Search

In recent years, many innovative optimization algorithms have been developed. These algorithms have been employed to solve structural damage detection problems as an inverse solution. However, traditional optimization methods such as particle swarm optimization, simulated annealing (SA), and genetic algorithm are constantly employed to detect damages in the structures. This paper reviews the application of SA in different disciplines of structural health monitoring, such as damage detection, finite element model updating, optimal sensor placement, and system identification. The methodologies, objectives, and results of publications conducted between 1995 and 2021 are analyzed. This paper also provides an in-depth discussion of different open questions and research directions in this area.

This study intends to investigate the application of model updating based on forced vibration data to a simply-supported truss bridge. A fast Bayesian FFT method was used to perform the modal identification obtained from field tests, and the Transitional Markov Chain Monte Carlo (TMCMC) algorithm is employed to generate samples. Although updating as many parameters as possible is the ideal model update process, it is not practical to identify all the parameters because of limitation of the experimental data. The bridge was thus divided into several clusters, and the values of the updated parameters of the members in the same cluster are assumed to be equal. Two model updating schemes were discussed as an example to investigate the effect of parameter selection, such as how to model the spring at each support, in model updating process. It was observed that although models with more parameters tend to fit better, the updated result often showed a different trend from the engineering prediction., Part of the Lecture Notes in Civil Engineering book series (LNCE, volume 224)

Structural health condition monitoring of bridge structures has been a concern in the last decades due to their aging and deterioration, in which the core task is damage detection. Recently, the drive-by method has gained much attention as it only needs several sensors installed on the passing vehicle. In this paper, we proposed an automatic damage detection method, which can be exploited in real time when the vehicle is passing the bridge. There are three steps in the proposed method: (1) The vehicle’s framed short-time vibrations instead of full-length data are utilized for training a deep auto-encoder model; at this stage, not commonly used time-domain accelerations of the passing vehicle, but its selected frequency-domain responses are employed to circumvent the influence of noises, (2) For the bridge with unknown health conditions, damage indicators can be extracted from its passing vehicle’s short-time vibration data using the trained model, and (3) The bridge’s health states are determined by real-timeextracted damage indicators. To verify the proposed idea, a U-shaped continuous beam and a model truck are used to simulate the vehicle bridge interaction system in engineering. Results showed that the proposed method could identify the bridge’s damage with an accuracy of 86.2% when different severity was considered. In addition, it was observed that higher damage severity could not be revealed by greater values of damage indicators in the laboratory test. Instead, a novel index called identified damage ratios was employed as a reference for assessing the severity of the bridge’s damage. It was shown that with the increase in damage severity, the index would increase and gradually approach 100%.

Vibration properties of civil structures, which are commonly analysed for damage detection, are affected by changing environmental and operational conditions, and most notably are subjected to bilinear effects from changing ambient temperature conditions. Therefore, damage detection in structures during the past decade has focused on eliminating the effects of these changing environments that affect the vibration properties of the structures. Several methods have been proposed in the literature to tackle the non-linear effects from changing environments. However, these methods can only analyse systems (e.g. natural frequency–environmental and operational system) that have an incremental change in relationship; they cannot model the bilinear effects from the changing temperature conditions, which may lead to false alerts. Hence, a damage detection method is proposed in this paper to tackle the piecewise effects from changing temperature conditions. The method makes use of a Gaussian mixture model to separate the different effects acting on the structures and uses principal component analysis for data processing. The method is applied to the Z24 Bridge, in Switzerland, which was subjected to bilinear effects from changing temperature conditions. The results obtained demonstrate that the proposed method successfully takes into account the piecewise effects to indicate the presence of damage.

Early damage detection plays an essential role in the safe and satisfactory maintenance of structures. This work investigates techniques use only damaged structure responses. A Timoshenko beam was modeled in finite element method, and an additional mass was applied along their length. Thus, a frequency-shift curve is observed, and different damage identification techniques were used, such as the discrete wavelet transform and the derivatives of the frequency-shift curve. A new index called wavelet damage ratio(WDR) is defined as a metric to measure the damage levels. Damages were simulated like a mass discontinuity and a rotational spring (stiffness damage). Both models were compared to experimental tests since the mass added to the structure is a non-destructive tool. It was evaluated different damage levels and positions. Numerical results showed that all proposed techniques are efficient techniques for damage identification in Timoshenko's beams concerning low computational cost and practical application.

The structural health monitoring (SHM) approach plays a key role not only in structural engineering but also in other various engineering disciplines by evaluating the safety and performance monitoring of the structures. The structural damage detection methods could be regarded as the core of SHM strategies. That is because the early detection of the damages and measures to be taken to repair and replace the damaged members with healthy ones could lead to economic advantages and would prevent human disasters. The optimization-based methods are one of the most popular techniques for damage detection. Using these methods, an objective function is minimized by an optimization algorithm during an iterative procedure. The performance of optimization algorithms has a significant impact on the accuracy of damage identification methodology. Hence, a wide variety of algorithms are employed to address optimization-based damage detection problems. Among different algorithms, the particle swarm optimization (PSO) approach has been of the most popular ones. PSO was initially proposed by Kennedy and Eberhart in 1995, and different variants were developed to improve its performance. This work investigates the objectives, methodologies, and results obtained by over 50 studies (2005-2020) in the context of the structural damage detection using PSO and its variants. Then, several important open research questions are highlighted. The paper also provides insights on the frequently used methodologies based on PSO, the computational time, and the accuracy of the existing methodologies.

[EN] Recent catastrophic events have aroused great interest in the scientific community regarding the evaluation and prediction of the structural response along the life cycle of infrastructures. Efforts are put into developing adequate health monitoring systems to help prevent future human life and economic losses. Here, two non-destructive damage detection methods are presented: the Frequency Response Function-based and the Spectral Density Function-based methods. The damage detection performance of both methods is compared through a particular case study, where different damage scenarios are analyzed in a 2D truss bridge. The reliability of each method is studied in terms of different prediction errors. Numerical results show that the PSD method for damage detection on a steel truss bridge structure provides more accurate and robust results when compared to that based on FRF., Grant PID2020-117056RB-I00 funded by MCIN/AEI/ 10.13039/501100011033 and by ERDF A way of making Europe.

Model order selection is a fundamental task in subspace identification for estimation of modal parameters, uncertainty propagation and damage diagnosis. However, the true model order and the related low-rank structure of the dynamic system are generally unknown. In this paper, a statistical methodology to actively select the dynamic signal subspace in covariance-driven subspace identification is developed on the basis of statistical analysis of the eigenvalue condition numbers of the output covariance Hankel matrix. It is shown that the condition numbers highly sensitive to random perturbations characterize the noise subspace. The signal subspace is separated from the noise subspace by analyzing two statistical parameters associated with the condition number sensitivity, whose thresholds are user-defined. A practical algorithm to retrieve the system dynamics is designed and demonstrated on a running example of a simulated wind turbine blade benchmark. The resultant framework is then applied in the context of damage detection on a medium-size wind turbine blade. It is demonstrated that the detectability of small damage is enhanced compared to the classic approaches and robustness of damage diagnosis is increased by reducing the number of false alarms., Mechanical Systems and Signal Processing, 197, ISSN:0888-3270, ISSN:1096-1216

In general, the electromechanical impedance-based SHM method (ISHM) uses a piezoelectric transducer as a sensor/actuator to excite/measure the dynamic response of a mechanical structure under investigation to find incipient damage. The SHM method requires many samples of impedance signatures to analyse the behaviour of the system and draw a diagnostic. This contribution proposes a method to generate new impedance signatures as based on a few measured signatures. The signature generator operates through the Monte Carlo method. This approach proposes drastically reducing the number of measured samples normally used in the ISHM. This reduction can be as large as 93%. For this aim, a case study is proposed using an “I” profile structure with four levels of damage. Moreover, 33 impedance signatures for each level of damage were measured. Then, the Monte Carlo method was used to generate 400 virtual signatures. Finally, the generated signatures were compared with the experimentally acquired ones to measure the error associated with the generated signatures. In conclusion, this contribution presents a method that uses the properties of impedance signatures to store them and, if necessary, uses these signatures to generate numerical signatures, thus reducing the need to store a large amount of data., Published in International Journal of Advances in Engineering & Technology (IJAET), Volume 16 Issue 3, pp. 105-117, June 2023. Available at: https://www.ijaet.org/media/4I75-IJAET1603617-v16-i3-pp85-104.pdf

In the field of structural health monitoring, Lamb Wave has become one of the most widely used inspection tools due to its advantages of wide detection range and high sensitivity. In this paper, a new damage detection method for honeycomb sandwich structures based on frequency spectrum and Lamb Wave Tomography is proposed. By means of simulation and experiment, a certain number of sensors were placed on the honeycomb sandwich plate to stimulate and receive the signals in both undamaged and damaged cases. By Lamb Wave Tomography, the differences of signals before and after damage were compared, and the damage indexes were calculated. Furthermore, the probability of each sensor path containing damage was analyzed, and the damage image was finally realized. The technology does not require analysis of the complex multimode propagation properties of Lamb Wave, nor does it require understanding and modeling of the properties of materials or structures. In both simulation and experiment, the localization errors of the damage conform to the detection requirements, thus verifying that the method has certain feasibility in damage detection.

This paper introduces a multistep damage identification process that is both straightforward and useful for identifying damage in buildings with regular plan geometries. The algorithm proposed in this study combines the utilization of a multi-damage sensitivity feature and MATLAB programming, providing a comprehensive approach for the structural health monitoring (SHM) of different structures through vibration analysis. The system utilizes accelerometers attached to the structure to capture data, which is then subjected to a classical statistical subspace-based damage detection test. This test focuses on monitoring changes in the data by analyzing modal parameters and statistically comparing them to the structure’s baseline behavior. By detecting deviations from the expected behavior, the algorithm identifies potential damage in the structure. Additionally, the algorithm includes a step to localize damage at the story level, relying on the jerk energy of acceleration. To demonstrate its effectiveness, the algorithm was applied to a steel shear frame model in laboratory tests. The model utilized in this study comprised a total height of 900 mm and incorporated three lumped masses. The investigation encompassed a range of scenarios involving both single and multiple damages, and the algorithm proposed in this research demonstrated the successful detection of the induced damages. The results indicate that the proposed system is an effective solution for monitoring building structure condition and detecting damage.

The Loewner framework has recently been proposed for the system identification of mechanical systems, mitigating the limitations of current frequency domain fitting processes for the extraction of modal parameters. In this work, the Loewner framework computational performance, in terms of the elapsed time till identification, is assessed. This is investigated on a hybrid, numerical and experimental dataset against two well-established system identification methods (least-squares complex exponential, LSCE, and subspace state space system identification, N4SID). Good results are achieved, in terms of better accuracy than LSCE and better computational performance than N4SID. Engineering and Physical Sciences Research Council (EPSRC): 2277626

The Loewner framework has recently been proposed for the system identification of mechanical systems, mitigating the limitations of current frequency domain fitting processes for the extraction of modal parameters. In this work, the Loewner framework computational performance, in terms of the elapsed time till identification, is assessed. This is investigated on a hybrid, numerical and experimental dataset against two well-established system identification methods (least-squares complex exponential, LSCE, and subspace state space system identification, N4SID). Good results are achieved, in terms of better accuracy than LSCE and better computational performance than N4SID.

Structural health monitoring (SHM) is crucial for ensuring the safety and performance of offshore platforms. SHM uses advanced sensor systems to detect and respond to negative changes in structures, improving their reliability and extending their life cycle. Model updating methods are also useful for sensitivity analysis. It is feasible to discuss and introduce established techniques for detecting damage in structures by utilizing their mode shapes. In this research, by considering reducing the stiffness of elements in the damage scenarios, we conducted simulations of the models in MATLAB, including both two-dimensional and three-dimensional structures, to update the method suggested by Wang. Wang’s method was improved to produce a sensitivity equation for the damaged structures. The sensitivity equation solution using a subset of mode shapes data was found to evaluate structural parameter changes. Comparing the updated results for Wang’s method and the suggested method in the two- and three-dimensional frames showed a noticeable modification in damage recognition. Furthermore, the suggested method can update a model containing measurement errors. Since Wang’s damage detection formulation is suitable only for 2D structures, this modified framework provides a more accurate decision-making tool for damage detection of structures, regardless of whether a 2D or 3D formulation is used.

This study proposes a methodology to predict the damage condition of Reinforced Concrete (RC) resisting-moment frame buildings using Machine Learning (ML) methods. Structural members of six hundred RC buildings with varying stories and spans in X and Y directions were designed using the virtual work method. Sixty thousand time-history analyses using ten spectrum-matched earthquake records and ten scaling factors were carried out to cover the structures’ elastic and inelastic behavior. The buildings and earthquake records were split randomly into training data and testing data to predict the damage condition of new ones. In order to reduce bias, the random selection of buildings and earthquake records was carried out several times, and the mean and standard deviation of the accuracy were obtained. Moreover, 27 Intensity Measures (IM) based on acceleration, velocity, or displacement from the ground and roof sensor responses were used to capture the building’s behavior features. The ML methods used IMs, the number of stories, and the number of spans in X and Y directions as input data and the maximum inter-story drift ratio as output data. Finally, seven Machine Learning (ML) methods were trained to predict the damage condition of buildings, finding the best set of training buildings, IMs, and ML methods for the highest prediction accuracy.

In this paper, the feasibility of using far-field acoustic measurements as a non-contact monitoring technique for wind turbine blade leading edge erosion is assessed. For this purpose, a DU96 W180 airfoil with several eroded leading edge configurations of different severities is experimentally investigated. The eroded leading edges are designed with pits, gouges and coating delamination scaled from a real eroded blade. To assess the feasibility of the technique in quasi-realistic configurations, experiments are carried out under clean and turbulent inflow conditions. Acoustic measurements are performed with a phased microphone array. In the absence of inflow turbulence, because of the low Reynolds number at which the experiments are carried out, the case with minor erosion severity shows similar far-field noise spectra as the clean leading-edge cases, i.e., the presence of tonal peaks caused by laminar boundary layer instability noise through a self-sustained feedback loop but with higher tonal amplitudes. Increasing the damage level (considered as moderate erosion), the spectra of the noise scattered from the suction side show that the tonal peaks shift to higher frequencies and have lower amplitudes, thus suggesting that the damage alters the flow features responsible for the acoustic feedback loop; whereas, the spectra from the pressure side show a broadband noise distribution. For heavy erosion, the far-field noise spectra show broadband features from both airfoil sides, thus suggesting that the damage has fully forced the transition to turbulent flow; in which case, an increase in the low-frequency content is observed. Conversely, in the presence of turbulent inflow, when comparing the noise scattered at the trailing edge, no difference is found. However, leading edge impingement noise decreases at medium–high frequency compared with the baseline case at a chord-length-based Strouhal number St_C~10. The experimental results also suggest that the delamination feature is the one which is the most easily detectable and the approach is valid for a wide range of angles of attack and inflow velocity.

Regular inspection and maintenance of infrastructure facilities are crucial to ensure their functionality and safety for users. However, current inspection methods are labor-intensive and can vary depending on the inspector. To improve this process, modern sensor systems and machine learning algorithms can be deployed to detect defects based on rapidly acquired data, resulting in lower downtime. A quality-controlled processing chain allows to provide hence informed uncertainty assessments to inspection operators. In this study, we present several Deeplab V3+ models optimized to predict corroded segments of the quay wall at JadeWeserPort, Germany, which is a dataset from the 3D HydroMapper research project. Our models achieve generally high accuracy in detecting this damage type. Therefore, we examine the use of a Region Growing-based weakly supervised approach to efficiently extend our model to other common types in the future. This approach achieves about 90 % of the results compared to corresponding fully supervised networks, of which a ResNet-50 variant peaks at 55.6 % Intersection-over-Union regarding the test set’s corrosion class.

Woven fabric composite structures are applied in a wide range of industrial applications. Composite structures are vulnerable to damage from working in complex conditions and environments, which threatens the safety of the in-service structure. Damage detection based on Lamb waves is one of the most promising structural health monitoring (SHM) techniques for composite materials. In this paper, based on guided Lamb waves, a lightweight deep-learning approach is proposed for identifying damaged regions in woven fabric composite structures. The designed deep neural networks are built using group convolution and depthwise separated convolution, which can reduce the parameters considerably. The input of this model is a multi-channel matrix transformed by a one-dimensional guided wave signal. In addition, channel shuffling is introduced to increase the interaction between features, and a multi-head self-attention module is designed to increase the model’s global modeling capabilities. The relevant experimental results show that the proposed SHM approach can achieve a recognition accuracy of 100% after only eight epochs of training, and the proposed LCANet has only 4.10% of the parameters of contrastive SHM methods, which further validates the effectiveness and reliability of the proposed method.

Instance-level object re-identification is a fundamental computer vision task, with applications from image retrieval to intelligent monitoring and fraud detection. In this work, we propose the novel task of damaged object re-identification, which aims at distinguishing changes in visual appearance due to deformations or missing parts from subtle intra-class variations. To explore this task, we leverage the power of computer-generated imagery to create, in a semi-automatic fashion, high-quality synthetic images of the same bike before and after a damage occurs. The resulting dataset, Bent & Broken Bicycles (BBBicycles), contains 39,200 images and 2,800 unique bike instances spanning 20 different bike models. As a baseline for this task, we propose TransReI3D, a multi-task, transformer-based deep network unifying damage detection (framed as a multi-label classification task) with object re-identification. The BBBicycles dataset is available at https://huggingface.co/datasets/GrainsPolito/BBBicycles

In this paper, a structural health monitoring (SHM) system is proposed to provide automatic early warning for detecting damage and its location in composite pipelines at an early stage. The study considers a basalt fiber reinforced polymer (BFRP) pipeline with an embedded Fiber Bragg grating (FBG) sensory system and first discusses the shortcomings and challenges with incorporating FBG sensors for accurate detection of damage information in pipelines. The novelty and the main focus of this study is, however, a proposed approach that relies on designing an integrated sensing-diagnostic SHM system that has the capability to detect damage in composite pipelines at an early stage via implementation of an artificial intelligence (AI)-based algorithm combining deep learning and other efficient machine learning methods using an Enhanced Convolutional Neural Network (ECNN) without retraining the model. The proposed architecture replaces the softmax layer by a k-Nearest Neighbor (k-NN) algorithm for inference. Finite element models are developed and calibrated by the results of pipe measurements under damage tests. The models are then used to assess the patterns of the strain distributions of the pipeline under internal pressure loading and under pressure changes due to bursts, and to find the relationship of strains at different locations axially and circumferentially. A prediction algorithm for pipe damage mechanisms using distributed strain patterns is also developed. The ECNN is designed and trained to identify the condition of pipe deterioration so the initiation of damage can be detected. The strain results from the current method and the available experimental results in the literature show excellent agreement. The average error between the ECNN data and FBG sensor data is 0.093%, thus confirming the reliability and accuracy of the proposed method. The proposed ECNN achieves high performance with 93.33% accuracy (P%), 91.18% regression rate (R%) and a 90.54% F1-score (F%).

The bearing plate is an important part of a tendon–anchorage subsystem; however, its function and safety can be compromised by factors such as fatigue and corrosion. This paper explores the feasibility of the electromechanical impedance (EMI) technique for fatigue crack detection in the bearing plate of a prestressed anchorage. Firstly, the theory of the EMI technique is presented. Next, a well-established prestressed anchorage in the literature is selected as the target structure. Thirdly, a 3D finite element model of the PZT transducer–target anchorage subsystem is simulated, consisting of a concrete segment, a steel anchor head, and a steel bearing plate instrumented with a PZT transducer. The prestress load is applied to the anchorage via the anchor head. The EMI response of the target structure is numerically obtained under different simulated fatigue cracks in the bearing plate using the linear impedance analysis in the frequency domain. Finally, the resulting EMI response was quantified using two damage metrics: root-mean-square deviation and correlation coefficient deviation. These metrics are then compared with a threshold to identify the presence of cracks in the bearing plate. The results show that the simulated cracks in the bearing plate are successfully detected by tracking the shifts in the damage metrics. The numerical investigation demonstrates the potential of the EMI technique as a non-destructive testing method for assessing the structural integrity of prestressed structures.

A novel method is proposed for the damage identification of modal bridge expansion joints (MBEJs) based on sound signals. Two modal bridge expansion joint specimens were fabricated to simulate healthy and damaged states. A microphone was used to collect the impact signals from different specimens. The wavelet packet energy ratio of the sound signal was used to identify the difference in specimen state. Firstly, the wavelet packet energy ratio was used to establish the feature vectors, which were reduced dimensionality using principal component analysis. Subsequently, a support vector data description model was established to detect the difference in the signals. The identification effects of three parameter optimization methods (particle swarm optimization, genetic algorithm optimization, and Bayesian optimization) were compared. The results showed that the wavelet packet energy ratio of sound signals could effectively distinguish the state of the support bar. The support vector data description of Bayesian optimization worked best, and the proposed method could successfully detect damage to the support bar of MBEJs with an accuracy of 99%.

Buried pipelines, such as waterworks pipelines, are critical for transmitting essential resources and energy in modern cities, but the risk of pipeline failure, especially due to third-party interference, is a major concern. While various studies have focused on leak detection in waterworks pipelines, research on preventing impact damage is limited. To address this issue, this study proposes a novel algorithm that utilizes energy and similarity measurements for impact detection and compares it theoretically to existing leak-detection methods. The proposed algorithm utilizes frequency-domain kurtosis to determine the frequency band on which the energy of the impact signals is concentrated, along with a time-shift coherence function to measure the similarity of the signals. The application of the source location using the filtered signals enables accurate detection of the location of third-party interference. The proposed algorithm aims to ensure the safety and to prevent failures of buried pipelines. To verify the feasibility of the proposed algorithm, an excavation experiment using a backhoe was conducted on an in-service waterworks pipeline with a diameter of 2200 mm and a burial depth of 3 m. This experiment confirmed the effectiveness of the proposed algorithm in preventing failures of buried pipelines and demonstrated its practical applicability in the field. The experiment also validated the algorithm’s ability to detect third-party interference damage at various points.

Structural Health Monitoring (SHM) represents a very powerful tool to assess the health condition of buildings. In recent years, the growing availability of high-resolution SAR satellite images has made possible the application of multi-temporal Interferometric Synthetic Aperture Radar (MT-InSAR) techniques for structural monitoring purposes, with high precision, low costs, timesaving, and the possibility to investigate wide areas. However, a comprehensive validation of the effectiveness of MT-InSAR in this application field has not been achieved yet. For this reason, in this paper a comparison between interferometric data and on-site measurement of displacements is proposed. The application case study is the Civic Tower of the city of L’Aquila (Abruzzo Region, Italy). After the seismic events that affected the area in 2009, an on-site monitoring system was installed on the tower to detect any changes in the damage pattern in the period 2010–2013. Furthermore, images acquired by COSMO-SkyMed constellation in Stripmap mode (~3 m resolution) during the same period were processed by the Permanent Scatterer-InSAR (PSI) technique to estimate the deformation of the structure and the surrounding area. The obtained results indicate that both methods are consistent in the measurement of displacement trends of the building and a slight rotation/displacement of the tower was detected. Such evidence highlights both the huge potential and the limitations of using InSAR techniques for SHM.

Single-view computer vision models for vehicle damage inspection often suffer from strong light reflections. To resolve this, multiple images under various viewpoints can be used. However, multiple views increase the complexity as multi-view training data, specialized models, and damage re-identification over different views are required. In addition, traditional point cloud applications require large computational power, being impractical for edge computing. Therefore, multi-view damage inspection has not yet found its way into practical applications. We present a novel approach that projects the results from widely available single-view computer vision models onto 3D representations, to combine the detections from various viewpoints. With this, we leverage all advantages of multi-view damage inspection, without the need for multi-view training data and specialized models or hardware. We conduct a practical evaluation using a drive-through camera setup, to show the applicability of the methods in practice. We show that our proposed method successfully combines similar damages across viewpoints, reducing the number of duplicate damages by almost 99%. In addition, we show that our approach reduces the number of false positives by 96%. The proposed method leverages the existing single-view training data and single-view deep learning models to make multi-view inspection more accessible for practical implementations.

Huge swirling storms known as hurricanes are tropical storms appearing in the North Atlantic Ocean and Northeast Pacific that result in winds of 120 km/hour and higher. The winds occurring during hurricanes are catastrophic resulting in immense damage to human life and property. Rapid assessment of damage caused by hurricanes is extremely important for the first responders. But this process is usually slow, expensive, labor intensive and prone to errors. The advancements in remote sensing and computer vision help in observing Earth at a different scale. In this paper, a Convolutional Neural Network model has been designed that assesses the damage caused to buildings of post hurricane satellite images. The images have been classified as Damaged and Undamaged. The model is composed of five convolutional layers, five pooling layers, one flattening layer, one dropout layer and two dense layers. Hurricane Harvey dataset consisting of 23000 images of size 128 X 128 pixels has been used in this paper. The proposed model performed best at learning rate of 0.00001 and 30 epochs with the Adam optimizer obtaining an accuracy of 0.95, precision of 0.97, recall of 0.96 and F1-score of 0.96. It also achieved the best accuracy and minimum loss.

A novel approach to active structural health monitoring and damage detection of massive reinforced concrete structures using piezoelectric smart aggregates is presented in this paper. An innovative three-dimensional damage index, based on wavelet signal decomposition and energy of wave propagation, is derived in matrix form. Although the proposed three-dimensional damage index can be used for all types of reinforced concrete structures, it is primarily recommended for massive infrastructure buildings. The approach proposed in this paper is theoretically considered for an arbitrary shape of a reinforced concrete element, and it is numerically verified for various scenarios by varying the geometry of reinforced concrete elements, as well as the position, size and quantity of damage. Quasi-static analysis of piezoelectric smart aggregates is modelled using a standard finite element method, and the explicit finite element method is successfully applied in this research for modelling propagation of ultrasonic waves. The results based on numerically generated simulations indicate that the new approach to non-destructive damage detection using three-dimensional damage indexes is quite promising. However, an experimental verification of the proposed damage index will certainly be required in future research.

A novel approach to damage detection based on dispersion analysis and signal processing methods is described. The proposed method was used on a scaled experimental model of a jacket-type offshore platform. A forced vibration test was conducted on the platform to acquire the acceleration signals. The frequency spectrum of the first intrinsic mode function of the recorded signals was obtained by the Hilbert transform (HT); it was found that damage engendered dispersion in the extracted frequencies. A novel damage index, capable of accurate damage detection and based on the Mahalanobis distance dispersion of the HT frequency spectrum was thus developed. The results of this work show that the proposed index can determine the location and severity of damage with acceptable accuracy.

Materials under advanced characterization methods demands the ever-increasing data collection and storage capacities and pose a challenge in the modern materials science which were understood to behave in a typical way. In contrary, the damage in any composites cause rejection during the materials screening for the destined applications. Any kind of micro damages which are insensitive to bare observation could be the reason for catastrophic failures. Many composites, be it sandwich type or any other needs to be free from any micro flaws. Thus it is inevitable for the material designers to develop sandwich materials free from any kind of damages. Thus the damage/crack detection plays an important attribute in the development of sandwich composites. The damage detection requires all new procedures for rapid interpreting and analyzing the data collected for the damage and helps to obtain a best materials discovery for the needy purpose.The work presented herein endeavours to solve the issues with current crack detection and classification practices of sandwich composites, and it is developed for achieving high performance. In this work authors leverage different machine learning algorithms for classifying the damages and non-damaged composites. And in which deep learning is significantly yield good accuracy.

International audience; For mechanical system structural health monitoring, a new residual generation method is proposed in this paper, inspired by a recent result on subspace system identification. It improves statistical properties of the existing subspace residual, which has been naturally derived from the standard subspace system identification method. Replacing the monitored system state-space model by the Kalman filter one-step ahead predictor is the key element of the improvement in statistical properties, as originally proposed by Verhaegen and Hansson in the design of a new subspace system identification method.

A recent survey of Europe’s highway infrastructure has concluded that almost half of Europe’s bridges are nearing the end of their design live. Work in the wider Structural Health Monitoring sector is aiming to develop reliable and cost-effective methods for verifying condition, remaining service life and safety of ageing structures. Most bridge condition assessment methods are based on deflection, acceleration or strain measurements. This paper looks at the possibility of using rotation measurements as a main parameter to identify damage. This study looks at numerical analyses of a moving point load on a one-dimensional bridge model to provide the theoretical basis of the proposed damage detection method. It is shown that when local damage occurs, even when it is remote from a sensor location, it results in an increase in the magnitude of rotation measurements. This study looks at how best to exploit this fact for damage detection. A number of damage scenarios, sensor locations, and load arrangements are investigated in this study and their influence on the ability of the algorithm to detect damage are reported.

Monitoring damage in concrete structures is crucial for maintaining the health of structural systems. The implementation of computer vision has been the key for providing accurate and quantitative monitoring. Recent development uses the robustness of deep-learning-aided computer vision, especially the convolutional neural network model. The convolutional neural network is not only accurate but also flexible in various scenarios. The convolutional neural network has been constructed to classify image in terms of individual pixel, namely pixel-level detection, which is especially useful in detecting and classifying damage in fine-grained detail. Moreover, in the real-world scenario, the scenes are mostly very complex with varying foreign objects other than concrete. Therefore, this study will focus on implementing a pixel-level convolutional neural network for concrete surface damage detection with complicated surrounding image settings. Since there are multiple types of damage on concrete surfaces, the convolutional neural network model will be trained to detect three types of damages, namely cracks, spallings, and voids. The training architecture will adopt U-Net and DeepLabV3+. Both models are compared using the evaluation metrics and the predicted results. The dataset used for the neural network training is self-built and contains multiple concrete damages and complex foregrounds on every image. To deal with overfitting, the dataset is augmented, and the models are regularized using L1 and Spatial dropout. U-Net slightly outperforms DeepLabV3+ with U-Net scores 0.7199 and 0.5993 on F1 and mIoU, respectively, while DeepLabV3+ scores 0.6478 and 0.5174 on F1 and mIoU, respectively. Given the complexity of the dataset and extensive image labeling, the neural network models achieved satisfactory results.

The development of a methodology for accurate and reliable condition assessment of civil struc-tures has become very important. The finite element (FE) model updating method provides an efficient, non-destructive, global damage identification technique, which is based on the fact that the modal parameters (e.g. natural frequencies and mode shapes) of the structure are af-fected by structural damage. In the FE model, the damage is represented by a change of the structural parameters and can be identified by updating the FE model to the measured modal parameters. This thesis describes an iterative sensitivity-based FE model updating method in which the discrepancies between the natural frequencies of the numerical model and the real structure are minimized. Furthermore, the updating procedure is applied to the model of the University of the Federal Armed Forces (UniBw) in Munich. For this purpose, it was necessary to design the model and develop an interface between the finite element software (ANSYS) and a computing software (MATLAB), which can apply the model updating technique to the finite element model.

[EN] The ageing infrastructure in ports requires regular inspection. This inspection is currently carried out manually by divers who sense by hand the entire underwater infrastructure. This process is cost-intensive as it requires a considerable amount of time and manpower. To overcome these difficulties, we propose to scan the above and underwater port structure with a Multi-Sensor-System (MSS), and -by a fully automated process- classify the obtained point cloud into damaged and undamaged regions. The MSS consists of a high-resolution hydro-acoustic underwater multi-beam echo-sounder, an above-water profile laser scanner, and five HDR cameras. In addition to the IMU-GPS/GNSS method known from various applications, hybrid referencing with automatically tracking total stations is used for positioning. The main research idea is based on 3D data from TLS, multi-beam or dense image matching. To that aim, we build a rasterised heightfield of the point cloud of a harbour structure by subtracting a CADbased geometry. To do this, we fit regular shapes into the point cloud and determine the distance of the points to the geometry. This latter is propagated through a Convolutional Neural Network (CNN) which detects anomalies. We make use of two methods: the VGG19 Deep Neural Network (DNN) and Local-Outlier-Factors (LOF). We tested our approach on simulated training data and evaluated it on a real-world dataset in Lübeck, Germany measured by an MSS. We showed that our approach can achieve a fully automated, reproducible, quality-controlled damage detection that can analyse the whole structure instead of the sample wise manual method with divers. We were able to achieve valuable results for our application., Open Access funding enabled and organized by Projekt DEAL. This research was funded by German Federal Ministry of Transport and Digital Infrastructure grant number 19H18011C.

This study focuses on developing and examining the effectiveness of Transfer Learning (TL) for structural health monitoring (SHM) systems that transfer knowledge about damage states from one structure (i.e., the source domain) to another structure (i.e., the target domain). Transfer Learning (TL) is an efficient method for knowledge transfer and mapping from source to target domains. In addition, Proper Orthogonal Modes (POMs), which help classify behavior and health, provide a promising tool for damage identification in structural systems. Previous investigations show that damage intensity and location are highly correlated with POM variations for structures under unknown loads. To train damage identification algorithms based on POMs and ML, one generally needs to use multiple simulations to generate damage scenarios. The developed process is applied to a simply supported truss span in a multi-span railway bridge. TL is first used to obtain relationships between POMs for two modeled bridges: one being a source model (i.e., labeled) and the other being the target modeled bridge (i.e., unlabeled). This technique is then implemented to develop POMs for a damaged, unknown target using TL that links source and target POMs. It is shown that the trained knowledge from one bridge was effectively generalized to other, somewhat similar, bridges in the population.

This paper presents a novel algorithm for compensating the changes in conductance signatures of a piezo sensor due to the temperature variation employed in condition monitoring using the electro-mechanical impedance (EMI) approach. It is crucial to consider the changes in an EMI signature due to temperature before using it for comparison with the baseline signature. The shifts in the signature due to temperature can be misinterpreted as damages to the structure, which might also result in a false alarm. In the present study, the compensation values are calculated based on experiments on piezo sensors both in a free boundary condition and in a bonded condition on a metallic host structure. The values were further validated experimentally for damage detection on a large 2D steel plate structure. The variation in first natural frequency values for the unbonded piezo sensor at different temperatures has been used to develop the compensation algorithms. Whereas, in the case of the bonded sensor, the shift in structural peaks has been used. The developed compensation relations showed promising results in damage detection. Lastly, a finite element-based study has also been performed, supporting the experimental findings. The outcome of this study will aid in the compensation of the signatures in the structure due to temperature variation in the conductance signature.

Due to the large size of offshore wind turbine blades (OWTBs) and the corrosive nature of salt water, OWTs need to be safer and more reliable that their onshore counterparts. To ensure blade reliability, an accurate and computationally efficient structural dynamic model is an essential ingredient. If damage occurs to the structure, the intrinsic properties will change, e.g., stiffness reduction. Therefore, the blade’s dynamic characteristics will differ from those of the intact ones. Hence, symptoms of the damage are reflected in the dynamic characteristics that can be extracted from the damaged blade. Thus, damage identification in OWTBs has become a significant research focus. In this study, modal model characteristics were used for developing an effective damage detection method for WTBs. The technique was used to identify the performance of the blade’s sections and discover the warning signs of damage. The method was based on a vibration-based technique. It was adopted by investigating the influence of reduced blade element rigidity and its effect on the other blade elements. A computational structural dynamics model using Rayleigh beam theory was employed to investigate the behaviour of each blade section. The National Renewable Energy Laboratory (NREL) 5MW blade benchmark was used to demonstrate the behaviour of different blade elements. Compared to previous studies in the literature, where only the simple structures were used, the present study offers a more comprehensive method to identify damage and determine the performance of complicated WTB sections. This technique can be implemented to identify the damage’s existence, and for diagnosis and decision support. The element most sensitive to damage was element number 14, which is NACA_64_618.

Refractory materials are basic materials widely used in industrial furnaces and thermal equipment. Their microstructure is similar to that of many heterogeneous high-performance materials used in micro/nanodevices. The presence of damage can reduce the mechanical properties and service life of refractory materials and even cause serious safety accidents. In this paper, a novel percussion and particle swarm optimization-support vector machine (PSO-SVM)-based method is proposed to detect damage in refractory materials. An impact is applied to the material and the generated sound is recorded. The percussion-induced sound signals are fed into a mel filter bank to generate time–frequency representations in the form of mel spectrograms. Then, two image descriptors—the local binary pattern (LBP) and histogram of oriented gradient (HOG)—are used to extract the texture information of the mel spectrogram. Finally, combining both HOG and LBP features, the fused features are input to the PSO-SVM algorithm to realize damage detection in refractory materials. The results demonstrated that the proposed method could identify five different degrees of damage of refractory materials, with an accuracy rate greater than 97%. Therefore, the percussion and PSO-SVM-based method proposed in this paper has high potential for field applications in damage detection in refractory material, and also has the potential to be extended to research on damage detection methods for other materials used in micro/nanodevices.

Vibration-based damage detection methods are a subcategory of Structural Health Monitoring (SHM) methods that rely on the fact that structural damage will affect the dynamic characteristic of a structure. The presented methodology uses Finite Element Models coupled with a metaheuristic optimization algorithm in order to locate the damage in a structure. The search domains of the optimization algorithm are the variables that control a parametric area, which is inserted into the FE model. During the optimization procedure, this area changes location, stiffness, and mass to simulate the effect of the physical damage. The final output is a damaged FE model which can approximate the dynamic response of the damaged structure and indicate the damaged area. For the current implementation of this Damage Detection Framework, the Particle Swarm Optimization algorithm is used. As an effective metric of the comparison between the FE model and the experimental structure, Transmittance Functions (TF) are used that require output only acceleration signals. As with most model-based methods, a common concern is the modeling error and how this can be surpassed. For this reason, the Dynamic Time Wrapping (DTW) algorithm is applied. When damage occurs in a structure it creates some differences between the Transmittance Functions (TF) of the healthy and the damaged state. With the use of DTW, the damaged pattern is recreated around the TF of the FE model, while creating the same differences and, thus, minimizing the modeling error. The effectiveness of the proposed methodology is tested on a small truss structure that consists of Carbon-Fiber Reinforced Polymer (CFRP) filament wound beams and aluminum connectors, where four cases are examined with the damage to be located on the composite material.

Concrete cracks have always been the focus of research because of the serious damage they cause to structures. With the updating of hardware and algorithms, the detection of concrete structure surface cracks based on computer vision has received extensive attention. This paper proposes an improved algorithm based on the open-source model Deeplabv3+ and names it Deeplabv3+ BDF according to the optimization strategy used. Deeplabv3+ BDF first replaces the original backbone Xception with MobileNetv2 and further replaces all standard convolutions with depthwise separable convolutions (DSC) to achieve a light weight. The feature map of a shallow convolution layer is additionally fused to improve the detail segmentation effect. A new strategy is proposed, which is different from the two-stage training. The model training is carried out in the order of transfer learning, coarse-annotation training and fine-annotation training. The comparative test results show that Deeplabv3+ BDF showed good performance in the validation set and achieved the highest mIoU and detection efficiency, reaching real-time and accurate detection.

Bridge inspections are relied heavily on visual inspection, and usually conducted within limited time windows, typically at night, to minimize their impact on traffic. This makes it difficult to inspect every meter of the structure, especially for largescale bridges with hard-to-access areas, which creates a risk of missing serious defects or even safety hazards. This paper presents a new technique for the semi-automated damage detection in tunnel linings and bridges using a hybrid approach based on photogrammetry and deep learning. The first approach involves using photogrammetry to reconstruct a 3D model. It is shown that a model with sub-centimeter accuracy can be obtained after noise removal. However, noise removal also reduces the point cloud density, making the 3D point cloud unsuitable for quantification of small-scale damages such as fine cracks. Therefore, the captured images are also analysed using deep convolutional neural network (CNN) models to enable crack detection and segmentation. For this aim, in the second approach, the 3D model is generated by the output of CNN models to enable crack localization and quantification on 3D digital model. These two approaches were evaluated in separate case studies, showing that the proposed technique could be a valuable tool to assist human inspectors in detecting, localizing, and quantifying defects on concrete structures. Semi‑autonomous inspection for concrete structures using digital models and a hybrid approach based on deep learning and photogrammetry

We introduce an approach for damage detection in gearboxes based on the analysis of sensor data with the multi-resolution dynamic mode decomposition (mrDMD). The application focus is the condition monitoring of wind turbine gearboxes under varying load conditions, in particular irregular and stochastic wind fluctuations. We analyze data stemming from a simulated vibration response of a simple nonlinear gearbox model in a healthy and damaged scenario and under different wind conditions. With mrDMD applied on time-delay snapshots of the sensor data, we can extract components in these vibration signals that highlight features related to damage and enable its identification. A comparison with Fourier analysis, Time Synchronous Averaging and Empirical Mode Decomposition shows the advantages of the proposed mrDMD-based data analysis approach for damage detection., 34 pages, 29 figures

During the last decades, significant efforts have been made to define appropriate Structural Health Monitoring (SHM) frameworks based on the vibration signatures collected by accelerometers. Data-driven approaches are increasingly adopted for damage detection through the identification of anomalies in the distribution of the frequencies. This paper analyzes the long-term monitoring data acquired from a system installed on the Matilde tower in Livorno (Italy). The tower is a historic masonry structure monitored since the end of 2018 using a wireless sensor network developed during the MOSCARDO project.

Bridge deck pavement damage has a significant effect on the driving safety and long-term durability of bridges. To achieve the damage detection and localization of bridge deck pavement, a three-stage detection method based on the you-only-look-once version 7 (YOLOv7) network and the revised LaneNet was proposed in this study. In stage 1, the Road Damage Dataset 202 (RDD2022) is preprocessed and adopted to train the YOLOv7 model, and five classes of damage were obtained. In stage 2, the LaneNet network was pruned to retain the semantic segmentation part, with the VGG16 network as an encoder to generate lane line binary images. In stage 3, the lane line binary images were post-processed by a proposed image processing algorithm to obtain the lane area. Based on the damage coordinates from stage 1, the final pavement damage classes and lane localization were obtained. The proposed method was compared and analyzed in the RDD2022 dataset, and was applied on the Fourth Nanjing Yangtze River Bridge in China. The results shows that the mean average precision (mAP) of YOLOv7 on the preprocessed RDD2022 dataset reaches 0.663, higher than that of other models in the YOLO series. The accuracy of the lane localization of the revised LaneNet is 0.933, higher than that of instance segmentation, 0.856. Meanwhile, the inference speed of the revised LaneNet is 12.3 frames per second (FPS) on NVIDIA GeForce RTX 3090, higher than that of instance segmentation 6.53 FPS. The proposed method can provide a reference for the maintenance of bridge deck pavement. Published version This research was funded by the National Natural Science Foundation of China (grant number: 51978155), the Postgraduate Research & Practice Innovation Program of Jiangsu Province (grant number: SJCX21_0056), and the Open Foundation of National Engineering Laboratory for High Speed Railway Construction (grant number: HSR202003).

Technical report on the activities carried out within the framework of the STRENGTH project.

This paper proposes a damage detection method based on the train-induced responses of high-speed railway box girders. Under the coupling effects of bending and torsion, the traditional damage detection method based on the Euler beam theory cannot be applied. In this research, the box girder section is divided into different components based on the plate element analysis method. The strain responses were preprocessed based on the principal component analysis (PCA) method to remove the influence of train operation variation. The residual error of the autoregressive (AR) model was used as a potential index of damage features. The optimal order of the model was determined based on the Bayesian information criterion (BIC) criterion. Finally, the confidence boundary (CB) of damage features (DF) constituting outliers can be estimated by the Gaussian inverse cumulative distribution function (ICDF). The numerical simulation results show that the proposed method in this paper can effectively identify, locate and quantify the damage, which verifies the accuracy of the proposed method. The proposed method effectively identifies the early damage of all components on the key section by using four strain sensors, and it is helpful for developing effective maintenance strategies for high-speed railway box girders.

In this paper, the feasibility of Structural Health Monitoring (SHM) employing a novel Fibonacy Sequence (FS)-based Optimization Algorithms (OAs) and up-to-date computing techniques is investigated for a large-scale railway bridge. During recent decades, numerous metaheuristic intelligent OAs have been proposed and immediately gained a lot of momentum. However, the major concern is how to employ OAs to deal with real-world problems, especially the SHM of large-scale structures. In addition to the requirement of high accuracy, a high computational cost is putting up a major barrier to the real application of OAs. Therefore, this article aims at addressing these two aforementioned issues. First, we propose employing the optimal ability of the golden ratio formulated by the well-known FS to remedy the shortcomings and improve the accuracy of OAs, specifically, a recently proposed new algorithm, namely Salp Swarm Algorithm (SSA). On the other hand, to deal with the high computational cost problems of OAs, we propose employing an up-to-date computing technique, termed superscalar processor to conduct a series of iterations in parallel. Moreover, in this work, the vectorization technique is also applied to reduce the size of the data. The obtained results show that the proposed approach is highly potential to apply for SHM of real large-scale structures.

Structural health monitoring (SHM) is damage detection strategy for aerospace, civiland mechanical infrastructure. This project tries to show that Lamb waves, that are being generated and sensed with piezoelectric transducers, can be used for damage detection in a SHM system. For these piezoelectric transducers to work, filtering and amplification circuits needs to be connected to them. This report include the design,simulation, assembly and testing of these circuits. Due to lack of time, it was not possible to generate and sense actual Lamb waves. The result of the thesis is thatsimulations and tests show that it is possible to generate and sense Lamb waves for damage detection in a SHM system Structural health monitoring (SHM) är en skadedetekteringsstrategi för flyg-,civil- och mekanisk infrastruktur. Detta projekt försöker visa att Lambvågor, som genereras och avkänns med piezoelektriska givare, kan användas för skadedetektering i ett SHM-system. För att dessa piezoelektriska givare ska fungera krävs att filtrerings- och förstärkningskretsar är anslutna till dem. Denna rapport inkluderar design, simulering, montering och testning av dessa kretsar. På grund av tidsbrist var det inte möjligt att generera eller avkänna Lambvågor. Resultatet av examensarbetet är att simuleringar och tester visar att det är möjligt att generera och avkänna Lambvågor för skadedetektering i ett SHM-system.