Building safety monitoring based on extreme gradient boosting in distributed optical fiber sensing

Huang, Lei; Li, Yingchun; Chen, Song; Zhang, Qianwu; Song, Yingxiong; Zhang, Junjie; Wang, Min

doi:10.1016/j.yofte.2020.102149

Cited by 21 publications

(13 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DAS was also the focus of Huang et al [ 168 ] who proposed a DOFS-based acoustic environmental safety monitoring scheme for the security of a building’s exterior glass walls/windows. In order to improve the accuracy of the disturbing event recognition, the authors suggested the use of the Wigner bispectrum analysis combined with an extreme gradient boosting tree algorithm.…”

Section: An Eye Towards the Futurementioning

confidence: 99%

A Review of Recent Distributed Optical Fiber Sensors Applications for Civil Engineering Structural Health Monitoring

Bado

Casas

2021

Sensors

240

View full text Add to dashboard Cite

The present work is a comprehensive collection of recently published research articles on Structural Health Monitoring (SHM) campaigns performed by means of Distributed Optical Fiber Sensors (DOFS). The latter are cutting-edge strain, temperature and vibration monitoring tools with a large potential pool, namely their minimal intrusiveness, accuracy, ease of deployment and more. Its most state-of-the-art feature, though, is the ability to perform measurements with very small spatial resolutions (as small as 0.63 mm). This review article intends to introduce, inform and advise the readers on various DOFS deployment methodologies for the assessment of the residual ability of a structure to continue serving its intended purpose. By collecting in a single place these recent efforts, advancements and findings, the authors intend to contribute to the goal of collective growth towards an efficient SHM. The current work is structured in a manner that allows for the single consultation of any specific DOFS application field, i.e., laboratory experimentation, the built environment (bridges, buildings, roads, etc.), geotechnical constructions, tunnels, pipelines and wind turbines. Beforehand, a brief section was constructed around the recent progress on the study of the strain transfer mechanisms occurring in the multi-layered sensing system inherent to any DOFS deployment (different kinds of fiber claddings, coatings and bonding adhesives). Finally, a section is also dedicated to ideas and concepts for those novel DOFS applications which may very well represent the future of SHM.

show abstract

Section: An Eye Towards the Futurementioning

confidence: 99%

A Review of Recent Distributed Optical Fiber Sensors Applications for Civil Engineering Structural Health Monitoring

Bado

Casas

2021

Sensors

240

View full text Add to dashboard Cite

show abstract

“…An overview of structural health monitoring using DAS was carried out in [ 109 ], which described applications for bridges, tunnels, pipes, geotechnical structures, and wind turbines. Some unusual applications of DAS can also be found ( Figure 13 ), e.g., for window glass monitoring [ 110 ]. The experimental results showed that the average recognition rate of the model for eight kinds of vibration events within the glass window was 93.3%.…”

Section: Das In the Engineering Sciences (Andrey A Zhirnov And Konsta...mentioning

confidence: 99%

Scientific Applications of Distributed Acoustic Sensing: State-of-the-Art Review and Perspective

Gorshkov

Yüksel

Fotiadi

et al. 2022

Sensors

View full text Add to dashboard Cite

This work presents a detailed review of the development of distributed acoustic sensors (DAS) and their newest scientific applications. It covers most areas of human activities, such as the engineering, material, and humanitarian sciences, geophysics, culture, biology, and applied mechanics. It also provides the theoretical basis for most well-known DAS techniques and unveils the features that characterize each particular group of applications. After providing a summary of research achievements, the paper develops an initial perspective of the future work and determines the most promising DAS technologies that should be improved.

show abstract

“…Many research works that combine DAS + PRS suffer from issues related to pattern classification design and experimental evaluation setups: real classification and results are not presented [45][46][47][48][49][50]; lack of details on both the system description and experimental conditions [25,[51][52][53][54][55][56][57][58][59]; data are not obtained in realistic field environments [15,25,49,[51][52][53]58,[60][61][62][63][64][65][66][67][68][69][70][71][72][73][74][75][76][77]; the lack of testing signals/classes to recognize [15,49,54,63,65,[69][70]…”

Section: Motivation and Organization Of This Papermentioning

confidence: 99%

A Multi-Position Approach in a Smart Fiber-Optic Surveillance System for Pipeline Integrity Threat Detection

et al. 2021

View full text Add to dashboard Cite

We present a new pipeline integrity surveillance system for long gas pipeline threat detection and classification. The system is based on distributed acoustic sensing with phase-sensitive optical time domain reflectometry (ϕ-OTDR) and pattern recognition for event classification. The proposal incorporates a multi-position approach in a Gaussian Mixture Model (GMM)-based pattern classification system which operates in a real-field scenario with a thorough experimental procedure. The objective is exploiting the availability of vibration-related data at positions nearby the one actually producing the main disturbance to improve the robustness of the trained models. The system integrates two classification tasks: (1) machine + activity identification, which identifies the machine that is working over the pipeline along with the activity being carried out, and (2) threat detection, which aims to detect suspicious threats for the pipeline integrity (independently of the activity being carried out). For the machine + activity identification mode, the multi-position approach for model training obtains better performance than the previously presented single-position approach for activities that show consistent behavior and high energy (between 6% and 11% absolute) with an overall increase of 3% absolute in the classification accuracy. For the threat detection mode, the proposed approach gets an 8% absolute reduction in the false alarm rate with an overall increase of 4.5% absolute in the classification accuracy.

show abstract

Building safety monitoring based on extreme gradient boosting in distributed optical fiber sensing

Cited by 21 publications

References 15 publications

A Review of Recent Distributed Optical Fiber Sensors Applications for Civil Engineering Structural Health Monitoring

A Review of Recent Distributed Optical Fiber Sensors Applications for Civil Engineering Structural Health Monitoring

Scientific Applications of Distributed Acoustic Sensing: State-of-the-Art Review and Perspective

A Multi-Position Approach in a Smart Fiber-Optic Surveillance System for Pipeline Integrity Threat Detection

Contact Info

Product

Resources

About