Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
6.8
3.9
Journals
Sensors
Special Issues
Methods and Applications of Machine/Deep Learning for Structural Monitoring and...
sensors-logo
Submit to Sensors Review for Sensors Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Methods and Applications of Machine/Deep Learning for Structural Monitoring and Sensing

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Industrial Sensors".

Deadline for manuscript submissions: closed (15 August 2023) | Viewed by 2800

Special Issue Editors

Dr. Chia-Ming Chang

E-Mail Website
Guest Editor
Department of Civil Engineering, National Taiwan University, Taipei 10617, Taiwan
Interests: structural health monitoring; smart structures; structural control; advanced technologies for structural engineering
Prof. Dr. Tzu-Kang Lin

E-Mail Website
Guest Editor
Department of Civil Engineering, National Yang Ming Chiao Tung University, Hsinchu 30010, Taiwan
Interests: structural health monitoring; artificial intelligence; information theory; bridge engineering; smart structural control
Dr. Fernando Moreu

E-Mail Website
Guest Editor
Department Civil, Construction, and Environmental Engineering, University of New Mexico, Albuquerque, NM 87131, USA
Interests: structural health monitoring; wireless smart sensor networks; infrastructure management and policies; performance-based monitoring; augmented reality; human–machine interfaces and human cognition
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Advanced learning technologies have further extended the capability of structural sensing and monitoring for infrastructure. Structural-health monitoring aims to provide a more scientific solution to understanding the current performance of structures and to diagnosing structural deterioration before it becomes a catastrophic disaster. A combination of monitoring and sensing strategies is needed to fulfill this goal. Meanwhile, these strategies should address the uncertainties (i.e., modeling errors) and deviations (i.e., measurement noise and sensor faults) that may occur in a complex or large-scale structure. With the aid of machine-/deep-learning technologies, accurate decision making can be carried out by retrievable information and identifiable conditions in the built environment. Consequently, predictive maintenance and structural protection against hazards become realizable and practical.

This Special Issue provides the opportunities to gather studies addressing the theoretical, computational, and experimental methods and applications of machine/deep learning for structural monitoring and sensing. Topics include, but are not limited to:

  • Advanced sensing technologies and networks for structural-health monitoring;
  • Structural-health monitoring using machine learning;
  • Innovative neural network architectures for structural-health monitoring;
  • Damage diagnosis and prognosis;
  • Quantification and localization;
  • Early warning systems;
  • Sensor fault detection;
  • Computer vision approaches for structural identification, damage detection, and response measurement with machine learning;
  • Digital twins;
  • Artificial-intelligence-based inspection using UAVs and UGVs.

Dr. Chia-Ming Chang
Prof. Dr. Tzu-Kang Lin
Dr. Fernando Moreu
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • advanced sensing
  • structural-health monitoring
  • machine and deep learning
  • damage detection
  • artificial intelligence
  • SHM methods and applications

Published Papers (2 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

18 pages, 12568 KiB  
Article
Post Disaster Damage Assessment Using Ultra-High-Resolution Aerial Imagery with Semi-Supervised Transformers
by Deepank Kumar Singh and Vedhus Hoskere
Sensors 2023, 23(19), 8235; https://doi.org/10.3390/s23198235 - 03 Oct 2023
Cited by 1 | Viewed by 1513
Abstract
Preliminary damage assessments (PDA) conducted in the aftermath of a disaster are a key first step in ensuring a resilient recovery. Conventional door-to-door inspection practices are time-consuming and may delay governmental resource allocation. A number of research efforts have proposed frameworks to automate [...] Read more.
Preliminary damage assessments (PDA) conducted in the aftermath of a disaster are a key first step in ensuring a resilient recovery. Conventional door-to-door inspection practices are time-consuming and may delay governmental resource allocation. A number of research efforts have proposed frameworks to automate PDA, typically relying on data sources from satellites, unmanned aerial vehicles, or ground vehicles, together with data processing using deep convolutional neural networks. However, before such frameworks can be adopted in practice, the accuracy and fidelity of predictions of damage level at the scale of an entire building must be comparable to human assessments. Towards this goal, we propose a PDA framework leveraging novel ultra-high-resolution aerial (UHRA) images combined with state-of-the-art transformer models to make multi-class damage predictions of entire buildings. We demonstrate that semi-supervised transformer models trained with vast amounts of unlabeled data are able to surpass the accuracy and generalization capabilities of state-of-the-art PDA frameworks. In our series of experiments, we aim to assess the impact of incorporating unlabeled data, as well as the use of different data sources and model architectures. By integrating UHRA images and semi-supervised transformer models, our results suggest that the framework can overcome the significant limitations of satellite imagery and traditional CNN models, leading to more accurate and efficient damage assessments. Full article
(This article belongs to the Special Issue Methods and Applications of Machine/Deep Learning for Structural Monitoring and Sensing)
►▼ Show Figures

Figure 1

15 pages, 5400 KiB  
Article
Rail Corrugation Index Development by Sound-Field Excitation on the Carriage Floor of In-Service Train
by Wei-Lun Hsu and Chia-Ming Chang
Sensors 2023, 23(17), 7539; https://doi.org/10.3390/s23177539 - 30 Aug 2023
Viewed by 804
Abstract
The steel rail and wheel in the railway system offer a high precision and smooth-running surface. Nevertheless, the point of contact between the rail and wheel presents a critical area that can give rise to rail corrugation. This phenomenon can potentially elevate sound [...] Read more.
The steel rail and wheel in the railway system offer a high precision and smooth-running surface. Nevertheless, the point of contact between the rail and wheel presents a critical area that can give rise to rail corrugation. This phenomenon can potentially elevate sound and vibration levels in the vicinity considerably, necessitating advanced monitoring and assessment measures. Recently, many efforts have been directed towards utilizing in-service trains for evaluating rail corrugation, and the evaluation has primarily relied on axle-box acceleration (ABA). However, the ABA measurements require a higher threshold for vibration detection. This study introduces a novel approach to rail corrugation detection by carriage floor acceleration (CFA), aimed at lowering the detection threshold. The method capitalizes on the acceleration data sensed on the carriage floor, which is induced by the sound pressure (e.g., sound-field excitation) generated at the wheel–rail contact point. An exploration of the correlation between these datasets is undertaken by simultaneously measuring both ABA and CFA. Moreover, a pivotal aspect of this research is the development of the eigenfrequency rail corrugation index (E-RCI), a mechanism that culminates energy around specific eigenfrequencies by CFA. Through this index, a focused analysis of rail corrugation patterns is facilitated. The study further delves into the stability, repeatability, and sensitivity of the E-RCI via varied measurement scenarios. Ultimately, the CFA-based rail corrugation identification is verified, establishing its practical applicability and offering a distinct approach to detecting and characterizing rail corrugation phenomena. This study has introduced an innovative methodology for rail corrugation detection using CFA, with the principal objective of lowering the detection threshold. This approach offers an efficient measurement technique for identifying rail corrugation areas, thereby potentially reducing maintenance costs and enhancing efficiency within the railway industry. Full article
(This article belongs to the Special Issue Methods and Applications of Machine/Deep Learning for Structural Monitoring and Sensing)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-2
Back to TopTop