the simplified spectrum of the acceleration-displacement responses and frequencies probability changes are good tools for detection and localization of the one-line bridge damage.

Sign in / Sign up

Export Citation Format

Share Document