Structural Health Monitoring Tasks Research Articles

On the consistent classification and treatment of uncertainties in structural health monitoring applications

Abstract In this paper, we provide a comprehensive definition and classification of various sources of uncertainty within the fields of Structural Dynamics, System Identification, and Structural Health Monitoring (SHM), with a primary focus on the latter. Utilizing the classical input-output system representation as a main contextual framework, we present a taxonomy of uncertainties, intended for consistent classification of uncertainties in SHM applications: (i) input uncertainty; (ii) model form uncertainty; (iii) model parameter/variable uncertainty; (iv) measurement uncertainty; and (v) inherent variability. We then critically review methods and algorithms that address these uncertainties in the context of key SHM tasks: system identification and model inference, model updating, accounting for environmental and operational variability, virtual sensing, damage identification, and prognostic health management. A benchmark shear frame model with hysteretic links is employed as a running example to illustrate the application of selected methods and algorithmic tools. Finally, we discuss open challenges and future research directions in uncertainty quantification for SHM.

Mitigation of unmeasured environmental and operational variability in long-term bridge health monitoring by unsupervised statistical learning

Environmental and operational variations present a significant challenge in the long-term health monitoring of bridge structures due to their potential to cause serious confounding influences and wrong decisions. These influences may lead to false alarms of damage during normal operation of a civil structure or, conversely, mask actual damage, resulting in a failure to correctly signal a warning. Consequently, a critical task in structural health monitoring, particularly for bridges, is to mitigate the negative impact of environmental variability. An initial approach is to measure the most influential environmental and operational factors and then apply statistical tools to eliminate their effects. However, this approach may not be effective under all conditions. Therefore, the primary objective of this paper is to propose an innovative unsupervised statistical learning method that addresses the challenges posed by environmental and operational variability by considering unmeasured factors. The proposed method involves three steps: data clustering, unsupervised feature selection, and novelty detection. The initial step utilizes k-means clustering to categorize features (modal frequencies) into five types of clusters, reflecting the influence of five environmental and operational factors on bridge structures; that is, temperature, humidity/rain/snow, wind speed/direction, traffic, and damage. These clustered features are then processed through an unsupervised feature selection algorithm based on reconstruction independent component analysis to extract new features. These reduced features are subsequently employed in a novelty detection model, developed using the Mahalanobis-squared distance, to analyze the environmental and operational effects. Real dynamic data of a steel arch bridge is utilized to verify the proposed method. Results demonstrate that this method can effectively handle the demanding issue stemming from unmeasured environmental and operational variability conditions.

Computer vision-based post-earthquake inspections for building safety assessment

Assessing the safety of earthquake-affected buildings is a critical structural health monitoring task that facilitates the timely response to present dangers and reduces potential threats to life and property. However, post-earthquake time constraints and harsh environmental conditions mean that images and videos taken on-site are frequently affected by poor resolution and blurriness, which may negatively affect the accuracy and usefulness of artificial intelligence image recognition tools. In this study, a HybridGAN model was developed that incorporates ESRGAN for resolution improvement and DeblurGANv2 for blurriness improvement. Additionally, a transfer learning U-Net (TF-Unet) was integrated to detect building components (i.e., columns and structural walls), classify building damage types, and identify building damage levels. Based on recognition results from three case studies and the relevant Taiwan codes, an automated system for building safety evaluation was proposed. The model was trained to directly classify and recognize the level of building component damage. The mean Intersection over Union (mIoU) results for the column and structural wall using the testing dataset were 81.326 % and 57.009 %, respectively. The pre-trained model was used to predict three case studies to test the capability of TF-Unet to handle real-word datasets.

Unsupervised structural damage identification based on covariance matrix and deep clustering

SummaryStructural damage identification is a major task in structural health monitoring. Machine learning and deep learning algorithms have been widely applied in the research of structural damage identification. Supervised algorithms require expert labeling, making it difficult to implement in engineering applications. Unsupervised structural damage identification algorithms are generally divided into two parts: damage‐sensitive factor extraction and damage determination. Existing algorithms all perform these two steps separately. This paper proposes a damage identification method combining covariance matrix and improved deep embedding clustering network (IDEC). IDEC can perform damage‐sensitive factor extraction and damage determination operations at the same time. The covariance matrix that introduces delay information contains rich damage features, and the combination of the two has been proven to effectively mine the damage‐sensitive feature space. After network hyperparameter optimization via Bayesian optimization, the proposed method is applied to the damage identification and quantification using real bridge acceleration response data under vehicle load. The results show that this method can identify structural damage with an accuracy of up to 97% with better performance than existing technologies, and it also has great performance in identifying small damages. The proposed method is expected to increase the damage identification accuracy if applied in engineering practice.

Acoustic source localization on finite structures using remote sensors

Acoustic waves are well-suited for remote sensing applications and structural health monitoring purposes because they convey information about their source and can be measured using non-contacting methods. Source localization is an important structural health monitoring task; however, traditional time-of-flight array signal processing techniques used to localize acoustic sources are ill-suited for many structural engineering applications due to the potential for complicated propagation paths, the dispersive propagation of acoustic waves in structures, and the coupling of the vibrating structure and the surrounding medium. Thus, source localization experiments were conducted using matched field processing (MFP) for a 0.9-m diameter round aluminum plate excited by the impact of a 1.3-cm stainless-steel ball bearing dropped from 7.6-cm. A 14-sensor linear remote acoustic array placed 8.9-cm above the plate measured the sound radiated by the 0.64-cm thick plate. MFP array signal processing localization techniques were used along with a physics-based finite element acoustic model to localize the excitation on the structure. Source localization results in both a quiet environment and environment with additive white Gaussian noise are discussed, and these results are compared to those from an acoustic model where plate edge reflections are neglected. [Work was sponsored by a SMART Scholarship and the NEEC.]

In-situ sparse-array imaging for through-thickness cracks in plates with [formula omitted] Lamb waves and an efficient waveform inversion algorithm

Structural health monitoring (SHM) requires efficient online crack detection and characterization to prevent structural failures, which mainly arise from fatigue cracks. Existing solutions for crack characterization involve analyzing sensed wave signals directly, but these approaches usually require onerous steps or many sensors to obtain sufficient and clear wave packets. An alternative strategy is a model-based inversion, which takes the full waveform into consideration and does not require analysis on a single wave packet. This approach can achieve accurate characterization with fewer sensors and simpler implementation. We propose an efficient model based on the Huygens’ principle and the no-mode-conversion property of the A0 mode Lamb waves to meet the requirements of online monitoring. We then verify the proposed model-based crack imaging method through simulation and experiments on smooth and rough cracks. The proposed method is easy, cheap, and efficient, making it a desirable option for SHM tasks.

Full-Field Vibration Response Estimation from Sparse Multi-Agent Automatic Mobile Sensors Using Formation Control Algorithm.

In structural vibration response sensing, mobile sensors offer outstanding benefits as they are not dedicated to a certain structure; they also possess the ability to acquire dense spatial information. Currently, most of the existing literature concerning mobile sensing involves human drivers manually driving through the bridges multiple times. While self-driving automated vehicles could serve for such studies, they might entail substantial costs when applied to structural health monitoring tasks. Therefore, in order to tackle this challenge, we introduce a formation control framework that facilitates automatic multi-agent mobile sensing. Notably, our findings demonstrate that the proposed formation control algorithm can effectively control the behavior of the multi-agent systems for structural response sensing purposes based on user choice. We leverage vibration data collected by these mobile sensors to estimate the full-field vibration response of the structure, utilizing a compressive sensing algorithm in the spatial domain. The task of estimating the full-field response can be represented as a spatiotemporal response matrix completion task, wherein the suite of multi-agent mobile sensors sparsely populates some of the matrix's elements. Subsequently, we deploy the compressive sensing technique to obtain the dense full-field vibration complete response of the structure and estimate the reconstruction accuracy. Results obtained from two different formations on a simply supported bridge are presented in this paper, and the high level of accuracy in reconstruction underscores the efficacy of our proposed framework. This multi-agent mobile sensing approach showcases the significant potential for automated structural response measurement, directly applicable to health monitoring and resilience assessment objectives.

Structural Health Monitoring in Long-Span Steel Structures Based on the BeiDou Navigation Satellite System.

The BeiDou navigation satellite system (BDS) provides precise positioning, navigation, and timing (PNT) services in the Asia-Pacific Region, but the BDS-based structural health monitoring (SHM) approach (SHM) is rarely studied, especially in civil engineering. Moreover, how BDS can be applied to complete the tasks of SHM in a real project is also not fully investigated, especially working in conjunction with other techniques. This study aims to propose a BDS-based approach for SHM in civil engineering. The performance of the proposed approach is investigated through a case study-the Tianhan Grand Theater (TGT). A specific Tianhan system corresponding to BDS is proposed to complete the SHM tasks of TGT. Based on the collected data, the trusses with maximum displacement and stress are found by BDS to evaluate structural health in the construction stage. The results show that the maximum displacement and stress have certain safety reserves and meet the requirements of the specifications and regulations. Thus, BDS can satisfactorily complete the tasks of SHM for Long-span steel structures. This study gives a clear view to engineers and researchers that how to apply BDS in structural construction and provides a valuable real case for evaluating the performance of BDS in SHM.

Deep transfer learning for connection defect identification in prefabricated structures

Defect and damage identification is a crucial task in structural health monitoring (SHM) systems. Recent advances in deep neural networks (DNNs) show success in identification from data for a wide range of SHM systems. However, this approach faces challenges in terms of robustness and scalability with respect to data scarcity. Data collection for the training of DNNs from both the field and laboratory experiments is costly. To address this issue, we employ transfer learning (TL) through the use of deep convolutional neural networks (CNNs) for defect identification in the context of a sensor network’s vibration data. A deep TL (DTL) paradigm is used herein so that a pretrained CNN, primarily trained for generalized defect identification tasks where sufficient training data exist (source domain), can be re-trained partially (fine-tuned) as a later secondary process that targets this application domain (target domain) specifically. Different DTL cases are compared, and training data are enhanced with numerical simulation data. The efficacy and robustness of this method are demonstrated on defect identification for full-scale prefabricated concrete shear wall structures with different levels of data scarcity. This method utilizes dynamic responses collected using a sensor network. This is an extension of deep learning vision for non-vision tasks. Defect features are extracted from the dataset of dynamic responses using this DTL frame. Experimental results show that this approach can improve identification models on datasets with few samples.

FFEDN: Feature Fusion Encoder Decoder Network for Crack Detection

Crack detection plays a crucial role in structural health monitoring tasks to ensure the reliability of the transportation infrastructures. However, the automatic detection of cracks remains a challenging task due to the complicated background. Especially, tiny crack detection should be attached importance because of its weak feature and background interference. Therefore, an end-to-end network Feature Fusion Encoder Decoder Network (FFEDN) with two novel modules is proposed to improve the crack detection accuracy. For one thing, the representation capability for tiny cracks is enhanced by introducing the attention mechanism, which redistributes and fuses different features of both the encoder and the decoder. For another, because high-level feature contains less interference, a shape semantic prior module is developed to learn the shape prior map that provides the rough shape and location information of cracks. This map is fed into the lower-level feature and helps it focus on crack areas, thereby suppressing background interference. To demonstrate the effectiveness of the proposed network, several experiments are implemented on three publicly available crack datasets. Compared with state-of-the-art crack detection methods, the novel network shows better performance on all the six evaluation metrics.

A population-based SHM methodology for heterogeneous structures: Transferring damage localisation knowledge between different aircraft wings

Population-based structural health monitoring (PBSHM) offers a new viewpoint for structural health monitoring (SHM), allowing diagnostic information to be shared across populations of structures. By extending the set of available damage observations, a population-based approach can diagnose damage previously unseen on a structure of interest by leveraging damage information from other structures in the population. These technologies therefore provide significant benefits for making SHM practicable in a variety of industrial settings. It is proposed that PBSHM methodologies must be comprised of tools to assess similarity coupled with algorithms that perform knowledge transfer. The similarity tools are important for identifying whether an SHM task should be attempted for a given population by assessing both the structural similarities between members of a population and similarities in their data spaces. An abstract representation of structures in a graphical domain is presented as an objective way of assessing structural similarity, with distance metrics utilised for assessing data-space similarities. Knowledge transfer is performed using a branch of transfer learning called domain adaptation. By determining if members of a population are similar in a structural and data-space sense, the risk of negative transfer can be reduced; whereby domain adaptation reduces classification performance. This paper demonstrates a PBSHM methodology for transferring knowledge within a heterogeneous population (a group of non-identical structures). Specifically, the PBSHM methodology is shown to transfer localisation labels from a Gnat aircraft wing to an unlabelled Piper Tomahawk aircraft wing dataset, resulting in 100% classification accuracy.

Impact Damage Detection of a Glass Fabric Composite Using Carbon Fiber Sensors with Regard to Mechanical Loading

Structural Health Monitoring (SHM) of composite structures leads to greater safety during operation and reduces the cost of regular inspections. Impact damage detection is an important SHM task. Since impact damage can significantly reduce the lifetime of composite structures, sensors for impact damage are of great interest. Carbon Fiber Sensors (CFSs) can be used to detect composite damage. CFSs are lightweight and compact, and they can be integrated during the manufacturing process. In our study, CFSs were manufactured from three types of carbon fiber tows and were integrated into different layers of the lay-up in order to investigate the influence on impact damage detection. The effect of mechanical loading and temperature change on the measured electrical resistance was investigated during cyclic flexural tests. It was revealed that, it is possible to distinguish between changes in measured signals due to impact and due mechanical loading. The change in the measured electrical signal caused by temperature can be eliminated. CFSs can be used for impact damage detection of a glass fabric composite. A combination of thermography and CFSs as an active heating element also provides good results in the field of impact damage detection

Densely connected convolutional networks for vibration based structural damage identification

Vibration-based damage identification has been a challenging task in structural health monitoring. The main difficulty lies on the reliable correlation between the measured vibration characteristics and damage states (e.g., stiffness reductions) of structures. Such states can ideally indicate the presence, locations, and severities of structural damages. The procedure is considered as a feature extraction process from the input measurement, mapping the selected features to damage states. Time domain vibration responses, e.g., acceleration responses, are used in this study for damage identification. To address this pattern recognition problem, many methods have been developed including various neural networks in recent years. This paper proposes a novel approach based on densely connected convolutional networks (DenseNets), which is one of the major breakthroughs in the computer vision community, for vibration based structural damage identification. It implements dense connectivity in the convolutional neural network architecture, which fits well for this study using acceleration responses. Both low-level and high-level features are learned and reused during training. It not only eases the information flow during training, but also preserves all levels of features and tends to be more effective for damage identification. Besides, the dense connectivity alleviates the gradient vanishing problem and strengthens feature propagation through the network. In the meantime, these designs substantially reduce the number of parameters, making the network easy to train. The performance of the proposed approach is evaluated through both numerical and experimental verifications. Both modelling uncertainties and measurement noises are considered in numerical studies. The results from numerical and experimental studies demonstrate that the damage localization and quantification are achieved with high accuracies (e.g., Regression value ≥ 96.0% on numerical datasets, and ≥ 94.9% on experimental datasets) and good robustness.

Классификатор изображений транспортных средств для определения корреляции их воздействия со смещением координат моста

Advanced computing brings opportunities for innovation in a broad gamma of applications. Traditional practices based on visual and manual methods tend to be replaced by cyber-physical systems to automate processes. The present work introduces an example of this, a machine vision system research based on deep learning to classify bridge load, to give support to an optical scanning system for structural health monitoring tasks. The optical scanning system monitors the health of structures, such as buildings, warehouses, water dams, etc. by the measurement of their coordinates to identify if a coordinate displacement befalls that could indicate an anomaly in the structure that can be related to structural damage. The use of this optical scanning system to monitor the structural health of bridges is a little more complicated due to the vehicle's transit over the bridge that causes a vehicle-bridge interaction which manifests as a bridge oscillation. Under this scheme, the bridge oscillation corresponds to their coordinate’s displacement due to the vehicle-bridge interaction, but not necessarily due to bridge damage. So, a bridge load classifier is required to correlate the bridge coordinates measurements behavior with the bridge oscillation due to vehicle-bridge interaction to discriminate the normal behavior of the structure to abnormal behavior or identify tendencies that could indicate bridge deformation or discover if the bridge behavior due to loads is changing through the time.

Bridge Load Classifier Based on Deep Learning for Structural Displacement Correlation

Advanced computing brings opportunities for innovation in a broad gamma of applications. Traditional practices based on visual and manual methods tend to be replaced by cyber-physical systems to automate processes. The present work introduces an example of this, a machine vision system research based on deep learning to classify bridge load, to give support to an optical scanning system for structural health monitoring tasks. The optical scanning system monitors the health of structures, such as buildings, warehouses, water dams, etc. by the measurement of their coordinates to identify if a coordinate displacement befalls that could indicate an anomaly in the structure that can be related to structural damage. The use of this optical scanning system to monitor the structural health of bridges is a little more complicated due to the vehicle’s transit over the bridge that causes a vehicle-bridge interaction which manifests as a bridge oscillation. Under this scheme, the bridge oscillation corresponds to their coordinate’s displacement due to the vehicle-bridge interaction, but not necessarily due to bridge damage. So, a bridge load classifier is required to correlate the bridge coordinates measurements behavior with the bridge oscillation due to vehicle-bridge interaction to discriminate the normal behavior of the structure to abnormal behavior or identify tendencies that could indicate bridge deformation or discover if the bridge behavior due to loads is changing through the time.

Novel Sensing Approaches for Structural Deformation Monitoring and 3D Measurements

Nowadays, laser vision systems have allowed the development of different applications such as reverse engineering, manufacturing, navigation systems and, structural health monitoring (SHM). However, most of the machine vision systems for structural behavior analysis have restricted field of view, consume high levels of computational resources for image processing and require special illumination conditions to achieve lower error rates. Therefore, the purpose of this paper is to present a technical vision system (TVS) for structural behavior analysis using dynamic laser triangulation and k- Nearest Neighbor (k-NN) machine learning regression algorithm. The proposed vision system was tested in order to demonstrate the practicality of it, different deformations and displacements were analyzed over real structures in controlled laboratory conditions to assure the reproducibility of the experimentation. The TVS prototype proved to be a reliable option on SHM tasks, presenting balance between precision and operating ranges, without the issues aforementioned.

Capsule Neural Networks for structural damage localization and quantification using transmissibility data

One of the current challenges in structural health monitoring (SHM) is to take the most advantage of large amounts of data to deliver accurate damage measurements and predictions. Deep Learning methods tackle these problems by finding complex relations hidden in the data available. Amongst these, Capsule Neural Networks (CapsNets) have recently been developed, achieving promising results in benchmark Deep Learning problems. In this paper, Capsule Networks are expanded to locate and to quantify structural damage. The proposed approach is evaluated in two case studies: a system with springs and masses that simulate a structure, and a beam with different damage scenarios. For both case studies, training and validation sets are created using Finite Element (FE) models and calibrated with experimental data, which is also used for testing. The main contributions of this study are: A novel CapsNets-based method for dual classification–regression task in SHM, analysis of both routing algorithms (dynamic routing and Expectation–Maximization routing) in the context of SHM, and analysis of generalization between FE models and real-life experiments. The results show that the proposed Capsule Networks with dynamic routing achieve better results than Convolutional Neural Networks (CNN), especially when it comes to false positive values.

Structural Health Monitoring Using Synchrosqueezed Wavelet Transform on IASC-ASCE Benchmark Phase I

Civil structures suffer deterioration either for years of service, deficiency due to environmental factors or damages caused by factors such as earthquakes, winds, impact loads, and cyclical loads. When a structure ages, it is necessary to know its state of health and make a decision of maintenance or replacement. When a structure such as a bridge or building is subjected to destructive environmental forces, determining its state of health becomes a priority since its recovery is urgently required to function normally. Structural Health Monitoring (SHM) is a technology that aims to prevent the collapse of structures and loss of human life through early diagnosis of the health status of a structure. There are a large number of damage detection methods that can be classified into (1) non-destructive testing methods, (2) dynamic characteristics-based damage detection methods, (3) dynamic response-based, (4) multi-scale damage detection method and (5) damage detection methods with consideration of uncertainties. In this work, it is implemented synchrosqueezed wavelet transform (SWT), which can be classified as a methods based on the dynamic response. To validate the robustness of the method it is identified first, the natural frequencies of the Benchmark Phase I without damage, which consists of a steel structure of 4-story [Formula: see text] bay 3D steel frame structure subjected to ambient vibrations. Subsequently, some damage patterns are validated according to IASC-ASCE SHM Task Group. The results obtained in the identification of natural frequencies are compared with those reported in literature. SWT was efficient, presenting a minimum error of 0.12[Formula: see text] and a maximum of 3.06[Formula: see text] in the identification of natural frequencies about the AISCE-ASCE group model. SWT overcomes some other damage detection methods, which are deficient in the identification of closely spaced frequencies, commonly present in many civil structures due to symmetric geometry or similar physical properties in different directions.

Analytical modeling of flexible structures for health monitoring under environmentally induced loads

Wireless structural health monitoring (SHM) represents an emerging paradigm in non-destructive testing evaluation, which is regularly performed within the framework of structural maintenance of critical infrastructure. While traditional cable-based SHM strategies have largely relied on centralized structural response data collection and processing, in wireless SHM the sensor nodes essentially operate as stand-alone processing units. Furthermore, the on-board processing capabilities of wireless sensor nodes have been widely exploited for decentralizing SHM tasks, thus avoiding power-consuming wireless transmission of entire structural response data sets. Evidently, on-board processing requires approaches tailored to the limited computational resources of wireless sensor nodes, particularly for computationally intensive, state-of-the-art strategies for SHM that rely on artificial intelligence (AI). Specifically, in model-based SHM/AI strategies, AI algorithms are trained by running the so-called what-if scenarios using numerical models of monitored structures. However, the use of numerical models in a decentralized wireless SHM scheme might be prohibitive from a computational resources point of view. To overcome this limitation, analytical modeling techniques using elastic waveguides are developed here that carry a low computational burden. These are specifically tailored for flexible structures of variable cross section, which comprise typical components of critical infrastructure such as masts, antennas and pylons, and can be used for simulating axial, torsional and flexural vibrations. The accuracy and efficiency of the proposed analytical modeling approach are then demonstrated through comparisons with conventional numerical models based on the finite element method.

Acousto-ultrasonics-based health monitoring for nano-engineered composites using a dispersive graphene-networked sensing system

Sensing is a fundamental yet crucial part of a functional structural health monitoring system. Substantial research has been invested in developing new sensing techniques to enhance sensing efficiency and accuracy. Practical applications of structural health monitoring approaches to real engineering structures require strict criteria for the sensing system (e.g. weight, position, intrusion and endurance), which challenge existing sensing techniques. The boom in nanotechnology has offered promising solutions for the development of new sensing approaches. However, a bottleneck still exists when considering the density of sensors and surface-mounted modality of installation. In this study, graphene nanoparticles are dispersed into a glass fibre/epoxy composite to form a dispersive network sensing system. The piezoresistivity of the graphene-formed network changes locally as a result of the change of inter-nanoparticle distances which triggers the ‘tunnelling effect’ and drives the sensor to respond to propagating elastic waves. Due to the dense graphene network formed within the composite, only a small area is required, functioning as a single sensing element to capture ultrasonic waves. To validate such capability, passive acoustic emission tests and active guided ultrasonic wave tests are performed individually. The graphene-networked sensing system can precisely capture wave signals which contain effective features to identify impact spot or damage location. Integrating passive graphene-formed network and active lead zirconate titanate wafers can form a dense network, capable of fulfilling general structural health monitoring tasks.