Search

This study addresses the challenges of data scarcity and class imbalance in structural health monitoring (SHM) of composite structures. Data-driven SHM techniques that benefit from non-destructive evaluation (NDE) are used in various composite structures. However, the lack of damaged state data causes data scarcity and class imbalance problems that prevent robust diagnostics of composite structures. This study introduces a novel data-driven multi-class data augmentation method for composite structures, employing a multi-class generative adversarial network (MC-GAN) for the first time to generate synthetic data for multiple classes without the need for excessive experimentation or simulation. Additionally, the MC-GAN model is integrated with the convolutional neural network (CNN) to develop the MC-GAN-CNN model for autonomous data augmentation and delamination detection. The approach has been validated using experimentally obtained vibrational data for laminated composites. The damage detection using manual feature extraction showed overfitting and very high standard deviation during 10-fold cross-validation for various machine learning models. However, the proposed method suggested a more rigorous assessment with a mean accuracy of 99.72 ± 0.08 %. In addition, the proposed framework assists in handling the delamination detection problem autonomously without requiring hand-crafted statistical features with a good generalization capability. • An intelligent data-driven framework for autonomous delamination detection. • Multi-class GAN model to overcome multi-class imbalance and scarce data. • Qualitative and quantitative assessment of synthetic data. • Delamination detection in laminated composites using CNN-based deep learning model. • The augmented dataset provided high accuracy, precision, recall and f1-score. [ABSTRACT FROM AUTHOR]

Composite structure is widely used in various technological fields because of its superior material properties. Composite structure detection technology has been exploring efficient and fast damage detection technology. In this paper, image-based NDT technology is proposed to detect composite damage using deep learning. A data set was established through literature, which contained images of damaged and non-damaged composite material structures. Then, five convolutional neural network models Alexnet, VGG16, ResNet-34, ResNet-50, and GoogleNet were used to automatically classify the damage. Finally, the performance of five pre-trained network architectures is evaluated, and the results show that RESNET-50 technology can successfully detect damage in a reasonable computation time with the highest accuracy and low complexity using relatively small image datasets. [ABSTRACT FROM AUTHOR]

Traditional vibration-based damage detection methods often involve human intervention in decision-making, therefore being time-consuming and error-prone. In this study, we propose using Artificial Neural Networks (ANNs) to detect patterns in the structural response and create accurate predictions. The features extracted from the response signal are the Relative Frequency Shifts (RFSs) of the first eight weak-axis bending vibration modes, and the predictions refer to the damage location. To increase the accuracy of the predictions, we propose a novel stacked neural network approach, capable of detecting damage locations with high accuracy. The dataset used for training involves, as input data, the RFSs calculated with an original method for numerous damage locations and severities. The following models were used as building blocks for our stacked approach: Multilayer Perceptron, Recurrent Neural Network, Long Short-term Memory, and Gated Recurrent Units. The entire beam was thus split into segments and each network was trained in this stacked model on one beam segment. All results obtained with the models are also compared to a standard neural network trained on the entire beam. The results obtained show that the model that performs the best contains 14 stacked two-layer feedforward networks. [ABSTRACT FROM AUTHOR]

Leading edge (LE) erosion is a type of damage that inhibits the aerodynamic performance of a wind turbine, resulting in high operation and maintenance (O&M) costs. This paper makes use of a small dataset consisting of 50 images of LE erosion and healthy blades for feature extraction and the training of four types of classifiers, namely, support vector machine (SVM), random forest, K-nearest neighbour (KNN), and multi-layer perceptron (MLP). Six feature extraction methods were used with these classifiers to train 24 models. The dataset has also been used to train a convolutional neural network (CNN) model developed using Keras. The purpose of this work is to determine whether classical machine learning (ML) classifiers trained with extracted features can produce higher-accuracy results, train faster, and classify faster than deep learning (DL) models for the application of LE damage detection of wind turbine blades. The oriented fast and rotated brief (ORB)-trained SVM achieved an accuracy of 90% ± 0.01, took 80.4 s to train, and achieved inference speeds of 63 frames per second (FPS), compared to the CNN model, which achieved an accuracy of 79.4% ± 2.07, took 4667.4 s to train, and achieved an inference speed of 1.3 FPS. These results suggest that classical ML models can be more accurate and efficient than DL models if the appropriate feature extraction method is used. [ABSTRACT FROM AUTHOR]

Detection of damage in a single tow ceramic matrix composite specimen has been achieved using orthogonal decomposition of volumetric tomographic datasets collected at four tensile loads. This decomposition approach has been applied at two different length scales: (i) individual fibres and (ii) bulk volumes containing fibres and matrix material. Volumes were first decomposed to feature vectors, orders of magnitude smaller than the original volume they describe, and then comparisons between datasets at different load levels were made in feature vector space. The results show quantitative measurements of damage location, damage morphology and the relative growth of this damage with increased load when compared with a dataset with less or no damage. No prior knowledge of the dataset or training of algorithms is required for damage to be detected, it is only necessary that at least two datasets are available for comparison, e.g. from in situ or repeated scanning measurements. Results are generated on significantly shorter timescales when compared with previous automated approaches to tomography data processing. This approach has the potential to be applied to damage detection in a range of materials through comparisons of volumetric datasets from a range of measurement or computational techniques. [ABSTRACT FROM AUTHOR]

In practical applications of wavelet transform, engineers and practitioners encounter challenges that arise due to the disparity between wavelet theory, which deals with continuous functions, and the digital nature of signals in engineering contexts. In particular, wavelet transform theory does not consider the effect of changes in digital signals on the result of the wavelet transform. This paper emphasizes the influence of the type of digital signals on the accuracy of wavelet transform in engineering applications and proposes an efficient wavelet function based on the derivative of the signal for better damage detection in beam structures. For this purpose, the obtained signals from the mode shapes of the steel beam are used to examine the efficiency of the proposed derivative-based wavelet transform. The effects of changes in boundary conditions, location of damage, and level of damage on the performance of the proposed method, are evaluated. Findings show that when we use the derivate of the signal in the wavelet transform, the location of damage in all damage scenarios is detected with high accuracy. This research demonstrates the importance of the type of signal used in the wavelet transform for enhancing the precision of fault and damage detection in signals. [ABSTRACT FROM AUTHOR]

• An analytical solution to the responses of a vehicle passing through continuous beams. • The quantitative relationship between vehicle acceleration and the damage. • Detailed comparison of the damage relationships for simply-supported and continuous beams. Damage detection for bridges using a passing vehicle has drawn much interest. Recent studies demonstrate that the tap-scan method is an efficient way to detect the change of beam bending stiffness. A quantitative relationship between the change of beam bending stiffness and the acceleration of a vehicle can be evaluated. However, the reported relationship is calibrated for a simply-supported beam, which may be unsuitable for continuous beams due to inherent structural differences. Addressing this, an analytical solution for damage detection for continuous beams using the tap-scan method is presented in this paper. Case studies reveal that damage relationships across different spans of continuous beams show negligible dependence on modal parameters and beam lengths. Consequently, the damage identification within any span of a continuous beam can be accomplished using the same damage relationship calibrated on a simply-supported beam. But it should be noticed that the damage relationship might differ by beam structural forms. The above result holds substantial implications for practical engineering scenarios, notably by diminishing the labor and complexity associated with the calibration of damage relationships for continuous beams. [ABSTRACT FROM AUTHOR]

This study addresses the challenge of detecting operational and environmental changes, termed linear damages, in building structures over their lifespan. Identification of these damages is crucial for enhancing serviceability and averting sudden disasters. However, the intricate nature of uncovering concealed changes results in demanding and time-intensive computations, posing a significant computational predicament for related algorithms. Moreover, structures are often exposed to diverse environmental noise, necessitating the development of a robust algorithm capable of effectively identifying subtly hidden damages amid varying noisy conditions with high accuracy and low time consumption. This research introduces a robust and expedited signal-based algorithm, comprising three key components: processing, feature selection, and classification. Multiresolution analysis through discrete wavelet transform is employed for processing, generating diverse features alongside several statistical indices. The grey wolf optimization algorithm is utilized for feature selection, yielding optimal features. This method not only ensures commendable performance under noisy circumstances compared with optimization algorithms such as particle swan optimization and genetic algorithms, as well as common feature extraction methods such as principal component analysis, it also accelerates computation speed by over four times compared with alternative feature-selection techniques such as ReliefF. Lastly, a supervised classification algorithm is integrated to discern distinct predefined scenarios. The efficacy of the proposed algorithm was validated using a comprehensive case study encompassing nine representative scenarios of operational and environmental damages. Incorporating four levels of noise to emulate real-world variations, the algorithm achieved compelling average accuracies of approximately 96%, 93%, 95%, 91.5%, and 89% at original data and signal-to-noise ratios (SNRs) of 10, 5, 1, and 0.5 dB, respectively. [ABSTRACT FROM AUTHOR]

The possibility of determining the integrity of a real structure subjected to non-invasive and non-destructive monitoring, such as that carried out by a series of accelerometers placed on the structure, is certainly a goal of extreme and current interest. In the present work, the results obtained from the processing of experimental data of a real structure are shown. The analyzed structure is a lattice structure approximately 9 m high, monitored with 18 uniaxial accelerometers positioned in pairs on 9 different levels. The data used refer to continuous monitoring that lasted for a total of 1 year, during which minor damage was caused to the structure by alternatively removing some bracings and repositioning them in the structure. Two methodologies detecting damage based on decomposition techniques of the acquired data were used and tested, as well as a methodology combining the two techniques. The results obtained are extremely interesting, as all the minor damage caused to the structure was identified by the processing methods used, based solely on the monitored data and without any knowledge of the real structure being analyzed. The results use 15 acquisitions in environmental conditions lasting 10 min each, a reasonable amount of time to get immediate feedback on possible damage to the structure. [ABSTRACT FROM AUTHOR]

Traditional methods of detecting concrete damage, such as manual inspection, are typically slow, labor‐intensive, and subjective. Integrating deep learning algorithms has automated this process, representing a significant advance in building damage inspection. Semantic segmentation, a technique within deep learning, is increasingly recognized for its capability to identify the location and shape of concrete damage accurately. Unlike basic deep learning approaches like classification and object detection, semantic segmentation not only recognizes damage but also delineates its boundaries, and has great potential in facilitating dimension measurement. However, multi‐level, high‐precision detection for various structural damage assessments remains an area requiring further research. This study created a database of reinforced concrete surfaces with pixel‐level, multi‐category semantic segmentation annotations for various levels of component damage, including cracks and spalling of concrete, exposure, buckling, fracture of reinforcing bars, etc. The performance of advanced deep learning segmentation algorithms, including U‐Net, DeepLab, K‐Net, and FastSCNN, was consequently trained and evaluated in detecting various types of concrete damage. All models show good accuracy of more than 98%, but lower F1 scores around 70%. U‐Net and K‐Net demonstrate relatively stable performance, indicating a certain degree of consistency and a high‐performance peak. In contrast, DeepLabv3's F1 score fluctuates significantly, suggesting the model may suffer from overfitting or other stability issues during training, resulting in a relatively low average performance. FastSCNN exhibits the highest potential, achieving the highest F1 score. In addition, this study also tested the performance of each model on new damage images and explored the impact of the dataset proportion ratio (training set vs. validation set), contributing to providing insights into each algorithm's suitability for various inspection scenarios. Finally, perspectives on current challenges and future directions in the field have also been given. [ABSTRACT FROM AUTHOR]

As the demand for renewable energy sources increases, the vulnerability of solar panels to lightning strikes becomes a critical concern. This research explores the correlation between lightning-induced voltage fluctuations and the resultant damage intensity on solar panels. The study adopts a systematic approach, first investigating the correlation between lightning-induced voltage assessment using 30kV, 60kV and 90 kV impulse voltage with multi-stage Marx impulse generator and the damage intensity on monocrystalline and polycrystalline solar panels. A portable active infrared thermography equipment with tCam-Mini was employed to conduct this research with wireless streaming. Furthermore, the study integrates Convolutional Neural Network (CNN)-based image classification techniques to enhance the efficiency of damage assessment. The results highlight the potential of neural networks in improving the accuracy and speed of image classification for damaged and undamaged samples. The findings contribute valuable insights into enhancing the resilience of solar panel systems against lightning strikes, ultimately advancing the reliability and sustainability of solar energy infrastructure. A new CNN model was developed to classify the images obtained from thermography with 90.21% accuracy for greyscale and 85.31% accuracy on thermal images. [ABSTRACT FROM AUTHOR]

A convolution neural network (CNN) is developed in this work to detect damage in pylons by measuring their vibratory response. More specifically, damage detection through testing relies on the development of damage-sensitive indicators, which are then used to reach a decision regarding the existence/absence of damage, provided they have been retrieved from at least two distinct structural states. Damage indicators, however, exhibit a relatively low sensitivity regarding the onset of structural damage, further exacerbated by the low amplitude response to a variety of environmentally induced loads. To this end, a mathematical model is developed to interpret the experimental data recovered from a fixed-base pylon with a top mass attachment to transverse motion. Damage is introduced in the mathematical model in the form of springs corresponding to the cracking of the beam's lower end. Families of numerically generated acceleration records are produced at select stations along the beam's height, which are then used for training a CNN. Once trained, it is used to identify damage from acceleration records produced from a series of experiments. Difficulties faced by CNN in correctly identifying the presence/absence of damage in the pylon are discussed, and steps taken to improve the quality of the results are proposed. [ABSTRACT FROM AUTHOR]

High electrical conductivity, along with high piezoresistive sensitivity and stretchability, are crucial for designing and developing nanocomposite strain sensors for damage sensing and on-line structural health monitoring of smart carbon fiber-reinforced polymer (CFRP) composites. In this study, the influence of the geometric features and loadings of carbon-based nanomaterials, including reduced graphene oxide (rGO) or carbon nanofibers (CNFs), on the tunable strain-sensing capabilities of epoxy-based nanocomposites was investigated. This work revealed distinct strain-sensing behavior and sensitivities (gauge factor, GF) depending on both factors. The highest GF values were attained with 0.13 wt.% of rGO at various strains. The stability and reproducibility of the most promising self-sensing nanocomposites were also evaluated through ten stretching/relaxing cycles, and a distinct behavior was observed. While the deformation of the conductive network formed by rGO proved to be predominantly elastic and reversible, nanocomposite sensors containing 0.714 wt.% of CNFs showed that new conductive pathways were established between neighboring CNFs. Based on the best results, formulations were selected for the manufacturing of pre-impregnated materials and related smart CFRP composites. Digital image correlation was synchronized with electrical resistance variation to study the strain-sensing capabilities of modified CFRP composites (at 90° orientation). Promising results were achieved through the incorporation of CNFs since they are able to form new conductive pathways and penetrate between micrometer-sized fibers. [ABSTRACT FROM AUTHOR]

Railway bridges are essential components of any transportation system and are typically subjected to several environmental and operational actions that can cause damage. Furthermore, they are not easily replaced, and their failure can have catastrophic consequences. Considering the expected lifespan of bridges, it is essential to guarantee their adequate serviceability and safety. In this scenario, emerges the Structural Health Monitoring (SHM), which allows the early identification of damage before it becomes critical. Damage identification is usually performed by the comparison between the damaged and undamaged responses obtained from monitoring data. Among the several features extracted from the responses, the time-series models exhibit a better performance, capability of early damage detection, and may also be applied within online damage detection strategies using unsupervised machine learning frameworks. In this paper, a review of advanced time-series methodologies for damage detection is presented. Initially, several time-series models often used in SHM are described, such as Autoregressive Models (AR), Recurrent Neural Networks (RNN), Gated Recurrent Unit (GRU), and Long Short-Term Memory (LSTM). Later, the framework where these models are usually applied is also detailed, including the latest upgrades and most relevant results. Finally, the conclusions summarize and elucidate the current perspectives and research gaps on the time-series models. [ABSTRACT FROM AUTHOR]

Aiming to support disaster recovery, we have developed a new method to extract damaged buildings by using machine learning that combines 10 explanatory variables obtained from analysis of aerial photographs and observation data. We used site amplification factors, seismic intensities of foreshock and mainshock, distance from faults, estimated building structures and ages, coverage by blue tarps, texture analysis, and digital surface model differences before and after the earthquake as explanatory variables, in addition to convolutional neural network prediction results based on post-earthquake aerial photographs. The random forest method resulted in an overall accuracy of about 81% and an average F-measure of three classes was about 70%, indicating that it can classify possible damage to buildings more accurately than our previous studies. [ABSTRACT FROM AUTHOR]

This paper presents a novel multi-initialization model for recognizing road surface damage, e.g. potholes and cracks, on video using convolutional neural networks (CNNs) in real-time for fast damage recognition. The model is trained by the latest Road Damage Detection dataset, which includes four types of road damage. In addition, the CNN model is updated using pseudo-labeled images from semi-learned methods to improve the performance of the pavement damage detection technique. This study describes the use of the YOLO architecture and optimizes it according to the selected parameters, demonstrating high efficiency and accuracy. The results obtained can enhance the safety and efficiency of road pavement and, hence, its traffic quality and contribute to decision-making for the maintenance and restoration of road infrastructure. [ABSTRACT FROM AUTHOR]

Copyright of Railway Construction Technology is the property of Railway Construction Technology Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Due to the increase in population, urbanisation, transportation development, and the aging of existing bridges, there is a growing need for new and rapid structural health monitoring (SHM) of bridges. To address this challenge, a method that stands out is the use of an interferometric radar system-based device, specifically Image by Interferometric Survey-Frequency for structures (IBIS-FS). Known for its portability and non-intrusive operation, IBIS-FS does not require direct contact with the bridge. This study utilised IBIS-FS to capture a pedestrian bridge's natural frequencies and mode shapes. The data obtained were found to be consistent with results from finite element models, demonstrating the reliability of IBIS-FS in capturing modal parameters. Building upon this foundation, the study then explores the application of advanced ensemble-based machine-learning techniques. By leveraging the data acquired from IBIS-FS, algorithms such as Random Forest, Gradient-boosted Decision Trees (GBDT), and Extreme Gradient Boosting (XGBoost) are used for bridge damage detection. These machine-learning (ML) techniques are suited to analyse the incomplete modal parameters of bridges, as captured by IBIS-FS. The study focuses on using these algorithms to interpret the changes in modal parameters, specifically identifying damage as a reduction in the stiffness of elements. This approach allows for a comprehensive analysis, where the modal parameters, including mode shapes and natural frequencies altered by varying noise levels, are fed as input to the models. It was observed that all three ML methods, with Random Forest in particular, can effectively identify the location and severity of damage, demonstrating an efficient training process. The robustness of GBDT and XGBoost in handling complex data sets also shows great promise for their application in bridge damage detection. Collectively, these results underscore the potential of combining advanced ML techniques like Random Forest, GBDT, and XGBoost with the data acquired from IBIS-FS. [ABSTRACT FROM AUTHOR]

Early identification of damages in tubular structures is crucial for their long-term safety and functionality, as they are essential in various modern life applications. Experimental and numerical modal data may slightly differ due to unknown structural characteristics and uncertainties, which are typically addressed using finite element (FE) model updating procedures. Instead of using the Euler-Bernoulli beam element, this paper utilises the semi-rigidly connected frame element (S-RCFE). By incorporating extra design parameters, such as the end fixity factor of all connections, the S-RCFE offers a unique opportunity to establish a strong agreement between experimental and numerical models through an optimisation-based FE model updating procedure. A well-calibrated FE model represents the actual behaviour of the structure and leads to achieving accurate results in the damage detection step. This paper employs the improved grey wolf optimiser (IGWO) and weIghted meaN oF vectOrs (INFO) to minimise 11 objective functions with adjustable coefficients. The statistical investigations reveal that the IGWO effectively minimised five out of six objective functions, which were defined based on the modified total modal assurance criterion (MTMAC). The rest of the objective functions based on the modal assurance criterion (MAC), natural frequency vector assurance criterion (NFVAC), differences in natural frequencies, and a combination of the MAC and NFVAC could not obtain accurate outcomes for the model updating problem. The statistical comparison indicates that the INFO algorithm is unreliable for the FE model updating despite achieving at least one successful result in ten independent runs. The INFO algorithm and the IGWO algorithm demonstrate comparable performance in damage detection. The analysis also shows that the coefficients of MTMAC, alpha and beta, should be adjusted to 0.65 and 1, respectively, to achieve the most accurate damage detection result. [ABSTRACT FROM AUTHOR]

For many years, structural health monitoring (SHM) has held significant importance across diverse engineering sectors. The main aim of SHM is to assess the health status and understand distinct features of structures by analyzing real-time data from physical measurements. The dynamic response (DR) is a significant tool in SHM studies. This response is used primarily to detect variations or damage by examining the vibration signals of DR. Numerous scholarly articles and reviews have discussed the phenomenon and importance of using DR to predict damages in uniform thickness (UT) plate structures. However, previous reviews have predominantly focused on the UT plates, neglecting the equally important varying thickness (VT) plate structures. Given the significance of VT plates, especially for academic researchers, it is essential to compile a comprehensive review that covers the vibration of both the UT and VT cracked plate structures and their identification methods, with a special emphasis on VT plates. VT plates are particularly significant due to their application in critical components of various applications where optimizing the weight, aerodynamics, and dimensions is crucial to meet specific design specifications. Furthermore, this review critically evaluates the damage identification methods, focusing on their accuracy and applicability in real-world applications. This review revealed that current research studies are inadequate in describing crack path identification; they have primarily focused on predicting the quantification of cracks in terms of size or possible location. Identifying the crack path is crucial to avoid catastrophic failures, especially in scenarios where the crack may propagate in critical dimensions of the plate. Therefore, it can be concluded that an accurate analytical and empirical study of crack path and damage identification in these plates would be a novel and significant contribution to the academic field. [ABSTRACT FROM AUTHOR]

Highlights Artificial intelligence (AI) techniques are increasingly used for structural health monitoring (SHM) of polymer composite structures. However, to be confident in the trustworthiness of AI models, the models must be reliable, interpretable, and explainable. The use of explainable artificial intelligence (XAI) is critical to ensure that the AI model is transparent in the decision‐making process and that the predictions it provides can be trusted and understood by users. However, existing SHM methods for polymer composite structures lack explainability and transparency, and therefore reliable damage detection. Therefore, an interpretable deep learning model based on an explainable vision transformer (X‐ViT) is proposed for the SHM of composites, leading to improved repair planning, maintenance, and performance. The proposed approach has been validated on carbon fiber reinforced polymers (CFRP) composites with multiple health states. The X‐ViT model exhibited better damage detection performance compared to existing popular methods. Moreover, the X‐ViT approach effectively highlighted the area of interest related to the prediction of each health condition in composites through the patch attention aggregation process, emphasizing their influence on the decision‐making process. Consequently, integrating the ViT‐based explainable deep‐learning model into the SHM of polymer composites provided improved diagnostics along with increased transparency and reliability. Autonomous damage detection of polymer composites using vision transformer based deep learning model. Explainable artificial intelligence by highlighting region of interest using patch attention. Comparison with the existing state of the art structural health monitoring methods. [ABSTRACT FROM AUTHOR]

Throughout history, the implementation of structural health monitoring systems has played a crucial role in evaluating the responses of dams to environmental and human-induced threats. By continuously monitoring structural integrity and analyzing dynamic characteristics, these systems offer a robust alternative to traditional visual inspection methods, ensuring the long-term safety of dams. This paper delves into the intricate process of operational modal analysis applied to dams, encompassing data collection, preprocessing, and the utilization of diverse modal identification techniques across both time and frequency domains. Moreover, it explores innovative approaches aimed at overcoming challenges encountered in previous methodologies. Also, the evolution of automated modal identification techniques and their application in dams are investigated. It explores the advancements in this field and their implications for enhancing the efficiency and accuracy of modal analysis processes. Furthermore, this paper evaluates the effectiveness of damage detection methods in dams based on operational modal identification. [ABSTRACT FROM AUTHOR]

Over the past decade, distributed acoustic sensing has been utilized for structural health monitoring in various applications, owing to its continuous measurement capability in both time and space and its ability to deliver extensive data on the conditions of large structures using just a single optical cable. This work aims to evaluate the performance of distributed acoustic sensing for monitoring a multilayer structure on a laboratory scale. The proposed structure comprises four layers: a medium-density fiberboard and three rigid polyurethane foam slabs. Three different damages were emulated in the structure: two in the first layer of rigid polyurethane foam and another in the medium-density fiberboard layer. The results include the detection of the mechanical wave, comparing the response with point sensors used for reference, and evaluating how the measured signal behaves in time and frequency in the face of different damages in the multilayer structure. The tests demonstrate that evaluating signals in both time and frequency domains presents different characteristics for each condition analyzed. The supervised support vector machine classifier was used to automate the classification of these damages, achieving an accuracy of 93%. The combination of distributed acoustic sensing with this learning algorithm creates the condition for developing a smart tool for monitoring multilayer structures. [ABSTRACT FROM AUTHOR]

In this study, an artificial intelligence framework is developed to facilitate the use of robotics for autonomous damage inspection. While considerable progress has been achieved by utilizing state-of-the-art computer vision approaches for damage detection, these approaches are still far away from being used for autonomous robotic inspection systems due to the uncertainties in data collection and data interpretation. To address this gap, this study proposes a framework that will enable robots to select the best course of action for active damage perception and reduction of uncertainties. By doing so, the required information is collected efficiently for a better understanding of damage severity which leads to reliable decision-making. More specifically, the active damage perception task is formulated as a Partially Observable Markov Decision Process, and a deep reinforcement learning-based active perception agent is proposed to learn the near-optimal policy for this task. The proposed framework is evaluated for the autonomous assessment of cracks on metallic surfaces of an underwater nuclear reactor. Active perception exhibits a notable enhancement in the crack Intersection over Union (IoU) performance, yielding an increase of up to 69% when compared to its raster scanning counterpart given a similar inspection time. Additionally, the proposed method can perform a rapid inspection that reduces the overall inspection time by more than two times while achieving a 15% higher crack IoU than that of the dense raster scanning approach. [ABSTRACT FROM AUTHOR]

Copyright of Experimental Technology & Management is the property of Experimental Technology & Management Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Applying unmanned aerial vehicles (UAVs) and vision-based analysis methods to detect bridge surface damage significantly improves inspection efficiency, but the existing techniques have difficulty in accurately locating damage, making it difficult to use the results to assess a bridge's degree of deterioration. Therefore, this study proposes a method to generate panoramic bridge surface images using multi-view images captured by UAVs, in order to automatically identify and locate damage. The main contributions are as follows: (1) We propose a UAV-based image-capturing method for various bridge sections to collect close-range, multi-angle, and overlapping images of the surface; (2) we propose a 3D reconstruction method based on multi-view images to reconstruct a textured bridge model, through which an ultra-high resolution panoramic unfolded image of the bridge surface can be obtained by projecting from multiple angles; (3) we applied the Swin Transformer to optimize the YOLOv8 network and improve the detection accuracy of small-scale damages based on the established bridge damage dataset and employed sliding window segmentation to detect damage in the ultra-high resolution panoramic image. The proposed method was applied to detect surface damage on a three-span concrete bridge. The results indicate that this method automatically generates panoramic images of the bridge bottom, deck, and sides with hundreds of millions of pixels and recognizes damage in the panoramas. In addition, the damage detection accuracy reached 98.7%, which is improved by 13.6% when compared with the original network. [ABSTRACT FROM AUTHOR]

The quality inspection of each precast utility tunnel segment is crucial, especially the cross-sectional dimensions and surface smoothness, since they influence the assembly precision at the construction site. Traditional manual inspection methods are not only time-consuming and costly but also limited in accuracy. In order to achieve a high-precision and high-efficiency geometric quality inspection for multi-type precast utility tunnel segments, this paper proposes an automated inspection method based on the Building Information Model (BIM) and Light Detection and Ranging (LiDAR). Initially, the point cloud data (PCD) of the precast utility tunnel segment are acquired through LiDAR and preprocessed to obtain independent point clouds of the precast utility tunnel segment. Then, the shape of the precast utility tunnel segment is identified using the proposed Cross-Sectional Geometric Ratio Feature Identification (CSGRFI) algorithm. Subsequently, the geometric features of the components are extracted based on preset conditions, and the geometric dimensions are calculated. Finally, the quality inspection results are obtained by comparing with the design information provided by the BIM. The proposed method was validated in a real precast component factory. The results indicate that the method achieved a 100% success rate in identifying the cross-sectional shapes of the segments. Compared with the manual measurement method, the proposed method demonstrated a higher accuracy in the geometric quality assessment and an improved time efficiency by 44%. The proposed method enables the efficient geometric quality inspection of tunnel segments, effectively addressing the construction industry's need for large-scale, high-quality tunnel projects. [ABSTRACT FROM AUTHOR]

This article introduces an innovative approach to assess the structural health of bridges based on dynamic and static load test data from the Xuan Duc bridge, a bridge constructed using Ultra-High-Performance Concrete (UHPC) in Tuyen Quang Province, Vietnam. The measured deflection values of all girders and the natural frequency of the superstructure, along with the PSO (Particle Swarm Optimization) algorithm, were employed to update a finite element model developed in SAP2000 (a commercial structural analysis and design software). This updating process resulted in a significant reduction in error from 5.81% to 0.22% for deflection values and from 2.48% to 0.02% for natural frequencies when compared with the measured data. It is shown that the updated numerical model accurately reflects the operational condition of the bridge during load testing, facilitating the determination of the elastic modulus values of UHPC material. Additionally, this paper explores the feasibility of the approach in identifying the location and degree of damage in superstructures by conducting two numerical case studies with high accuracy. Furthermore, the effect of noise in load testing on the updating process was also considered. With a maximum noise level of 3%, the method maintains accuracy in locating damaged zones, yielding damage level values of 24.70% and 36.47% compared to respective 20% and 30% without noise. Results from this paper confirm the effectiveness of applying machine learning in advanced structural health monitoring. [ABSTRACT FROM AUTHOR]

This study addresses the challenges of data scarcity and class imbalance in structural health monitoring (SHM) of composite structures. Data-driven SHM techniques that benefit from non-destructive evaluation (NDE) are used in various composite structures. However, the lack of damaged state data causes data scarcity and class imbalance problems that prevent robust diagnostics of composite structures. This study introduces a novel data-driven multi-class data augmentation method for composite structures, employing a multi-class generative adversarial network (MC-GAN) for the first time to generate synthetic data for multiple classes without the need for excessive experimentation or simulation. Additionally, the MC-GAN model is integrated with the convolutional neural network (CNN) to develop the MC-GAN-CNN model for autonomous data augmentation and delamination detection. The approach has been validated using experimentally obtained vibrational data for laminated composites. The damage detection using manual feature extraction showed overfitting and very high standard deviation during 10-fold cross-validation for various machine learning models. However, the proposed method suggested a more rigorous assessment with a mean accuracy of 99.72 ± 0.08 %. In addition, the proposed framework assists in handling the delamination detection problem autonomously without requiring hand-crafted statistical features with a good generalization capability.

Abstract This paper introduces an approach for vibration-based damage detection based on matrix updating aided by the Whale Optimization Algorithm (WOA). The methodology uses the Data-driven Stochastic Subspace Identification (SSI-DATA) technique to determine the modal parameters, which are compared with those obtained from both healthy and damaged conditions of the structure. The methodology’s efficacy is assessed through three distinct steps: numerical simulations, experimental data, and real-world data from a bridge. Initially, numerical analyses are conducted on a cantilever beam, a 10-bar truss, and a Warren truss subjected to environmental vibrations with varying damage cases and noise levels. Subsequently, experimental validations are performed on a test system and in the Z24 Bridge. Results from the computational simulations demonstrate the method’s promise to identify, locate, and quantify single and multiple damage cases, even amidst signal noise, variations in the first vibration mode as minimal as 0.015%, and complex structures with 54 elements. Moreover, the matrix updating method utilizing WOA showcased superior accuracy compared to existing techniques in the literature. In addition, the Z24 Bridge example validated the capability of the presented damage detection method to localize structural damage solely based on natural frequencies.

Data synergy involves acquiring and combining data from different sensors to achieve better problem analysis and research results. For more comprehensive data analysis, the sensors are not only mounted on one platform. Still, they should also be compatible with software and hardware, e.g. for the same timestamp registration by different sensors. The aim of this article is to propose the synergy between various remote sensing sensors including the ground penetrating radar (GPR), LiDAR (Light Detection and Ranging) sensor and three photogrammetric RGB cameras for damage detection in a pavement in a park alley. The data were acquired with a low-cost platform, in the Pole Mokotowskie Park in Warsaw, Poland. Three drives were made along the same path with the platform, so it was possible to assess the repeatability of the data. Based on the GPR data, orthophotomap, and digital terrain model (DTM) from images, an analysis of the cracks in the pavement was done. The paper proves additive value from the synergy of data collected for the alley also in the form of a common visualization of acquired data. Results presented in the article showed that using mobile mapping platform and technologies describing the situation above and below the ground level enable a more detailed analysis and inspection of the damages in the park alley.

Civil structures are always considered one of the most valuable properties of each country. Many factors can lead to local damages in different parts of structures during their operational life. These damages are reflected in the vibration responses of structures. This research aims to detect the existence and determine the location of damage in a truss bridge under a moving load using an artificial neural network and experimental wavelet transform. For this purpose, a two-dimensional truss bridge was built in the laboratory to investigate this research's objectives. Earlier experimental studies in damage detection were subjected to excitations such as impact loads and electrodynamic shakers. Since the appearance of damage effects in the vibration responses of the structure mainly depends on the applied location of the impact load, a moving load that crosses the entire length of the bridge can be used as input excitation to detect the presence and location of damages for which there is no available data. After measuring the vibration responses of the bridge, 17 time-domain features were extracted from the raw signals, which were used to detect the presence of damage. Although feature extraction is applied to raw signals, the signal processing stage was not eliminated for damage localization. By processing the response signals of the healthy and damaged state of the bridge using experimental wavelet transform, these signals were decomposed into different modes and 5 non-parametric damage-sensitive features such as Shannon and Tsallis entropies, Root Mean Square (RMS), Shape Factor and kurtosis which are all based on statistical parameters in addition to energy, were extracted. Finally, these damage-sensitive features were presented as input to the neural network whereas the state of the bridge (healthy or damaged) was considered as its target. The obtained results showed that the proposed method can effectively detect the presence and the location of the damage in the truss bridge.

Improvement in mechanical properties of fibre-reinforced polymer composites through proper matrix modification has emerged as the significant trend in recent advanced technology. Dispersion of nanofillers in the matrix results in ultra-light weight, high strength, impact resistant and durable structures. In the current investigation, effect of the addition of varying percentages (0, 1, 3, 5 and 7 wt.%) of low-cost nanoclay to the unsymmetrical carbon/glass (C2G8) hybrid composites on mechanical, tribological and low-velocity impact (LVI) behaviour were investigated. Using traditional hand lay-up techniques, nanocomposite specimens were prepared. The results revealed that C2G8 hybrid composite with 5 wt.% loading of nanoclay possessed maximum hardness (35 HV), flexural strength (494 MPa), impact strength (Izod (119.022 kJ m−2), Charpy (563.922 kJ m−2)) and minimum specific wear rate (19.6 × 10−3 mm3 Nm−1) in comparison with other hybrid combinations. LVI test also revealed enhanced energy absorption (112.46 J) for hybrid nanocomposite against plain C2G8 hybrid composite. Furthermore, the damage depth and areas were observed by visual inspection and scanning electron microscope to account for best possible structure–property relationship. Developed hybrid nanocomposite may be considered as a suitable material for various automotive applications. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Shanghai Jiaotong University (Science) is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The primary goal of structural health monitoring is to detect damage at its onset before it reaches a critical level. In the present work an in-depth investigation addresses deep learning applied to data-driven damage detection in nonlinear dynamic systems. In particular, autoencoders and generative adversarial networks are implemented leveraging on 1D convolutional neural networks. The onset of damage is detected in the investigated nonlinear dynamic systems by exciting random vibrations of varying intensity, without prior knowledge of the system or the excitation and in unsupervised manner. The comprehensive numerical study is conducted on dynamic systems exhibiting different types of nonlinear behavior. An experimental application related to a magneto-elastic nonlinear system is also presented to corroborate the conclusions. [ABSTRACT FROM AUTHOR]

In recent years, Double Window Principal Component Analysis (DWPCA) has been proposed. The spatial windows exclude damage-insensitive data from the analysis, while the temporal window improves the discrimination between healthy and damaged states. As a result, the DWPCA method exhibits higher sensitivity and resolution in damage identification compared to traditional PCA methods, as well as other traditional signal processing methods such as wavelet analysis. However, existing research on DWPCA has mainly focused on using the first-order eigenvector for damage identification, while the potential of higher order DWPCA eigenvectors remains unexplored. Therefore, the objective of this paper is to investigate the damage identification capabilities of higher-order DWPCA eigenvectors. Furthermore, we propose three types of damage-sensitive features based on DWPCA eigenvectors and use them as inputs to artificial intelligence (AI) algorithms for damage localization and quantification. The AI algorithms considered include AutoGluon and Transformer, which are powerful machine learning (ML) and deep learning (DL) algorithms proposed in recent years, respectively. In addition, classical ML algorithms such as Decision Tree (DT), Random Forest (RF) and Extreme Gradient Boost (XGBoost) are considered for comparison. Extensive benchmark experiments are performed and the numerical results obtained show that the combination of AutoGluon with DWPCA features achieves remarkable performance in terms of damage localization and quantification. This performance exceeds that of DT, RF, XGBoost and Transformer algorithms. Specifically, the prediction accuracies for damage localization and quantification exceed 90%. These results highlight the great potential of integrating AutoGluon with DWPCA features, particularly by combining AutoGluon with the first and second DWPCA eigenvectors, for real-world applications in structural health monitoring.

Abstract A method based on Gabor spectral mode transmissibility functions (GSMTFs) is proposed to detect local damage in a cantilevered structure under nonstationary ambient excitations. Gabor transformation and singular value decomposition are used to reduce the influences of other vibration modes on Gabor spectral mode transmissibility functions and process nonstationary structural responses, respectively. A new state characteristic based on the fundamental structure frequency is formulated on the basis of the GSMTFs, eventually leading to the development of a new damage indicator. The probability density functions of the damage indicator for healthy and damaged states can be estimated from the measured data, and the receiver operating characteristic (ROC) curve derived from these probability distributions and the corresponding area under the ROC curve (AUC) are used to determine the damage location. A six-degree-of-freedom system and a typical transmission tower are numerically studied, and the results show that the proposed method can estimate the structural damage location under nonstationary random loads. The proposed method is further validated with a planar frame in the laboratory, which exhibits multiple damage elements via random force hammer excitations. The results show that the AUC values computed for certain parts of the structure containing the damaged elements are greater than those for other parts of the structure, indicating the effectiveness of the proposed method. Moreover, the proposed method is compared with the dot product difference (DPD) index, and the results from the laboratory planar frame demonstrate that the proposed method can better identify damage.

In the past five years, the implementation of machine learning (ML) techniques has surged in civil engineering applications, particularly for optimizing and predicting solutions to various challenges. More robust prediction models may be produced by combining test data collected in the laboratory or field with ML. These models may be used to estimate the compressive strength of masonry or repair mortars, probable damage scenarios in buildings, concrete models, beams, and columns for determining the mechanical characteristics of materials, damage detection in civil structures, and so on. This comprehensive review aims to clarify the array of ML-based methods employed in civil engineering, specifically focusing on their efficacy in strengthening energy efficiency and cost-effectiveness. In combination with ML, the review explores corresponding soft computing methodologies such as fuzzy logic (FL) and design of experiments (DOE). A variety of case examples that highlight the versatility of these approaches, particularly in applications linked to structural reinforcement, enhance the story. The review navigates difficulties associated with the integration of soft computing in civil engineering and expands its scope to include emerging research directions. This synthesis of advanced artificial intelligence (AI) serves as a guide, providing new researchers with knowledge about a developing field. These methods could revolutionize the current situation by providing creative answers to complex problems that arise in civil structural applications.

Recent advancements in digital technologies and automated analysis techniques applied to Historic Built Environment (HBE) demonstrate significant advantages in efficiently collecting and interpreting data for building conservation activities. Integrating digital image processing through Artificial Intelligence approaches further streamlines data analysis for diagnostic assessments. In this context, this paper presents a scoping review based on Scopus and Web of Science databases, following the PRISMA protocol, focusing on applying Deep Learning (DL) architectures for image-based classification of decay phenomena in the HBE, aiming to explore potential implementations in decision support system. From the literature screening process, 29 selected articles were analyzed according to methods for identifying buildings' surface deterioration, cracks, and post-disaster damage at a district scale, with a particular focus on the innovative DL architectures developed, the accuracy of results obtained, and the classification methods adopted to understand limitations and strengths. The results highlight current research trends and the potential of DL approaches for diagnostic purposes in the built heritage conservation field, evaluating methods and tools for data acquisition and real-time monitoring, and emphasizing the advantages of implementing the adopted techniques in interoperable environments for information sharing among stakeholders. Future challenges involve implementing DL models in mobile apps, using sensors and IoT systems for on-site defect detection and long-term monitoring, integrating multimodal data from non-destructive inspection techniques, and establishing direct connections between data, intervention strategies, timing, and costs, thereby improving heritage diagnosis and management practices. [ABSTRACT FROM AUTHOR]

The wind energy sector is experiencing rapid growth, marked by the expansion of wind farms and the development of large-scale turbines. However, conventional manual methods for wind turbine operations and maintenance are struggling to keep pace with this development, encountering challenges related to quality, efficiency, and safety. In response, unmanned aerial vehicles (UAVs) have emerged as a promising technology offering capabilities to effectively and economically perform these tasks. This paper provides a review of state-of-the-art research and applications of UAVs in wind turbine blade damage detection, operations, and maintenance. It encompasses various topics, such as optical and thermal UAV image-based inspections, integration with robots or embedded systems for damage detection, and the design of autonomous UAV flight planning. By synthesizing existing knowledge and identifying key areas for future research, this review aims to contribute insights for advancing the digitalization and intelligence of wind energy operations. [ABSTRACT FROM AUTHOR]

Damage detection in structurally reinforced concrete elements is a vital topic for structural health monitoring and for assessing the capacity of reinforced concrete members. In this regard, many destructive tests exist that allow technical experts to evaluate the damage to a structural member. Such techniques are often employed for damage assessment after a natural disaster or a man-made event to assess the structural integrity and prioritize the locations that require urgent repair work. The researcher was successful in developing a testing methodology using nondestructive testing to identify internal damage in reinforced concrete elements by linking the delay in ultrasonic wave propagation to the initiation, development, and progression of cracks in the concrete surrounding the steel reinforcement. It was observed during experimentation that using the proposed methodology of gradual loading and comparing the speed of travel of the ultrasonic pulse velocity to the undamaged elements, the researcher was successful in identifying and localizing the internal cracked portions in the structural concrete member. Twelve reinforced concrete elements with full-size tension, compression, and shear reinforcements were tested to validate the proposed nondestructive test methodology. Direct and indirect methods of investigation were employed for testing purposes. From the performed experiments on reinforced concrete members, it was concluded that the proposed nondestructive testing methodology can be successfully applied in structural capacity assessment. The data collected from on-site investigations can be used for minimizing repair and strengthening work. In-addition an in-depth sensitivity analysis was conducted using the Latin hypercube sampling method to understand the influence of each variable on the ultrasonic pulse velocity test results. A purely random combination of parameters was adopted for the sensitivity analysis. Through the analysis, it was concluded that concrete strength played the most influential role in the ultrasonic pulse velocity testing followed by concrete cover, bar diameter and wave path length. [ABSTRACT FROM AUTHOR]

Granite is a common engineering material that exhibits complex mechanical properties under external loads. This study conducted experimental research and analysis in conjunction with the active monitoring technology of piezoelectric ceramics. A quantitative analysis method for the mechanical properties of rock materials based on piezoelectric health monitoring was established, and for the first time, the piezoelectric monitoring results of rock were mapped and compared with the uniaxial compression performance indicators of rock. In this study, two sets of cyclic impact experiments were conducted on granite samples using a drop hammer. The piezoelectric signals of the granite samples were detected using piezoelectric ceramic active sensing technology. A piezoelectric ceramic damage monitoring method was proposed, and the damage factor of the granite samples was calculated using the wavelet packet energy method. Subsequently, uniaxial compression experiments were performed on the damaged granite samples to obtain mechanical performance data. Finally, a mathematical relationship model was established between the piezoelectric signal and the uniaxial compressive strength of the rocks. It was found that the damage factor of the piezoelectric monitoring signal of the damaged rock were linearly related to the uniaxial compressive strength of the damaged rock. [ABSTRACT FROM AUTHOR]

Bridge authorities have been reticent to integrate structural health monitoring into their bridge management systems, as they do not have the financial and technical resources to collect long-term monitoring data from every bridge. As bridge authorities normally own huge amount of similar bridges, like the pedestrian ones, the ability to transfer knowledge from one or a small group of well-known bridges to help make more effective decisions in new bridges and environments has gained relevance. In that sense, transfer learning, a subfield of machine learning, offers a novel solution to periodically evaluate the structural condition of all pedestrian bridges using long-term monitoring data from one or more pedestrian bridges. In this paper, the applicability of unsupervised transfer learning is firstly shown on data from numerical models and then on data from two similar pedestrian prestressed concrete bridges. Two domain adaptation techniques are used for transfer learning, where a classifier has access to unlabeled training data (source domain) from a reference bridge (or a small set of reference bridges) and unlabeled monitoring test data (target domain) from another bridge, assuming that both domains are from similar but statistically different distributions. This type of mapping is expected to improve the classification accuracy for the target domain compared to a procedure that does not implement domain adaptation, as a result of reducing distributions mismatch between source and target domains. [ABSTRACT FROM AUTHOR]