Structural Health Monitoring Techniques Research Articles

Automated Surface Crack Identification of Reinforced Concrete Members Using an Improved YOLOv4-Tiny-Based Crack Detection Model

In recent times, the deployment of advanced structural health monitoring techniques has increased due to the aging infrastructural elements. This paper employed an enhanced You Only Look Once (YOLO) v4-tiny algorithm, based on the Crack Detection Model (CDM), to accurately identify and classify crack types in reinforced concrete (RC) members. YOLOv4-tiny is faster and more efficient than its predecessors, offering real-time detection with reduced computational complexity. Despite its smaller size, it maintains competitive accuracy, making it ideal for applications requiring high-speed processing on resource-limited devices. First, an extensive experimental program was conducted by testing full-scale RC members under different shear span (a) to depth ratios to achieve flexural and shear dominant failure modes. The digital images captured from the failure of RC beams were analyzed using the CDM of the YOLOv4-tiny algorithm. Results reveal the accurate identification of cracks formed along the depth of the beam at different stages of loading. Moreover, the confidence score attained for all the test samples was more than 95%, which indicates the accuracy of the developed model in capturing the types of cracks in the RC beam. The outcomes of the proposed work encourage the use of a developed CDM algorithm in real-time crack detection analysis of critical infrastructural elements.

In-situ acoustic emission based technique for damage detection and identification and failure mode prediction in scarf repaired composite structures

One of the great challenges facing adhesively bonded repair procedures in the industry is the absence of a reliable structural health monitoring technique to ensure that the repaired region is intact during service. To this end, this paper proposes a novel in-situ acoustic emission-based methodology to detect and identify damages as well as to predict failure modes at early stages. In this essence, two tapered-scarf repaired plates are produced with different patch materials. The first patch consists of neat carbon fiber prepregs whereas in the second thermally exfoliated graphene oxide integrated carbon fiber prepregs are utilized. Testing the constituents of the repair system individually while monitoring their acoustic activity makes it possible to separate each damage type precisely. Hence, when the specimens of the repaired panel are tested, very detailed information is revealed regarding the current structural status of the specimen and probable failure scenarios. The effectiveness and robustness of the proposed methodology in detecting and identifying damages of varying severity in addition to predicting the failure scenario are verified in the composite panels repaired with pristine and graphene integrated patches.

A review on early-age cracking of concrete: Causes and control

The early-age cracking of concrete is one of the most critical parameters affecting the performance of concrete structures. It is attributed to both the internal and external influences such as early age restrained shrinkage, thermal deformation as well as the applied load. In this paper, a detailed review of the causes of early-age cracking is first presented, followed by the factors affecting the concrete cracking including raw materials quality problems, improper construction measures, external environmental influences and structural design flaws. Then the preventive measures for concrete cracking are summarized. The potential for the application and development of structural health monitoring and artificial intelligence techniques for early-age cracking of concrete is also discussed. Through the comprehensive review of the early-age cracking of concrete, the research direction for the subsequent research on early-age cracking of concrete is pointed out. The current problems and concerns of concrete cracking are also prospected.

A four-node inverse curved shell element coupling MITC method for deformation reconstruction of plate and shell structures

In the field of structural deformation monitoring, the inverse finite element method (iFEM) has significant engineering value as a structural health monitoring technique that provides timely and reliable warnings for shell structures. However, existing inverse finite elements are mainly based on first-order shear deformation theory and kirchhoff-love theory, which are not suitable for deformation reconstruction in plate and shell structures of arbitrary thickness. This study integrates iFEM with the Mixed Interpolation of Tensorial Components (MITC) method to develop a novel four-node quadrilateral inverse curved shell element, named iMICS(inverse Mixed Interpolation Curved Shell)4, aimed at enhancing the accuracy and efficiency of deformation reconstruction in complex plate and shell structures. The method uses the MITC4 shell element as the kinematic framework and applies the least squares variational principle to achieve deformation reconstruction, effectively alleviating shear and membrane locking issues across structures of varying thickness. Numerical examples validate the superior performance of the iMICS4 element, demonstrating its promising application prospects.

Using acoustic emission technique for structural health monitoring of laminate composite: A novel CNN-LSTM framework

This research has developed a real-time end-to-end deep learning model for structural health monitoring (SHM) method for composite impact damage diagnosis based on Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM). The acoustic emission (AE) signals collected under low-velocity impacts by means of piezoelectric sensors on composite materials are used for training deep learning networks. Based on the impact load curves, specimens are categorized into minor failure, intermediate failure, and severe failure. The convolved signals are segmented and reconstructed at a given length for the following LSTM module. The average accuracies for basic CNN, CNN– Recurrent Neural Network (RNN), CNN-LSTM, and CNN– Gated Recurrent Unit (GRU) are respectively 88.7 %, 92.6 %, 98 %, and 95.4 %. A sensitivity analysis on sub-signal length was conducted on the CNN-LSTM model, revealing that the model achieved its best performance when the sub-signal length was set at 16. The model attained prediction accuracies of 97.4 %, 100 %, and 100 %, respectively, for minor failure, intermediate failure, and severe failure cases.

Hybrid operational modal analysis of an operative two-bladed offshore wind turbine

As with any strategic structure, vibration-based structural health monitoring techniques are often used to ensure the structurally safe operation of offshore wind turbines. Among such techniques, Operational Modal Analysis (OMA) methods allow the identification of modal properties, such as natural frequencies, mode shapes and damping, which variation might be caused by damage or operational/environmental factors. This paper investigates the application of OMA techniques on a two-bladed offshore wind turbine, which poses multiple challenges: fundamental OMA assumptions about the applied loads are violated by environmental and operational loads; the closely spaced modes of an offshore wind turbine are hard to identify; and an operative two-bladed offshore wind turbine is a time-variant system. Within this study, three OMA procedures to overcome some of the preceding challenges are discussed: (1) a standard frequency domain decomposition method; (2) a proposed enhanced transmissibility-based approach with a post-processing technique based on the Kurtosis index; and (3) a proposed refined hybrid OMA procedure that combines a transmissibility-based approach, the dedicated post-processing technique based on the Kurtosis index, and the frequency domain decomposition method. A numerical model representative of an operative two-bladed offshore wind turbine is used to compare the three procedures. Based on the comparison, the hybrid method is proven to be a promising new OMA-based procedure that outperforms the stand-alone transmissibility-based approach and the frequency domain decomposition method in identifying the modal properties of a two-bladed offshore wind turbine.

Meta-model structural monitoring with cutting-edge AAE-VMD fusion alongside optimized machine learning methods

Transfer learning significantly enhances machine learning by leveraging knowledge from one dataset to boost performance on another, which is particularly beneficial when labelled data ares limited or costly. Sensor fusion, an essential technique in structural health monitoring, improves the effectiveness of transfer learning by combining data from multiple sensors to extract more informative features. This article proposes a novel meta-model structural monitoring using a new data fusion method named the adversarial autoencoder (AAE)–variational mode decomposition (VMD) algorithm, which integrates optimization algorithms, transfer learning, and machine learning techniques for damage detection tasks. The proposed meta-model combines transfer learning with an optimized machine learning framework for training and employs pretrained models for testing across diverse datasets. First, the tensors are fused using the AAE approach into 300 data points, reducing noise and outliers, performing dimensionality reduction, and enriching the training and test datasets. Then, a preprocessing step involves decomposing and denoising tensors using the VMD algorithm, followed by selecting the most informative intrinsic mode functions (IMFs) based on their variance. These selected IMFs are concatenated, and 13 statistical features are extracted from them and used as inputs for machine learning models. Various optimization algorithms are employed to fine-tune the hyperparameters of the machine learning models for optimal classification results. Validation of this meta-model utilizes the dataset collected from a steel grandstand structure, available in benchmark dataset format. For decomposed fused tensors, both particle swarm optimization and covariance matrix adaptation evolution strategy emerge as equally effective optimization techniques for K-nearest neighbours (KNN), consistently achieving the highest mean test accuracy and F1 score of 99.5%. Conversely, KNN stands out as a robust and reliable classification algorithm for denoised fused tensors in transfer learning classification problems, consistently demonstrating perfect accuracy and an F1 score of 1.0 ± 0.0 across all optimization techniques.

AI-Driven Structural Health Monitoring: Unleashing Potential and Embracing Future Opportunities

Structural Health Monitoring (SHM) is a critical aspect of ensuring the safety and longevity of infrastructure such as bridges, buildings, and dams. Traditional SHM techniques, while effective, often rely on manual inspections and can be laborintensive, time-consuming, and prone to human error. Recent advancements in Artificial Intelligence (AI) have the potential to revolutionize SHM by automating data analysis, improving predictive capabilities, and enhancing overall system efficiency. This article explores the integration of AI in SHM, highlighting key innovations, challenges, and future directions for this transformative technology.

Off-the-shelf UHF RFID-based sensors for corrosion characterization of coated steel

The application of the UHF RFID technique in non-destructive testing (NDT) and structural health monitoring (SHM) has gained increasing attention due to its wireless, battery-less, and cost-effective attributes. It offers a promising approach for SHM and the Internet of Things (IoTs). This paper reports commercial off-the-shelf (COTS) flexible UHF RFID tag-based sensors for corrosion characterization on coated mild steel. Two types of COTS flexible UHF RFID tags with different bends are fabricated as sensors. The received signal strength indicator (RSSI) measurement is implemented to characterize the corrosion. Three parts (T-match area, dipole arms, and dipole loadings) of the two tags are tested for sensing purposes, and comparison and discussion of sensitivity, read range, and results are provided. This study successfully validates the feasibility of the proposed tag-bent method for corrosion characterization undercoating. It can be concluded that the dipole arm part of the applied COTS tags is the most sensitive area.

DF-CDM: Conditional diffusion model with data fusion for structural dynamic response reconstruction

In structural health monitoring (SHM) systems, data loss inevitably occurs and reduces the applicability of SHM techniques, such as condition assessment and damage identification. The current mainstream data-driven method, generative adversarial networks (GAN), suffers from convergence difficulty, limiting the accuracy and efficiency of response reconstruction. In this study, a conditional diffusion model with data fusion (DF-CDM) is proposed for structural dynamic response reconstruction. The original unsupervised diffusion model is improved by introducing the conditional input and modifying the deep denoising neural network to achieve supervised learning. Besides, data fusion is developed to further utilize the frequency-domain information and improve the reconstruction quality of the time-domain signals. The proposed model is validated on a three-span continuous bridge. Results show that the diffusion model with data fusion achieves the highest accuracy on the test set with R2, RMSE and MAE equaling 0.821, 0.0053 and 0.0042 respectively. Compared with the state-of-the-art GAN model, the diffusion model without the adversarial modules has a more stable training process and better reconstruction performance in both time and frequency domains. The modal identification and robustness analysis further verify the effectiveness of the proposed model. The proposed diffusion model with data fusion achieves high-quality structural response reconstruction, guaranteeing the applicability and reliability of subsequent response-based structural analysis.

A novel damage localization technique for type III composite pressure vessels based on guided wave mode-matching method

Damage monitoring during the service life of Type III composite overwrapped pressure vessels (COPVs) is crucial for ensuring their safe operation. This paper focuses on the damage localization in COPVs using ultrasonic guided waves structural health monitoring (SHM) techniques. Firstly, dispersion curves were plotted to establish a foundation for experiments and simulations based on the propagation theory of guided waves in multilayered anisotropic structures. Subsequently, a 3D finite element model of COPV was constructed to capture the propagation characteristics of guided waves within the COPV and their interaction with damage. The effects of different fiber angles and fiber layer numbers on guided waves propagation were analyzed, and their interrelationships were established. Furthermore, the “Wave Velocity Directionality” effect of the A0 mode was identified during its propagation in COPV. The monitoring signals obtained from experiments were analyzed to assess the impact of damage on the time-domain and frequency-domain signals of guided waves. Finally, a damage localization algorithm based on mode-matching was proposed, and its localization accuracy was verified in COPVs with different damage locations and fiber layer numbers. The results demonstrate the significant potential of the proposed damage localization algorithm in the damage monitoring of COPV structures.

Pattern recognition in electromechanical impedance spectroscopy damage detection of adhesive joints using multidimensional scaling

Adhesive joints are prone to various types of damage sources, which may not be identifiable with current non-destructive tests (NDTs). Structural health monitoring techniques, such as those based on electromechanical impedance spectroscopy (EMIS), aim to outperform NDTs in damage detection, by continuously monitoring structures. Although the EMIS-based algorithmic performance of damage detection has been evaluated on metallic and composite components, integrity monitoring of adhesive joints is yet to be fully determined. Therefore, this article investigates the use of multidimensional scaling (MDS) to cluster and visualize experimental impedance measurements of bonded joints in a three dimensional space. With these results, an Euclidean distance damage metric is used to try and classify the type of damage. The results show that damage detection is easily performed with the MDS algorithm, but effectiveness is dependent on the spectral measurement conditions. Furthermore, reduced dimensional spaces can yield information regarding the size and location of the damage in the adhesive layer, yielding increased knowledge on the integrity of structural adhesive joints.

A statistical volume element-based procedure for the prediction of the mechanical and electrical response of an epoxy-PZT self-sensing layer for application in composite laminates

Structural Health Monitoring (SHM) techniques are being developed to continuously oversee defects in composite structures. Within this context, research is focusing on the development of new types of sensors with high sensitivity and proper integration in the laminate.In this work, the mechanical and electrical properties of a recently developed piezoelectric composite material made of a Lead Zirconate Titanate (PZT) powder embedded in an epoxy matrix are evaluated with finite element simulations of plane strain Statistical Volume Elements (SVEs). The homogenized properties are then implemented in a second finite element model of a composite specimen with the embedded self-sensing material and loaded in compression. The electrical sensitivity is evaluated as a function of the distance between the signal electrodes.The results show that the finite element models with the homogenized properties have decreasing sensitivity with increasing electrodes distance, in agreement with the experimental results from another work, in which Glass Fiber Reinforced Polymer (GFRP) laminates with the embedded piezoelectric composite are loaded in compression and tested for output signal.

Convolutional Autoencoders for Signal Reconstruction and their Application to Damage Signature Extraction

The utilization of Machine Learning (ML) techniques for Structural Health Monitoring (SHM) has increased in the last years. Using ML techniques for signal reconstruction has been explored in the literature of this field. In this work, a database of Ultrasonic Guided Waves (UGW), propagated through a thermoplastic composite plate, and generated and acquired with piezoelectric transducers (PZT), has been preprocessed, organized, and analyzed to reconstruct signals by using Convolutional Autoencoders (cAE) neural networks. This special type of autoencoders (AE) is based on the utilization of convolutional stages, which are formed by deep-learning layers that are especially useful for their utilization on discretized time-series signals, due to their ability to convolve different sections of the signal, thus extracting different features which are automatically learned by the network. The cAE, which have a bottleneck section in their middle part (between the encoder and the decoder sections), have the ability to reduce the dimensionality of the input data, thus allowing the extraction of a minimum number of relevant features of the signals. Summarizing, this paper presents a neural network designed as a cAE which is able to reconstruct data from a reduced number of features, reaching a correlation value between the real and the artificial data higher than 98%.

On the fusion between interferometric satellite data and in situ measurements for the monitoring of built heritage

Over the past decades, earthquakes, and other catastrophic events has highlighted the increasingly growing vulnerability of infrastructures, buildings, and architectural heritage structures. In addition to catastrophic events, often related to climate change, another fundamental aspect is represented by the lack of maintenance and monitoring of the asset. In the field of preservation of buildings and infrastructures, Structural Health Monitoring techniques can effectively contribute to the assessment of the health state of structures. In the case of structural monitoring using data-driven approaches, since the information depends on the type of data used, a great resource for knowing as much as possible about the structure is represented by the combination of multiple data. Thanks to the integration of different types of data, it is possible to know the conditions of the structure in more detail as different aspects can be combined. In this context, together with the data obtained from in situ monitoring systems, data obtained remotely, i.e. satellite data, can be used. There are different types of satellite data that can be used to study different aspects, e.g., multispectral data, hyperspectral data, and interferometric data, and they can make different contribution to civil engineering. In this paper, the exploitability of open-source interferometric data is investigated and they are studied for the purpose of their integration with data obtained from a monitoring system installed on a monumental building, in order to monitor and observe structural health.

Temperature-based damage detection for the commissioning dataset of the MX3D Bridge

Environmental and operational variations (EOV) remain a major obstacle for the successful transfer of structural health monitoring (SHM) techniques from laboratory experiments, such as cracked beam experiments, to full-scale structures, such as long-span bridges. With evidence that timely interventions significantly increase the service-life and reduce the overall life-cycle cost of ageing infrastructure, carrying out SHM in the presence of EOV, such as temperature, is therefore of high priority within the civil engineering community. The temperature-based measurement-interpretation (TB-MI) approach was developed to monitor the thermal response of an instrumented structure and detect changes linked to damage by minimising the impact that temperature variations have on anomaly detection techniques. The iterative regression-based thermal response prediction (IRBTRP) methodology is utilised in the TB-MI approach, and is trained on the healthy condition of the bridge to predict its undamaged response to temperature fluctuations. Thermal response predictions are compared to the measured response and deviations between them are indicative of a variation in the thermal response, due to structural change such as damage. Small deviations can then be identified using anomaly detection techniques, which results in earlier damage detection than if thermal response predictions had not been used. The TB-MI approach and the IRBTRP methodology have been applied to detect damage on the MX3D Bridge, the world’s first structure produced through metal additive manufacturing (i.e. 3D printing). This study demonstrates that the use of the TB-MI approach enables earlier and more widespread damage detection amongst multiple sensor groups, compared to when no temperature effects are considered. The adoption of the TB-MI approach can therefore greatly increase the reliability of and our reliance on SHM techniques for critical infrastructure.

Model Updating and Assessment using Axial Strains for a Statically Determinate Truss Bridge

The safety of aging structures over the course of their service life is given by structural reliability. Additionally, there is a lack of techniques available for processing raw structural health monitoring (SHM) data in a way that makes it possible to validate and/or update structural reliability. Along with the diagnosis of structural anomaly using SHM techniques, the prognosis of structural condition is also an important aspect. Field-measured strain responses can be used as an indication of structural safety and provide information regarding the load-carrying capacity of the structure. Reliability assessment can be conducted only if a more accurate digital analogue is obtained for the actual bridge and when the structural responses can be predicted accurately. This paper validates a digital model of a real-life railway truss bridge. Pamban bridge is a century-old railway bridge having one track and four internally statically determinate truss leaves. Electrical strain gauges are instrumented to measure the axial strain responses in 84 out of 92 members of the bridge. Strain responses of 1072 train movements that traversed the bridge from 1st January 2021 to 14th July 2021 are recorded, and root mean square error (RMSE) between these field-measured strain responses and analytically computed strain responses from the digital model are estimated. The stationary trend of the time history of RMSE values depicts constant structural reliability. A technique is also proposed to forecast structural strain responses, which is validated with field-measured strain responses.

Drive-by modal identification of railway bridges via on-board measurements from a single railroad vehicle

The global railway network spans over one million kilometers of tracks, and this extensive infrastructure is set to expand even further. The objective is to promote rail transportation as an environmentally sustainable solution to address the growing demands of mobility. A significant portion of these tracks spans across bridge structures, which must also accommodate the rising demands for mobility and increased travel speeds, placing additional demands in terms of imposed loads. At the same time, bridges worldwide suffer from aging, leading to the deterioration of their structural integrity. Such combined effects necessitate monitoring the structural health of bridges to ensure the quality and safety of railway networks by detecting possible alterations in their response characteristics. Traditional Structural Health Monitoring (SHM) techniques use stationary sensors affixed to the bridge structure, enabling the direct assessment of the collected data. While such approaches are reliable, they present limitations in the comprehensive inspection of multiple railway bridges within a network. As an alternative, mobile vibration-based sensing, utilizing sensors on passing trains, presents the potential to gather data from multiple railway bridges using only a few sensors installed on board trains. Furthermore, operating the sensor-equipped trains at frequent intervals allows for collecting continuous data, offering valuable insights into the ongoing deterioration of bridges. In light of this, our work proposes a model-based methodology for extracting the modal frequencies of bridges based on acceleration data collected from traversing trains. Our approach hinges on Kalman filtering for estimating the state and input of the train and employs a subspace identification method to ascertain the frequencies of the bridge. The ultimate goal is to develop a drive-by bridge monitoring scheme that accommodates the assessment of the remaining lifespan of bridges as well as timely repairs in the event of damage, ensuring the safety and reliability of rail transportation.

Dispersion aware matching pursuit decomposition of Lamb wave signals for structural health monitoring of thin plates structures

Structural Health Monitoring (SHM) techniques are key to monitor in real time the health state of engineering structures, where damage type, location and severity are to be estimated by applying signal processing and deep learning techniques to temporal signals measured by sensors coming from the structure under study. Among the most widely used signal processing techniques in the SHM community is the Matching Pursuit Method (MPM), which allows to extract key features from a measured signal. MPM simply consists in approximating temporal data as a sum of different terms composed of a delayed and scaled signal called atom. This signal decomposition approach is however limited to non-dispersive signals which is not the case when dealing with Lamb waves signals widely used in the SHM of thin structures. In this case, in addition of delays and attenuations, wave packed also endure dispersion caused by the fact that all the frequencies do not propagate at the same speed within the structures under study. In this context, an improved version of Matching Pursuit is proposed in the present work, which address the dispersion phenomena by decomposing a measured signal as delayed and dispersed impulse response of an atom, obtaining better features for Lamb wave measurements. The performance of the developed technique is tested for the approximation of real measured signals, showing its better performance compared to classical MPM, especially when dealing with dispersive signals. This improved signal decomposition can be very useful for SHM purposes.

SHM to detect and characterize impact events in metallic aircraft structure

Aircraft structures are susceptible to foreign object impacts, which may occur during manufacturing, maintenance and in-service. Sizes of these impacted objects especially during in-service can range from a small rock to a large bird. Common ways to detect such impacts are based on flight / ground crew observations and reports leading to close examinations of structures using non-destructive evaluation (NDE) techniques. If undetected these impact damages can grow during service loading and may be detrimental to flight safety. Therefore, timely detection of any signs of impact damages are critical such that proper maintenance actions can be taken. The aim is to develop methodologies using Structural Health Monitoring (SHM) techniques to detect and characterize foreign object impact events. In this experiment, a cut-out of an aluminum panel measuring 31 x 26 inches from an out-of-service aircraft was used. The panel was instrumented with four Lead Zirconate Titanate (PZT) sensors from Acellent Inc., as well as, four Acoustic Emission (AE) sensors from Mistras Inc. Impedance and susceptance measurements were acquired to assess the proper functionality of the PZT sensors before and after the impact events. Both the PZTs and the AE sensors were directly connected to a digital oscilloscope, without any amplification and / or filtering for acquiring raw data during the impact events. An instrumented multi-use tapper was designed and developed to calibrate the system, as well as, to record the impulse (impact force and time) during the impact events. The acquired data were processed using physics-based and machine learning techniques to detect and characterize the impact events.