Showing papers on "Structural health monitoring published in 2020"
TL;DR: This work has shown that structural health monitoring techniques have been widely used in long-span bridges but, due to limitations of computational ability and data analysis methods, the knowledge in these techniques is limited.
Abstract: Structural health monitoring (SHM) techniques have been widely used in long-span bridges. However, due to limitations of computational ability and data analysis methods, the knowledge in ma...
264 citations
TL;DR: The procedure and application of vibration-based, vision-based monitoring, along with some of the recent technologies used for SHM, such as sensors, unmanned aerial vehicles (UAVs), etc. are discussed.
Abstract: Data-driven methods in structural health monitoring (SHM) is gaining popularity due to recent technological advancements in sensors, as well as high-speed internet and cloud-based computation. Since the introduction of deep learning (DL) in civil engineering, particularly in SHM, this emerging and promising tool has attracted significant attention among researchers. The main goal of this paper is to review the latest publications in SHM using emerging DL-based methods and provide readers with an overall understanding of various SHM applications. After a brief introduction, an overview of various DL methods (e.g., deep neural networks, transfer learning, etc.) is presented. The procedure and application of vibration-based, vision-based monitoring, along with some of the recent technologies used for SHM, such as sensors, unmanned aerial vehicles (UAVs), etc. are discussed. The review concludes with prospects and potential limitations of DL-based methods in SHM applications.
232 citations
TL;DR: The great novelty of the proposed AMSD-kNN method is to create a novel unsupervised learning strategy for SHM by a new multivariate distance measure and one-class kNN rule by finding sufficient nearest neighbors that guarantee the estimate of well-conditioned local covariance matrices.
129 citations
TL;DR: A novel convolutional neural network (CNN)‐based approach for structural health monitoring (SHM) that exploits a form of measured compressed response data through transfer learning (TL) based techniques and indicates that deep TL can be implemented effectively for SHM of similar structural systems with different types of sensors.
Abstract: This study introduces a novel convolutional neural network (CNN)‐based approach for structural health monitoring (SHM) that exploits a form of measured compressed response data through tra...
126 citations
TL;DR: A comprehensive review of the recent data fusion applications in structural health monitoring is presented, and state-of-the-art theoretical concepts and applications of data fusion inStructural health monitoring are presented.
Abstract: During the past decades, significant efforts have been dedicated to develop reliable methods in structural health monitoring. The health assessment for the target structure of interest is achieved ...
119 citations
TL;DR: The current state-of-the-art of fiber optic sensing/monitoring technologies, including the basic principles of various optical fiber sensors, novel sensing and computational methodologies, and practical applications for railway infrastructure monitoring are reviewed.
Abstract: In recent years, railway infrastructures and systems have played a significant role as a highly efficient transportation mode to meet the growing demand in transporting both cargo and passengers. Application of these structures in extreme environmental situation under severe working and loading conditions, caused by the traffic growth, heavier axles and vehicles and increase in speed makes it extremely susceptible to degradation and failure. In the last two decades, a significant number of innovative sensing technologies based on fiber optic sensors (FOS) have been utilized for structural health monitoring (SHM) due to their inherent distinctive advantages, such as small size, light weight, immunity to electromagnetic interference (EMI) and corrosion, and embedding capability. Fiber optic-based monitoring systems use quasi-distributed and continuously distributed sensing techniques for real time measurement and long term assessment of structural properties. This allows for early stage damage detection and characterization, leading to timely remediation and prevention of catastrophic failures. In this scenario, FOS have been proved to be a powerful tool for meticulous assessment of railway systems including train and track behavior by enabling real-time data collection, inspection and detection of structural degradation. This article reviews the current state-of-the-art of fiber optic sensing/monitoring technologies, including the basic principles of various optical fiber sensors, novel sensing and computational methodologies, and practical applications for railway infrastructure monitoring. Additionally, application of these technologies to monitor temperature, stresses, displacements, strain measurements, train speed, mass and location, axle counting, wheel imperfections, rail settlements, wear and tear and health assessment of railway bridges and tunnels will be thoroughly discussed.
117 citations
27 Jan 2020
TL;DR: The main different SHM systems (vibration methods, strain-based fiber optics methods, guided waves, acoustic emission, and nanoparticle-doped resins) are reviewed, and the main issues to be solved are identified.
Abstract: Condition-based maintenance refers to the installation of permanent sensors on a structure/system. By means of early fault detection, severe damage can be avoided, allowing efficient timing of maintenance works and avoiding unnecessary inspections at the same time. These are the goals for structural health monitoring (SHM). The changes caused by incipient damage on raw data collected by sensors are quite small, and are usually contaminated by noise and varying environmental factors, so the algorithms used to extract information from sensor data need to focus on sensitive damage features. The developments of SHM techniques over the last 20 years have been more related to algorithm improvements than to sensor progress, which essentially have been maintained without major conceptual changes (with regards to accelerometers, piezoelectric wafers, and fiber optic sensors). The main different SHM systems (vibration methods, strain-based fiber optics methods, guided waves, acoustic emission, and nanoparticle-doped resins) are reviewed, and the main issues to be solved are identified. Reliability is the key question, and can only be demonstrated through a probability of detection (POD) analysis. Attention has only been paid to this issue over the last ten years, but now it is a growing trend. Simulation of the SHM system is needed in order to reduce the number of experiments.
110 citations
TL;DR: A state of the art review of the effects of EOCs parameters including: temperature, moisture, load, vibration and bonding (adhesive layer shear modulus and thickness, bond defects), on Lamb wave propagation is provided.
108 citations
TL;DR: Achievements in the area of temperature optical fiber sensors, different configurations of the sensors reported over the last five years, and application of this technology in biomedical applications are reviewed.
Abstract: The use of sensors in the real world is on the rise, providing information on medical diagnostics for healthcare and improving quality of life. Optical fiber sensors, as a result of their unique properties (small dimensions, capability of multiplexing, chemical inertness, and immunity to electromagnetic fields) have found wide applications, ranging from structural health monitoring to biomedical and point-of-care instrumentation. Furthermore, these sensors usually have good linearity, rapid response for real-time monitoring, and high sensitivity to external perturbations. Optical fiber sensors, thus, present several features that make them extremely attractive for a wide variety of applications, especially biomedical applications. This paper reviews achievements in the area of temperature optical fiber sensors, different configurations of the sensors reported over the last five years, and application of this technology in biomedical applications.
90 citations
TL;DR: The theoretical capabilities of a number of prominent SHM methods are demonstrated by comparing their fundamental physical models to the actual effects of damage on metal and composite structures.
Abstract: Structural health monitoring (SHM) is the continuous on-board monitoring of a structure's condition during operation by integrated systems of sensors. SHM is believed to have the potential to increase the safety of the structure while reducing its deadweight and downtime. Numerous SHM methods exist that allow the observation and assessment of different damages of different kinds of structures. Recently data fusion on different levels has been getting attention for joint damage evaluation by different SHM methods to achieve increased assessment accuracy and reliability. However, little attention is given to the question of which SHM methods are promising to combine. The current article addresses this issue by demonstrating the theoretical capabilities of a number of prominent SHM methods by comparing their fundamental physical models to the actual effects of damage on metal and composite structures. Furthermore, an overview of the state-of-the-art damage assessment concepts for different levels of SHM is given. As a result, dynamic SHM methods using ultrasonic waves and vibrations appear to be very powerful but suffer from their sensitivity to environmental influences. Combining such dynamic methods with static strain-based or conductivity-based methods and with additional sensors for environmental entities might yield a robust multi-sensor SHM approach. For demonstration, a potent system of sensors is defined and a possible joint data evaluation scheme for a multi-sensor SHM approach is presented.
90 citations
TL;DR: A strategy based on autoregressive moving average (ARMA) modeling for feature extraction, and on an innovative hybrid divergence-based method for feature classification that succeeds in detecting damage in cases strongly characterized by big data are proposed.
Abstract: Recent advances in sensor technologies and data acquisition systems opened up the era of big data in the field of structural health monitoring (SHM). Data-driven methods based on statistical pattern recognition provide outstanding opportunities to implement a long-term SHM strategy, by exploiting measured vibration data. However, their main limitation, due to big data or high-dimensional features, is linked to the complex and time-consuming procedures for feature extraction and/or statistical decision-making. To cope with this issue, in this article we propose a strategy based on autoregressive moving average (ARMA) modeling for feature extraction, and on an innovative hybrid divergence-based method for feature classification. Data relevant to a cable-stayed bridge are accounted for to assess the effectiveness and efficiency of the proposed method. The results show that the offered hybrid divergence-based method, in conjunction with ARMA modeling, succeeds in detecting damage in cases strongly characterized by big data.
TL;DR: High precision structural displacement monitoring is challenging, but an effective method for structural health monitoring and particularly damage evaluation, and a high precision fiber approach is proposed.
Abstract: High precision structural displacement monitoring is challenging, but an effective method for structural health monitoring and particularly damage evaluation. In this paper, a high precision fiber ...
TL;DR: Three domain adaptation techniques are demonstrated on four case studies providing new frameworks for approaching the problem of SHM, specifically for population-based SHM.
23 Apr 2020
TL;DR: As a step towards the goal of automated damage detection, preliminary results are presented from dynamic modelling of beam structures using physics-informed artificial neural networks and a sensing paradigm for non-contact full-field measurements for damage diagnosis is presented.
Abstract: A physics-based approach to structural health monitoring (SHM) has practical shortcomings which restrict its suitability to simple structures under well controlled environments. With the advances in information and sensing technology (sensors and sensor networks), it has become feasible to monitor large/diverse number of parameters in complex real-world structures either continuously or intermittently by employing large in-situ (wireless) sensor networks. The availability of this historical data has engendered a lot of interest in a data-driven approach as a natural and more viable option for realizing the goal of SHM in such structures. However, the lack of sensor data corresponding to different damage scenarios continues to remain a challenge. Most of the supervised machine-learning/deep-learning techniques, when trained using this inherently limited data, lack robustness and generalizability. Physics-informed learning, which involves the integration of domain knowledge into the learning process, is presented here as a potential remedy to this challenge. As a step towards the goal of automated damage detection (mathematically an inverse problem), preliminary results are presented from dynamic modelling of beam structures using physics-informed artificial neural networks. Forward and inverse problems involving partial differential equations are solved and comparisons reveal a clear superiority of physics-informed approach over one that is purely datadriven vis-a-vis overfitting/generalization. Other ways of incorporating domain knowledge into the machine learning pipeline are then presented through case-studies on various aspects of NDI/SHM (visual inspection, impact diagnosis). Lastly, as the final attribute of an optimal SHM approach, a sensing paradigm for non-contact full-field measurements for damage diagnosis is presented.
TL;DR: This review provides a summary of studies applying machine learning algorithms for fault monitoring and a brief interpretation of deep neural networks is provided to guide further applications in the structural vibration analysis.
Abstract: With the rapid progress in the deep learning technology, it is being used for vibration-based structural health monitoring. When the vibration is used for extracting features for system diagnosis, it is important to correlate the measured signal to the current status of the structure. The measured vibration responses show large deviation in spectral and transient characteristics for systems to be monitored. Consequently, the diagnosis using vibration requires complete understanding of the extracted features to discard the influence of surrounding environments or unnecessary variations. The deep-learning-based algorithms are expected to find increasing application in these complex problems due to their flexibility and robustness. This review provides a summary of studies applying machine learning algorithms for fault monitoring. The vibration factors were used to categorize the studies. A brief interpretation of deep neural networks is provided to guide further applications in the structural vibration analysis.
TL;DR: The purpose of this review article is devoted to presenting a summary of the basic principles of various fiber-optic sensors, classification and principles of FOS, typical and functional fiber- optic sensors (FOSs), and the practical application status of the FOS technology in SHM of civil infrastructure.
Abstract: In recent years, with the development of materials science and architectural art, ensuring the safety of modern buildings is the top priority while they are developing toward higher, lighter, and more unique trends. Structural health monitoring (SHM) is currently an extremely effective and vital safeguard measure. Because of the fiber-optic sensor's (FOS) inherent distinctive advantages (such as small size, lightweight, immunity to electromagnetic interference (EMI) and corrosion, and embedding capability), a significant number of innovative sensing systems have been exploited in the civil engineering for SHM used in projects (including buildings, bridges, tunnels, etc.). The purpose of this review article is devoted to presenting a summary of the basic principles of various fiber-optic sensors, classification and principles of FOS, typical and functional fiber-optic sensors (FOSs), and the practical application status of the FOS technology in SHM of civil infrastructure.
TL;DR: A role of the piezoelectric-based techniques in developing the next-generation self-monitoring and self-powering health monitoring systems is envisioned.
Abstract: Recently, there has been a growing interest in deploying smart materials as sensing components of structural health monitoring systems In this arena, piezoelectric materials offer great promise for researchers to rapidly expand their many potential applications The main goal of this study is to review the state-of-the-art piezoelectric-based sensing techniques that are currently used in the structural health monitoring area These techniques range from piezoelectric electromechanical impedance and ultrasonic Lamb wave methods to a class of cutting-edge self-powered sensing systems We present the principle of the piezoelectric effect and the underlying mechanisms used by the piezoelectric sensing methods to detect the structural response Furthermore, the pros and cons of the current methodologies are discussed In the end, we envision a role of the piezoelectric-based techniques in developing the next-generation self-monitoring and self-powering health monitoring systems
TL;DR: An adaptive wavelet packet denoising algorithm applicable to numerous SHM technologies including acoustics, vibrations, and acoustic emission is outlined, which incorporates a blend of non-traditional approaches for noise estimation, threshold selection, and threshold application to augment theDenoising performance of real-time structural health monitoring measurements.
TL;DR: A digital image correlation (DIC) system installed on a drone is used as a sensing technique to obtain the dynamic characteristics of rotating wind turbine blades and can be eventually used for structural health monitoring of these structures.
TL;DR: A novel SHM method is tested where all data is solely derived from FE calculated responses, after an initial experimental cost for FE model updating on the healthy structure state and the presented combination of optimal FE and DL is a potential solution for future SHM tools.
TL;DR: A probabilistic approach for characterization of the regression pattern between bridge temperature and expansion joint displacement by use of Structural Health Monitoring data and for SHM-based condition assessment and damage alarm of bridge expansion joints is developed in the Bayesian context.
TL;DR: This work presents a brief review of data-driven algorithms for damage identification in structural health-monitoring applications, which covers damage detection, localization, classification, extension, and prognosis, as well as the development of smart structures.
Abstract: The damage identification process provides relevant information about the current state of a structure under inspection, and it can be approached from two different points of view. The first approach uses data-driven algorithms, which are usually associated with the collection of data using sensors. Data are subsequently processed and analyzed. The second approach uses models to analyze information about the structure. In the latter case, the overall performance of the approach is associated with the accuracy of the model and the information that is used to define it. Although both approaches are widely used, data-driven algorithms are preferred in most cases because they afford the ability to analyze data acquired from sensors and to provide a real-time solution for decision making; however, these approaches involve high-performance processors due to the high computational cost. As a contribution to the researchers working with data-driven algorithms and applications, this work presents a brief review of data-driven algorithms for damage identification in structural health-monitoring applications. This review covers damage detection, localization, classification, extension, and prognosis, as well as the development of smart structures. The literature is systematically reviewed according to the natural steps of a structural health-monitoring system. This review also includes information on the types of sensors used as well as on the development of data-driven algorithms for damage identification.
TL;DR: This article presents a deep-learning-based method that can extract the damage features from mode shapes without utilizing any hand-engineered feature or prior knowledge, and designs a new network architecture to meet various requirements of the damage scenarios.
Abstract: Extracting damage features precisely while overcoming the adverse interferences of measurement noise and incomplete data is a problem demanding prompt solution in structural health monitoring (SHM)...
TL;DR: A long-term displacement measurement strategy that uses computer vision-based ego-motion compensation and the sub-camera was found to provide a noticeable error compensation and a laboratory-scale test showed that the motion-induced error was reduced.
TL;DR: The developed ResNet extracts high-level features from the vibration signal and learns the modal information of structures automatically, therefore it can well preserve the most important vibration characteristics in vibration signals, and can assist in distinguishing the physical modes from the spurious modes in structural modal identification.
TL;DR: In this work, a HUMS was developed and implemented in an UAV based on 20 Fiber Bragg Gratings embedded into the composite front spar of the aircraft’s wing, a miniaturized data acquisition subsystem for gathering strain signals and a wireless transmission subsystem for remote sensing.
TL;DR: Practical DIC sampling rates were used to accurately monitor and capture the dynamic response of bridges, which shows a high potential for using DIC for larger structural health monitoring applications and future reconnaissance works.
TL;DR: A finite element model of a simply supported bridge is developed considering the aforementioned variabilities and various levels of structural damage to indicate that the proposed approach can serve as a viable health monitoring strategy and should be further tested on physical bridge systems.
TL;DR: This paper presents a damage detection method based on Variational Auto-encoder (VAE), one of the most important generative models in unsupervised deep learning, and a baseline-free data driven method, suitable for real engineering application in SHM.
TL;DR: In this paper, a Distributed Optical Fiber Sensor System (DOFS) was installed in the TMB L-9 metro tunnel in Barcelona for Structural Health Monitoring (SHM) purposes as the former could potentially be affected by the construction of a nearby residential building.