sensors-logo

Journal Browser

Journal Browser

Smart Sensors and Physics-Based Machine Learning for Structural Health Monitoring

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

Deadline for manuscript submissions: closed (30 June 2022) | Viewed by 10774

Special Issue Editor

Department of Structural Mechanics and Hydraulic Engineering, University of Granada, 18001 Granada, Spain
Interests: multifunctional composite materials; multi-physics modeling; structural health monitoring; vibration-based testing; structural dynamics; structural damage identification
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Recent advances in Smart Sensor Systems and Artificial Intelligence (AI) have opened vast possibilities for the development of disruptive innovations in the field of Structural Health Monitoring (SHM). In their broadest sense, smart sensors are designed to mitigate operating and efficiency limitations related to traditional monitoring solutions. These may range from sensors incorporating on-board microprocessing and state interrogation, sparse and dense sensor networks capable of detecting local and global pathologies, to novel composite materials with self-diagnostic properties. In addition, the increasingly frequent implementation of AI algorithms in the realm of SHM is enabling unprecedented possibilities to link monitoring signals to decision-making. Particularly promising are physics-based AI applications, enabling the injection of engineering knowledge and expertise into decision-making steps. In this light, the aim of this Special Issue is to generate discussions on the latest advances in research on smart sensing technologies and physics-based AI for SHM. Topics of interest include but are not limited to:

  • Novel sensors and transducers;
  • Intelligent signal processing;
  • Smart sparse and dense sensor networks;
  • Integrated systems;
  • Multifunctional materials for sensing applications;
  • Data fusion;
  • Data mining;
  • Supervised/unsupervised machine learning;
  • Surrogate modeling for automated damage identification;
  • Long-term big data processing and management;
  • Internet of Things for structural health monitoring.

Dr. Enrique García Macías
Guest Editor

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.

Published Papers (5 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Review

29 pages, 6820 KiB  
Article
Data Augmentation for Deep-Learning-Based Multiclass Structural Damage Detection Using Limited Information
by Kyle Dunphy, Mohammad Navid Fekri, Katarina Grolinger and Ayan Sadhu
Sensors 2022, 22(16), 6193; https://0-doi-org.brum.beds.ac.uk/10.3390/s22166193 - 18 Aug 2022
Cited by 9 | Viewed by 1874
Abstract
The deterioration of infrastructure’s health has become more predominant on a global scale during the 21st century. Aging infrastructure as well as those structures damaged by natural disasters have prompted the research community to improve state-of-the-art methodologies for conducting Structural Health Monitoring (SHM). [...] Read more.
The deterioration of infrastructure’s health has become more predominant on a global scale during the 21st century. Aging infrastructure as well as those structures damaged by natural disasters have prompted the research community to improve state-of-the-art methodologies for conducting Structural Health Monitoring (SHM). The necessity for efficient SHM arises from the hazards damaged infrastructure imposes, often resulting in structural collapse, leading to economic loss and human fatalities. Furthermore, day-to-day operations in these affected areas are limited until an inspection is performed to assess the level of damage experienced by the structure and the required rehabilitation determined. However, human-based inspections are often labor-intensive, inefficient, subjective, and restricted to accessible site locations, which ultimately negatively impact our ability to collect large amounts of data from inspection sites. Though Deep-Learning (DL) methods have been heavily explored in the past decade to rectify the limitations of traditional methods and automate structural inspection, data scarcity continues to remain prevalent within the field of SHM. The absence of sufficiently large, balanced, and generalized databases to train DL-based models often results in inaccurate and biased damage predictions. Recently, Generative Adversarial Networks (GANs) have received attention from the SHM community as a data augmentation tool by which a training dataset can be expanded to improve the damage classification. However, there are no existing studies within the SHM field which investigate the performance of DL-based multiclass damage identification using synthetic data generated from GANs. Therefore, this paper investigates the performance of a convolutional neural network architecture using synthetic images generated from a GAN for multiclass damage detection of concrete surfaces. Through this study, it was determined the average classification performance of the proposed CNN on hybrid datasets decreased by 10.6% and 7.4% for validation and testing datasets when compared to the same model trained entirely on real samples. Moreover, each model’s performance decreased on average by 1.6% when comparing a singular model trained with real samples and the same model trained with both real and synthetic samples for a given training configuration. The correlation between classification accuracy and the amount and diversity of synthetic data used for data augmentation is quantified and the effect of using limited data to train existing GAN architectures is investigated. It was observed that the diversity of the samples decreases and correlation increases with the increase in the number of synthetic samples. Full article
Show Figures

Figure 1

15 pages, 2294 KiB  
Article
Damage Detection in Steel–Concrete Composite Structures by Impact Hammer Modal Testing and Experimental Validation
by Viviana Meruane, Sergio J. Yanez, Leonel Quinteros and Erick I. Saavedra Flores
Sensors 2022, 22(10), 3874; https://0-doi-org.brum.beds.ac.uk/10.3390/s22103874 - 20 May 2022
Cited by 7 | Viewed by 1887
Abstract
Steel–concrete composite systems are an efficient alternative to mid- and high-rise building structures because of their high strength-to-weight ratio when compared to traditional concrete or steel constructive systems. Nevertheless, composite structural systems are susceptible to damage due to, for example, deficient construction processes, [...] Read more.
Steel–concrete composite systems are an efficient alternative to mid- and high-rise building structures because of their high strength-to-weight ratio when compared to traditional concrete or steel constructive systems. Nevertheless, composite structural systems are susceptible to damage due to, for example, deficient construction processes, errors in design and detailing, steel corrosion, and the drying shrinkage of concrete. As a consequence, the overall strength of the structure may be significantly decreased. In view of the relevance of this subject, the present paper addresses the damage detection problem in a steel–concrete composite structure with an impact-hammer-based modal testing procedure. The mathematical formulation adopted in this work allows for the identification of regions where stiffness varies with respect to an initial virgin state without the need for theoretical models of the undamaged structure (such as finite element models). Since mode shape curvatures change due to the loss of stiffness at the presence of cracks, a change in curvature was adopted as a criterion to quantify stiffness reduction. A stiffness variability index based on two-dimensional mode shape curvatures is generated for several points on the structure, resulting in a damage distribution pattern. Our numerical predictions were compared with experimentally measured data in a full-scale steel–concrete composite beam subjected to bending and were successfully validated. The present damage detection strategy provides further insight into the failure mechanisms of steel–concrete composite structures, and promotes the future development of safer and more reliable infrastructures. Full article
Show Figures

Figure 1

11 pages, 1440 KiB  
Article
Feasibility of Using Shear Wave Ultrasonic Probes as Pump-Wave Sources in Concrete Microcrack Detection and Monitoring by Nonlinear Ultrasonic Coda Wave Interferometry
by Belfor A. Galaz Donoso, Siva Avudaiappan and Erick I. Saavedra Flores
Sensors 2022, 22(6), 2105; https://0-doi-org.brum.beds.ac.uk/10.3390/s22062105 - 09 Mar 2022
Viewed by 1496
Abstract
This paper represents a first attempt to study the feasibility of using shear wave (SW) ultrasonic probes as pump-wave sources in concrete microcrack detection and monitoring by Nonlinear Ultrasonic Coda Wave Interferometry (NCWI). The premise behind our study is that the nonlinear elastic [...] Read more.
This paper represents a first attempt to study the feasibility of using shear wave (SW) ultrasonic probes as pump-wave sources in concrete microcrack detection and monitoring by Nonlinear Ultrasonic Coda Wave Interferometry (NCWI). The premise behind our study is that the nonlinear elastic hysteretic behavior at microcracks may depend on their orientation with respect to the stationary wave-field induced by the pump-wave source. In this context, the use of a SW probe as a pump-wave source may induce the nonlinear elastic behavior of microcracks oriented in directions not typically detected by a conventional longitudinal pump-wave source. To date, this premise is hard to address by current experimental and numerical methods, however, the feasibility of using SW probes as a pump-wave source can be experimentally tested. This idea is the main focus of the present work. Under laboratory conditions, we exploit the high sensitivity of the CWI technique to capture the transient weakening behaviour induced by the SW pump-wave source in concrete samples subjected to loading and unloading cycles. Our results show that after reaching a load level of 40% of the ultimate stress, the material weakening increases as a consequence of microcrack proliferation, which is consistent with previous studies. Despite the lack of exhaustive experimental studies, we believe that our work is the first step in the formulation of strategies that involve an appropriate selection and placement of pump-wave sources to improve the NCWI technique. These improvements may be relevant to convert the NCWI technique into a more suitable non-destructive testing technique for the inspection of microcracking evolution in concrete structures and the assessment of their structural integrity. Full article
Show Figures

Figure 1

11 pages, 800 KiB  
Article
Optimal Sensor Placement in Reduced-Order Models Using Modal Constraint Conditions
by Eun-Taik Lee and Hee-Chang Eun
Sensors 2022, 22(2), 589; https://0-doi-org.brum.beds.ac.uk/10.3390/s22020589 - 13 Jan 2022
Cited by 6 | Viewed by 1605
Abstract
Sensor measurements of civil structures provide basic information on their performance. However, it is impossible to install sensors at every location owing to the limited number of sensors available. Therefore, in this study, we propose an optimal sensor placement (OSP) algorithm while reducing [...] Read more.
Sensor measurements of civil structures provide basic information on their performance. However, it is impossible to install sensors at every location owing to the limited number of sensors available. Therefore, in this study, we propose an optimal sensor placement (OSP) algorithm while reducing the system order by using the constraint condition between the master and slave modes from the target modes. The existing OSP methods are modified in this study, and an OSP approach using a constrained dynamic equation is presented. The validity and comparison of the proposed methods are illustrated by utilizing a numerical example that predicts the OSPs of the truss structure. It is observed that the proposed methods lead to different sensor layouts depending on the algorithm criteria. Thus, it can be concluded that the OSP algorithm meets the measurement requirements for various methods, such as structural damage detection, system identification, and vibration control. Full article
Show Figures

Figure 1

Review

Jump to: Research

30 pages, 6868 KiB  
Review
Recent Advances in Nondestructive Method and Assessment of Corrosion Undercoating in Carbon–Steel Pipelines
by Zazilah May, Md Khorshed Alam and Nazrul Anuar Nayan
Sensors 2022, 22(17), 6654; https://0-doi-org.brum.beds.ac.uk/10.3390/s22176654 - 02 Sep 2022
Cited by 11 | Viewed by 2528
Abstract
Carbon–steel pipelines have mostly been utilized in the oil and gas (OG) industry owing to their strength and cost-effectiveness. However, the detection of corrosion under coating poses challenges for nondestructive (ND) pipeline monitoring techniques. One of the challenges is inaccessibility because of the [...] Read more.
Carbon–steel pipelines have mostly been utilized in the oil and gas (OG) industry owing to their strength and cost-effectiveness. However, the detection of corrosion under coating poses challenges for nondestructive (ND) pipeline monitoring techniques. One of the challenges is inaccessibility because of the pipeline structure, which leads to undetected corrosion, which possibly leads to catastrophic failure. The drawbacks of the existing ND methods for corrosion monitoring increase the need for novel frameworks in feature extraction, detection, and characterization of corrosion. This study begins with the explanations of the various types of corrosion in the carbon–steel pipeline in the OG industry and its prevention methods. A review of critical sensors integrated with various current ND corrosion monitoring systems is then presented. The importance of acoustic emission (AE) techniques over other ND methods is explained. AE data preprocessing methods are discussed. Several AE-based corrosion detection, prediction, and reliability assessment models for online pipeline condition monitoring are then highlighted. Finally, a discussion with future perspectives on corrosion monitoring followed by the significance and advantages of the emerging AE-based ND monitoring techniques is presented. The trends and identified issues are summarized with several recommendations for improvement in the OG industry. Full article
Show Figures

Figure 1

Back to TopTop