Search

Copyright of Shipin Kexue/ Food Science is the property of Food Science Editorial Department 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.)

Earthquakes such as Kobe, Chi-Chi, Wenchuan, and many more damaged the rock tunnels to various extents. To understand the vulnerability of rock tunnels caused by earthquakes, the damage degree and damage classification are major components. The damage degree and descriptions in the post-seismic damage classifications of rock tunnels are modified by researchers for every seismic event based on the amount of damage. This implies that existing post-seismic damage classifications are not uniform or consistent. The existing classifications are based on data from one or a maximum of three seismic events and also are site-specific, and lack a generalized view of the problem. To overcome such limitations, this study proposes a new post-seismic damage classification of rock tunnels. This classification is obtained from the largest global seismic damage database which contains information on 285 rock tunnels damaged by 26 earthquakes. This study introduces seven tunnel damage classes for different damage degrees namely None, Very Slight, Slight, Moderate, Severe, Extremely Severe, and Collapse with their detailed damage descriptions. Further, the influence of seismic, geological, and structural parameters are summarized from the database. The efficacy of this classification and conclusions from the influence parameters are validated by applying it to the five-rock tunnels damaged by Luding (2022), and Menyuan (2022) earthquakes in China and Kahramanmaraş earthquake sequences (2023) in Türkiye. The proposed classification shows a good agreement with the damage degree and its description for these five rock tunnels. Thus, the proposed damage classification and outcomes of influence parameters using such a large database can be utilized to understand the damage levels caused in the tunnel after an earthquake and for performing post-seismic damage assessment of rock tunnels. [ABSTRACT FROM AUTHOR]

The Probabilistic Multistage (PM) algorithm was developed by authors for identifying and localizing damages in isotropic plates. More specifically, PM algorithm consists of a fully automated probabilistic damage imaging methodology based on ultrasonic guided wave propagation and a 5-sensor array working in a pitch-catch approach. The algorithm processes the gathered data in three steps to identify key features associated with damage. The aim of this work is to assess the effectiveness of the PM algorithm on more complex structures. Specifically, the study investigates three cases of study, made of Carbon Fiber Reinforced Plastic (CFRP) composite, characterized by different geometries and layups. The algorithm is initially tested on panels with artificial damage in the form of a Teflon disk located in a specific location between the middle laminae of the panels, which is used to replicate the effect of delamination. In order to expand the experimental dataset without incurring additional costs or waste, new damage conditions are simulated by adding masses on the upper surface of the panels. Each plate is investigated considering three different damage sizes and 16 different damage locations. The proposed algorithm successfully detects damages both within and outside the sensor network. The PM algorithm produces a clear damage positioning map and a positioning (probabilistic field) range for the identified damage. This information can be used to assist operators in conducting inspections more efficiently by focusing on the highlighted areas, which may potentially lead to reduced maintenance and repair expenses. [ABSTRACT FROM AUTHOR]

After an earthquake, rapid assessment of building damage is crucial for emergency response, reconstruction planning, and public safety. This study evaluates the performance of various Generative Artificial Intelligence (GAI) models in analyzing post-earthquake images to classify structural damage according to the EMS-98 scale, ranging from minor damage to total destruction. Correct classification rates for masonry buildings varied from 28.6% to 64.3%, with mean damage grade errors between 0.50 and 0.79, while for reinforced concrete buildings, rates ranged from 37.5% to 75.0%, with errors between 0.50 and 0.88. Fine-tuning these models could substantially improve accuracy. The practical implications are significant: integrating accurate GAI models into disaster response protocols can drastically reduce the time and resources required for damage assessment compared to traditional methods. This acceleration enables emergency services to make faster, data-driven decisions, optimize resource allocation, and potentially save lives. Furthermore, the widespread adoption of GAI models can enhance resilience planning by providing valuable data for future infrastructure improvements. The results of this work demonstrate the promise of GAI models for rapid, automated, and precise damage evaluation, underscoring their potential as invaluable tools for engineers, policymakers, and emergency responders in post-earthquake scenarios. [ABSTRACT FROM AUTHOR]

This study investigated the combined application of visible/near-infrared (Vis-NIR) spectroscopy with linear discriminant analysis (LDA) and machine learning (ML) for the classification of apples with different degrees of damage. The Vis-NIR spectral data of apples with different degrees of damage were collected, and the effect of different spectral preprocessing methods on the support vector machine (SVM) classification model was analyzed. LDA was used to reduce the dimensionality of the preprocessed spectral data, and five machine learning models including SVM, random forest (RF), K-nearest neighbor (KNN), decision tree (DT) and extreme gradient boosting (XGBoost) were constructed and compared for the classification of apple damage. The results showed that the SVM model based on preprocessed spectra with Savitzky-Golay (SG) smoothing had the best classification performance, with an accuracy of 87.3%. After dimensionality reduction using LDA, the classification accuracy of all the models was significantly improved, with the highest increase of 16% being observed in the DT model. The KNN model showed the best classification performance, with an accuracy of 96.0% and a precision of 96.4%. This study provides a basis for efficient and accurate assessment of the degree of mechanical damage in apples.

This study presents the structural damage classification of a large-scale bridge, considering several damage scenarios using One dimensional convolutional neural network (1D-CNN). Measurements obtained from the Z24 bridge in Switzerland during the short-term progressive damage tests are used for this study. Acceleration responses at 291 sensor locations are measured under forced and ambient excitations. This study considers only the measurements under ambient excitations, which has the advantage over forced excitation of not required to measure the excitations. Furthermore, to reduce the overall cost of monitoring the structure, this study aims to use fewer sensor measurements. Out of 291 sensors, only three measurements are used in this study. Each measurement contains 65,536 samples collected at a sampling frequency of 100 Hz. The measurements from three sensors are processed into shorter lengths of 150 data points, each with a 50% overlap. The processed data are inputted to the proposed 1D-CNN model. The proposed 1D-CNN consists of two 1D-CNN networks with different kernel sizes to perform better with different abstract features. The flattened outputs from these two networks using the same input are concatenated and fed into a fully connected dense network for damage classification. The labelled outputs are the different damage scenarios introduced in the progressive damage tests. The performance of the proposed approach is measured in terms of accuracy supported by a confusion matrix. The performance is measured for three cases. The result indicates that better performance is obtained compared to a previous study with the fused features as input to the deep learning models, although fewer sensors are used. Practical Applications: The findings from this study demonstrated that a good damage classification could be achieved using fewer sensor measurements from a large-scale bridge. The Z24 bridge benchmark data are used as an example in this study. Several damage scenarios were considered during the progressive damage test, and all tests were performed under ambient and forced excitation conditions. A multi-headed, one-dimensional convolutional neural network is proposed to classify the damages using the ambient condition data set. The performance is compared with an existing study using the same data set, but the data pre-processing techniques and model are improved. Three cases are defined by varying the size and length of the available time-series data. The proposed model has obtained better damage classification results for all the cases than an existing study. The advantage of the study is that the damage classification is performed using data obtained from a real large-scale structure under ambient conditions, eliminating the need for external force excitation. The proposed method could also be used for condition monitoring and safety evaluation of aerospace and mechanical structures. [ABSTRACT FROM AUTHOR]

The South-to-North Water Diversion Project in China is an extensive inter-basin water transfer project, for which ensuring the safe operation and maintenance of infrastructure poses a fundamental challenge. In this context, structural health monitoring is crucial for the safe and efficient operation of hydraulic infrastructure. Currently, most health monitoring systems for hydraulic infrastructure rely on commercial software or algorithms that only run on desktop computers. This study developed for the first time a lightweight convolutional neural network (CNN) model specifically for early detection of structural damage in water supply canals and deployed it as a tiny machine learning (TinyML) application on a low-power microcontroller unit (MCU). The model uses damage images of the supply canals that we collected as input and the damage types as output. With data augmentation techniques to enhance the training dataset, the deployed model is only 7.57 KB in size and demonstrates an accuracy of 94.17 ± 1.67% and a precision of 94.47 ± 1.46%, outperforming other commonly used CNN models in terms of performance and energy efficiency. Moreover, each inference consumes only 5610.18 μ J of energy, allowing a standard 225 mAh button cell to run continuously for nearly 11 years and perform approximately 4,945,055 inferences. This research not only confirms the feasibility of deploying real-time supply canal surface condition monitoring on low-power, resource-constrained devices but also provides practical technical solutions for improving infrastructure security. [ABSTRACT FROM AUTHOR]

Damage to parcels reduces customer satisfaction with delivery services and increases return-logistics costs. This can be prevented by detecting and addressing the damage before the parcels reach the customer. Consequently, various studies have been conducted on deep learning techniques related to the detection of parcel damage. This study proposes a deep learning-based damage detection method for various types of parcels. The method is intended to be part of a parcel information-recognition system that identifies the volume and shipping information of parcels, and determines whether they are damaged; this method is intended for use in the actual parcel-transportation process. For this purpose, 1) the study acquired image data in an environment simulating the actual parcel-transportation process, and 2) the training dataset was expanded based on StyleGAN3 with adaptive discriminator augmentation. Additionally, 3) a preliminary distinction was made between the appearance of parcels and their damage status to enhance the performance of the parcel damage detection model and analyze the causes of parcel damage. Finally, using the dataset constructed based on the proposed method, a damage type detection model was trained, and its mean average precision was confirmed. This model can improve customer satisfaction and reduce return costs for parcel delivery companies. [ABSTRACT FROM AUTHOR]

The increase in both the frequency and magnitude of natural disasters, coupled with recent advancements in artificial intelligence, has introduced prospects for investigating the potential of new technologies to facilitate disaster response processes. Preliminary Damage Assessment (PDA), a labor-intensive procedure necessitating manual examination of residential structures to ascertain post-disaster damage severity, stands to significantly benefit from the integration of computer vision-based classification algorithms, promising efficiency gains and heightened accuracy. Our paper proposes a Vision Transformer (ViT)-based model for classifying damage severity, achieving an accuracy rate of 95%. Notably, our model, trained on a repository of over 18,000 ground-level images of homes with damage severity annotated by damage assessment professionals during the 2020–2022 California wildfires, represents a novel application of ViT technology within this domain. Furthermore, we have open sourced this dataset—the first of its kind and scale—to be used by the research community. Additionally, we have developed a publicly accessible web application prototype built on this classification algorithm, which we have demonstrated to disaster management practitioners and received feedback on. Hence, our contribution to the literature encompasses the provision of a novel imagery dataset, an applied framework from field professionals, and a damage severity classification model with high accuracy. [ABSTRACT FROM AUTHOR]

Purpose: The paper presents a machine-learning approach for the classification of damage and nonlinearity in frame structures based on stress wave amplitude features. It uses a model-based method to extract equivalent stress wave amplitudes in the damaged structure. In the wave-based approach, structural elements are viewed as Timoshenko waveguides through which longitudinal and flexural waves transmit and refract at path discontinuities such as joints, changes in material properties, or cross-section geometry. Damage and nonlinearity introduce additional discontinuities in the structure, causing stress waves to refract and alter the response. The type of damage is identified by introducing the structural response to high-dimensional classifiers, including artificial and convolutional neural networks. Methods: Experimental data from a three-story laboratory structure is used and imposed on a wave-based frame model. For the method to be output-only, stress wave amplitudes are normalized to the base excitation using the frequency response function. Results: The results show that the accuracy of the convolutional neural network with stress wave features reaches 98% while it is only 74% using accelerations as features. Conclusions: The findings showed that damage identification based on features extracted from wave propagation in structures provides more helpful information for the classification of deep learning algorithms. [ABSTRACT FROM AUTHOR]

Automated procedures for classifying vehicle damage are critical in industries requiring extensive vehicle management. Despite substantial research demands, challenges in the field of vehicle damage classification persist due to the scarcity of public datasets and the complexity of constructing datasets. In response to these challenges, we introduce a Three-Quarter View Car Damage Dataset (TQVCD dataset), emphasizing simplicity in labeling, data accessibility, and rich information inherent in three-quarter views. The TQVCD dataset distinguishes class by vehicle orientation (front or rear) and type of damage while maintaining a three-quarter view. We evaluate performance using five prevalent pre-trained deep learning architectures—ResNet-50, DenseNet-160, EfficientNet-B0, MobileNet-V2, and ViT—employing a suite of binary classification models. To enhance classification robustness, we implement a model ensemble method to effectively mitigate individual model dependencies' deviations. Additionally, we interview three experts from the used-car platform to validate the necessity of a vehicle damage classification model using the corresponding dataset from an industrial perspective. Empirical findings underscore the dataset's comprehensive coverage of vehicle perspectives, facilitating efficient data collection and damage classification while minimizing labor-intensive labeling efforts.

After an earthquake, rapid assessment of building damage is crucial for emergency response, reconstruction planning, and public safety. This study evaluates the performance of various Generative Artificial Intelligence (GAI) models in analyzing post-earthquake images to classify structural damage according to the EMS-98 scale, ranging from minor damage to total destruction. Correct classification rates for masonry buildings varied from 28.6% to 64.3%, with mean damage grade errors between 0.50 and 0.79, while for reinforced concrete buildings, rates ranged from 37.5% to 75.0%, with errors between 0.50 and 0.88. Fine-tuning these models could substantially improve accuracy. The practical implications are significant: integrating accurate GAI models into disaster response protocols can drastically reduce the time and resources required for damage assessment compared to traditional methods. This acceleration enables emergency services to make faster, data-driven decisions, optimize resource allocation, and potentially save lives. Furthermore, the widespread adoption of GAI models can enhance resilience planning by providing valuable data for future infrastructure improvements. The results of this work demonstrate the promise of GAI models for rapid, automated, and precise damage evaluation, underscoring their potential as invaluable tools for engineers, policymakers, and emergency responders in post-earthquake scenarios.

The purpose of this study is to use acoustic emission (AE) technology to explore the changes in the interface and mechanical properties of GF/VER composite materials after being treated with NaOH and to analyze the optimal modification conditions and damage propagation process. The results showed that the GF surface became rougher, and the number of reactive groups increased after treating the GF with a NaOH solution. This treatment enhanced the interfacial adhesion between the GF and VER, which increased the interfacial shear strength by 25.31% for monofilament draw specimens and 27.48% for fiber bundle draw specimens compared to those before the GF was modified. When the modification conditions were a NaOH solution concentration of 2 mol/L and a treatment time of 48 h, the flexural strength of the GF/VER composites reached a peak value of 346.72 MPa, which was enhanced by 20.96% compared with before the GF was modified. The process of damage fracture can be classified into six types: matrix cracking, interface debonding, fiber pullout, fiber relaxation, matrix delamination, and fiber breakage, and the frequency ranges of these failure mechanisms are 0~100 kHz, 100~250 kHz, 250~380 kHz, 380~450 kHz, 450~600 kHz, and 600 kHz and above, respectively. This paper elucidates the fracture process of GF/VER composites in three-point bending. It establishes the relationship between the AE signal and the interfacial and force properties of GF/VER composites, realizing the classification of the damage process and characterizing the mechanism. The frequency ranges of damage types and failure mechanisms found in this study offer important guidance for the design and improvement of composite materials. These results are of great significance for enhancing the interfacial properties of composites, assessing the damage and fracture behaviors, and implementing health monitoring. [ABSTRACT FROM AUTHOR]

Many studies deal with the correlation between landslide velocity and damage degree of buildings or infrastructure. For shallow or moderate depth, slow landslides such as complex, slow flow or roto-translation type are well studied by InSAR or other ground-based instruments to retrieve a matrix correlation of velocity damage. However, few of them investigate the effects of deep-seated gravitational slope deformation (DsGSD) displacement. These phenomena usually have a very deep sliding surface, covering a vast area with constant velocity. This study investigates the building damage, mapped with a detailed field survey, correlated with one of the massive DsGSD of the Alps (Sauze d'Oulx DsGSD, NW Italy) affecting several villages. We used multi-temporal InSAR data and ground-based monitoring to obtain 26 years of displacement time series. The results show a complicated correlation, in which several factors influence the degree of building damage, such as the material of the building, their state of maintenance, the position on DsGSD, the depth of movement, the secondary process or the velocity range variability. A simple correlation with velocity is not exhaustive: the central part of DsGSD shows a higher velocity rate (up to 30 mm/yr), but with limited damage; while at the toe boundary of deformation, slow rate of movement produces more severe damage. These findings show that several in-depth studies should integrate velocity data from monitoring to assess the coexistence of these huge complex phenomena and define their impact on anthropic structures before making a risk assessment and a suitable land use planning of mountainous territory. [ABSTRACT FROM AUTHOR]

Effective damage identification is paramount to evaluating safety conditions and preventing catastrophic failures of concrete structures. Although various methods have been introduced in the literature, developing robust and reliable structural health monitoring (SHM) procedures remains an open research challenge. This study proposes a new approach utilizing a 1-D convolution neural network to identify the formation of cracks from the raw electromechanical impedance (EMI) signature of externally bonded piezoelectric lead zirconate titanate (PZT) transducers. Externally bonded PZT transducers were used to determine the EMI signature of fiber-reinforced concrete specimens subjected to monotonous and repeatable compression loading. A leave-one-specimen-out cross-validation scenario was adopted for the proposed SHM approach for a stricter and more realistic validation procedure. The experimental study and the obtained results clearly demonstrate the capacity of the introduced approach to provide autonomous and reliable damage identification in a PZT-enabled SHM system, with a mean accuracy of 95.24% and a standard deviation of 5.64%. [ABSTRACT FROM AUTHOR]

In the current state of the art of process industries/manufacturing technologies, computer‐instrumented and computer‐controlled autonomous techniques are necessary for damage diagnosis and prognosis in operating machinery. From this perspective, the paper addresses the issue of fatigue damage that is one of the most encountered sources of degradation in polycrystalline‐alloy structures of machinery components. In this paper, the convolutional neural networks (CNNs) are applied to synergistic combinations of ultrasonic measurements and images from a confocal microscope (Alicona) to detect and evaluate the risk of fatigue damage. The database of the Alicona has been used to calibrate the ultrasonic database and to provide the ground truth for fatigue damage assessment. The results show that both the ultrasonic data and Alicona images are capable of classifying the fatigue damage into their respective classes with considerably high accuracy. However, the ultrasonic CNN model yields better accuracy than the Alicona CNN model by almost 9%. Highlights: This paper shows the role of artificial intelligence in evaluating the severity of the fatigue damage.A comparison between two convolutional neural network (CNN) models has been demonstrated in this paper.The ultrasonic CNN model provides better performance than microscope CNN model. [ABSTRACT FROM AUTHOR]

Fire hazards can cause severe and irrecoverable damage to reinforced concrete (RC) tunnel linings. Historically, major fire events have led to months of downtime and millions of dollars of losses owing to repair costs and affected operations. The potential threat to the serviceability of transportation networks emphasizes the need to establish a standardized and effective post-fire damage assessment method to guide repairs and restore functionality. This paper proposes a fire damage assessment framework for RC tunnel linings that integrates advanced modeling with visual inspections, non-destructive testing and material sampling. The framework quantifies fire damage to RC tunnel linings in terms of surface discoloration, crack width, concrete spalling, sectional temperatures, strength loss of materials and residual displacement. A damage classification system is proposed based on a collection of international guidelines and feedback from industry experts to map damage metrics and repair strategies. A case study, using data from recent experiments, is conducted to demonstrate the applicability of the proposed framework and the benefits of the information obtained from numerical modeling. This framework can also be integrated with risk-assessment methods to optimize the fire design of tunnels with associated active and/or passive fire protection. [ABSTRACT FROM AUTHOR]

The South-to-North Water Diversion Project in China is an extensive inter-basin water transfer project, for which ensuring the safe operation and maintenance of infrastructure poses a fundamental challenge. In this context, structural health monitoring is crucial for the safe and efficient operation of hydraulic infrastructure. Currently, most health monitoring systems for hydraulic infrastructure rely on commercial software or algorithms that only run on desktop computers. This study developed for the first time a lightweight convolutional neural network (CNN) model specifically for early detection of structural damage in water supply canals and deployed it as a tiny machine learning (TinyML) application on a low-power microcontroller unit (MCU). The model uses damage images of the supply canals that we collected as input and the damage types as output. With data augmentation techniques to enhance the training dataset, the deployed model is only 7.57 KB in size and demonstrates an accuracy of 94.17 ± 1.67% and a precision of 94.47 ± 1.46%, outperforming other commonly used CNN models in terms of performance and energy efficiency. Moreover, each inference consumes only 5610.18 μJ of energy, allowing a standard 225 mAh button cell to run continuously for nearly 11 years and perform approximately 4,945,055 inferences. This research not only confirms the feasibility of deploying real-time supply canal surface condition monitoring on low-power, resource-constrained devices but also provides practical technical solutions for improving infrastructure security.

The increase in both the frequency and magnitude of natural disasters, coupled with recent advancements in artificial intelligence, has introduced prospects for investigating the potential of new technologies to facilitate disaster response processes. Preliminary Damage Assessment (PDA), a labor-intensive procedure necessitating manual examination of residential structures to ascertain post-disaster damage severity, stands to significantly benefit from the integration of computer vision-based classification algorithms, promising efficiency gains and heightened accuracy. Our paper proposes a Vision Transformer (ViT)-based model for classifying damage severity, achieving an accuracy rate of 95%. Notably, our model, trained on a repository of over 18,000 ground-level images of homes with damage severity annotated by damage assessment professionals during the 2020–2022 California wildfires, represents a novel application of ViT technology within this domain. Furthermore, we have open sourced this dataset—the first of its kind and scale—to be used by the research community. Additionally, we have developed a publicly accessible web application prototype built on this classification algorithm, which we have demonstrated to disaster management practitioners and received feedback on. Hence, our contribution to the literature encompasses the provision of a novel imagery dataset, an applied framework from field professionals, and a damage severity classification model with high accuracy.

The importance of the sustainability of wood buildings is increasing. The renewed attention highlights the need to assess the wood deterioration accurately, in the initial years of service, to optimize treatment during its lifetime and reduce maintenance costs. This study presents a methodology for inspecting and classifying damage of wood in service, relying on visual inspection and oriented to non-structural wooden components. This approach enables more affordable, widespread, and frequent monitoring of wooden elements in use, promoting their routine maintenance. The methodology was tested in the pine wood (Pinus sylvestris) facades with up to 5 years of service in a hotel building in northern Portugal. Despite its relatively brief period of operation, the building displays indications of both abiotic and biotic degradation of the wood across all its different facade orientations. Based on that, the study highlights the natural aging of Scots pine according to the building's age, orientation, maintenance treatments, and exposure conditions. These findings provide insights into conservation plan optimization and emphasize the need for regular maintenance of wooden elements in outdoor environments, even in the early years of service. [ABSTRACT FROM AUTHOR]

With the increasingly comprehensive utilisation of Carbon Fibre-Reinforced Polymers (CFRP) in modern industry, defects detection and characterisation of these materials have become very important and draw significant research attention. During the past 10 years, Artificial Intelligence (AI) technologies have been attractive in this area due to their outstanding ability in complex data analysis tasks. Most current AI-based studies on damage characterisation in this field focus on damage segmentation and depth measurement, which also faces the bottleneck of lacking adequate experimental data for model training. This paper proposes a new framework to understand the relationship between Barely Visible Impact Damage features occurring in typical CFRP laminates to their corresponding controlled drop-test impact energy using a Deep Learning approach. A parametric study consisting of one hundred CFRP laminates with known material specification and identical geometric dimensions were subjected to drop-impact tests using five different impact energy levels. Then Pulsed Thermography was adopted to reveal the subsurface impact damage in these specimens and recorded damage patterns in temporal sequences of thermal images. A convolutional neural network was then employed to train models that aim to classify captured thermal photos into different groups according to their corresponding impact energy levels. Testing results of models trained from different time windows and lengths were evaluated, and the best classification accuracy of 99.75% was achieved. Finally, to increase the transparency of the proposed solution, a salience map is introduced to understand the learning source of the produced models. [ABSTRACT FROM AUTHOR]

The condition monitoring of offshore wind power plants is an important topic that remains open. This monitoring aims to lower the maintenance cost of these plants. One of the main components of the wind power plant is the wind turbine foundation. This study describes a data-driven structural damage classification methodology applied in a wind turbine foundation. A vibration response was captured in the structure using an accelerometer network. After arranging the obtained data, a feature vector of 58 008 features was obtained. An ensemble approach of feature extraction methods was applied to obtain a new set of features. Principal Component Analysis (PCA) and Laplacian eigenmaps were used as dimensionality reduction methods, each one separately. The union of these new features is used to create a reduced feature matrix. The reduced feature matrix is used as input to train an Extreme Gradient Boosting (XGBoost) machine learning-based classification model. Four different damage scenarios were applied in the structure. Therefore, considering the healthy structure, there were 5 classes in total that were correctly classified. Five-fold cross validation is used to obtain a final classification accuracy. As a result, 100% of classification accuracy was obtained after applying the developed damage classification methodology in a wind-turbine offshore jacket-type foundation benchmark structure. [ABSTRACT FROM AUTHOR]

To understand the workload of house cleanup and related workforce shortage after a disaster, the actual work situation in disaster-stricken areas is accounted for by disaster volunteer work management data created by the Disaster Volunteer Center of Joso City in Ibaraki Prefecture at the time of the Kanto–Tohoku Heavy Rain Disaster in September 2015. Using the classification of inundation depth, judged from ground elevation, the weekly workload of house cleanup according to the work content is recorded to clarify the characteristics of each area. Comparing this with the inundated areas without destructions by water flow, near the bank break with house destructions, in the urban area, and around the farmland along the old road, a model to estimate the workload is constructed. It was observed that indoor work to recommence living in urban areas continued for a long time, while the work was completed in a relatively short time in the area along the old road. The area near the bank break, with a small number of houses, witnessed very few house destructions. Hence, it is not necessary to separately calculate the workload caused by house destructions. The appropriateness of the estimated results was verified by using a method to estimate the workload based on the amount of disaster waste. As a result, the total workload estimated by disaster volunteers and victims for the busy period of two months was a million people. In the case of the Joso City flood, very few houses were completely destroyed, therefore, regular living could be resumed swiftly and people settled there after the disaster due to its proximity to the metropolitan area. Hence, the population decreased by the flood was recovered in two years. [ABSTRACT FROM AUTHOR]

Automatic damage assessment by analysing UAV-derived 3D point clouds provides fast information on the damage situation after an earthquake. However, the assessment of different damage grades is challenging given the variety in damage characteristics and limited transferability of methods to other geographic regions or data sources. We present a novel change-based approach to automatically assess multi-class building damage from real-world point clouds using a machine learning model trained on virtual laser scanning (VLS) data. Therein, we (1) identify object-specific point cloud-based change features, (2) extract changed building parts using k-means clustering, (3) train a random forest machine learning model with VLS data based on object-specific change features, and (4) use the classifier to assess building damage in real-world photogrammetric point clouds. We evaluate the classifier with respect to its capacity to classify three damage grades (heavy, extreme, destruction) in pre-event and post-event point clouds of an earthquake in L’Aquila (Italy). Using object-specific change features derived from bi-temporal point clouds, our approach is transferable with respect to multi-source input point clouds used for model training (VLS) and application (real-world photogrammetry). We further achieve geographic transferability by using simulated training data which characterises damage grades across different geographic regions. The model yields high multi-target classification accuracies (overall accuracy: 92.0%–95.1%). Classification performance improves only slightly when using real-world region-specific training data (< 3% higher overall accuracies). We consider our approach especially relevant for applications where timely information on the damage situation is required and sufficient real-world training data is not available.

Effective damage identification is paramount to evaluating safety conditions and preventing catastrophic failures of concrete structures. Although various methods have been introduced in the literature, developing robust and reliable structural health monitoring (SHM) procedures remains an open research challenge. This study proposes a new approach utilizing a 1-D convolution neural network to identify the formation of cracks from the raw electromechanical impedance (EMI) signature of externally bonded piezoelectric lead zirconate titanate (PZT) transducers. Externally bonded PZT transducers were used to determine the EMI signature of fiber-reinforced concrete specimens subjected to monotonous and repeatable compression loading. A leave-one-specimen-out cross-validation scenario was adopted for the proposed SHM approach for a stricter and more realistic validation procedure. The experimental study and the obtained results clearly demonstrate the capacity of the introduced approach to provide autonomous and reliable damage identification in a PZT-enabled SHM system, with a mean accuracy of 95.24% and a standard deviation of 5.64%.

Adaptive boosting (AdaBoost) algorithms fuse multiple weak classifiers to generate a strong classifier by adaptively determining the fusion weights of the weak classifiers. According to incorrect or correct classification results, sample weights become larger or smaller. However, this weight update scheme neglects valuable information in the results. Moreover, an important requirement for weak classifiers is an accuracy higher than random guessing. This requirement is likely to lead to an unexpected result. This means that several generated weak classifiers with similar classification results cannot learn from each other. Consequently, the advantage of fusing multiple weak classifiers disappears. The classification and therefore distinction of different failure modes in materials is a typical task for classical nondestructive testing approaches as well as for new approaches based on machine learning methods. In the case different approaches can be applied, the main question is, which and how tuned approaches provide the best results in terms of accuracy or similar metrics. In the multi-damage classification task distinguishing different physical failure mechanisms in Carbon Fiber Reinforced Polymer (CFRP), the above two aspects complicate the application of AdaBoost algorithms. To improve the results, a novel AdaBoost with distance-based weighted least square support vector machine (WLSSVM) and filter factor is proposed. The distance-based WLSSVM is employed to increase the diversity of weak classifiers, the distances of the classification plane and samples are used to measure the classification task. The filter factor is proposed to filter out unnecessary classifiers contributing less to the final decision. The experimental results demonstrate that the improved AdaBoost schemes with distance-based WLSSVM and filter factor outperform state-of-the-art algorithms. The effects of the scheme using the new weighted update and the filter factor on the algorithm are discussed, respectively. The experimental results show that the combination of the two schemes perform better than other schemes. [ABSTRACT FROM AUTHOR]

Most modern Earth and Universe observation spacecraft are now equipped with large lightweight and flexible structures, such as antennas, telescopes, and extendable elements. The trend of hosting more complex and bigger appendages, essential for high-precision scientific applications, made orbiting satellites more susceptible to performance loss or degradation due to structural damages. In this scenario, Structural Health Monitoring strategies can be used to evaluate the health status of satellite substructures. However, in particular when analysing large appendages, traditional approaches may not be sufficient to identify local damages, as they will generally induce less observable changes in the system dynamics yet cause a relevant loss of payload data and information. This paper proposes a deep neural network to detect failures and investigate sensor sensitivity to damage classification for an orbiting satellite hosting a distributed network of accelerometers on a large mesh reflector antenna. The sensors-acquired time series are generated by using a fully coupled 3D simulator of the in-orbit attitude behaviour of a flexible satellite, whose appendages are modelled by using finite element techniques. The machine learning architecture is then trained and tested by using the sensors' responses gathered in a composite scenario, including not only the complete failure of a structural element (structural break) but also an intermediate level of structural damage. The proposed deep learning framework and sensors configuration proved to accurately detect failures in the most critical area or the structure while opening new investigation possibilities regarding geometrical properties and sensor distribution. [ABSTRACT FROM AUTHOR]

The condition monitoring of offshore wind power plants is an important topic that remains open. This monitoring aims to lower the maintenance cost of these plants. One of the main components of the wind power plant is the wind turbine foundation. This study describes a data-driven structural damage classification methodology applied in a wind turbine foundation. A vibration response was captured in the structure using an accelerometer network. After arranging the obtained data, a feature vector of 58 008 features was obtained. An ensemble approach of feature extraction methods was applied to obtain a new set of features. Principal Component Analysis (PCA) and Laplacian eigenmaps were used as dimensionality reduction methods, each one separately. The union of these new features is used to create a reduced feature matrix. The reduced feature matrix is used as input to train an Extreme Gradient Boosting (XGBoost) machine learning-based classification model. Four different damage scenarios were applied in the structure. Therefore, considering the healthy structure, there were 5 classes in total that were correctly classified. Five-fold cross validation is used to obtain a final classification accuracy. As a result, 100% of classification accuracy was obtained after applying the developed damage classification methodology in a wind-turbine offshore jacket-type foundation benchmark structure.

This study demonstrates the use of multi-temporal LiDAR data to extract collapsed buildings and to monitor their removal process in Minami-Aso village, Kumamoto prefecture, Japan, after the April 2016 Kumamoto earthquake. By taking the difference in digital surface models (DSMs) acquired at pre- and post-event times, collapsed buildings were extracted and the results were compared with damage survey data by the municipal government and aerial optical images. Approximately 40% of severely damaged buildings showed a reduction in the average height within a reduced building footprint between the pre- and post-event DSMs. Comparing the removal process of buildings in the post-event periods with the damage classification result from the municipal government, the damage level was found to affect judgements by the owners regarding demolition and removal. [ABSTRACT FROM AUTHOR]

Summary: A large amount of the world's existing infrastructure is reaching the end of its service life, requiring intervention in the form of structural rehabilitation or replacement. A critical aspect of such asset management is the condition assessment of these structures to evaluate their existing health and dictate the scheduling and extent of required rehabilitation. It has been demonstrated that human‐based manual inspections face logistical constraints and are expensive, time extensive, and subjective, depending on the knowledge of the inspection. Recently, autonomous vision‐based techniques have been proposed as an alternative, more accurate method for the inspection of deteriorating structures. Convolutional neural networks (CNNs) have demonstrated state‐of‐the‐art accuracy with respect to damage classification for concrete structures and are often implemented to process images taken from vision‐based sensors such as cameras, smartphones, and drones. However, these archetypes require a large database of annotated images to train the network to an accurate level, which is not readily available for real‐life structures. Moreover, CNNs are limited to the extent by which they are trained; they are often only trained for binary damage classification of a singular material model. This paper addresses these challenges of CNNs through the application of a generative adversarial network (GANs) for multiclass damage detection of concrete structures. The proposed GAN is trained using the SDNET2018 dataset to detect cracking, spalling, pitting, and construction joints in concrete surfaces. Moreover, transfer learning is implemented to transfer the learned features of the GAN to a CNN architecture to allow for accurate image classification. It is concluded that, for a 0%–30% reduction in the amount of labeled data used, the proposed GAN method has comparable accuracy to traditional CNNs. [ABSTRACT FROM AUTHOR]

Damage types are important for structural condition assessment, however, for conventionally guided wave-based inspections, the characteristics extracted from the guided wave packets are usually used to detect, locate and quantify the damages, but not classify them. In this work, the data-driven method is proposed to classify the common damages in the pipe utilizing the guided wave signals obtained from numerous damage detection tests. The fundamental torsional mode T(0,1) is selected to conduct the guided wave-based damage detection to reduce the complexity of signal processing for its almost non-dispersive property. A total of 520 groups of experimental data under different degrees of damage were obtained to verify the proposed method. Finally, with help of a deep neural network (DNN) algorithm, all response data from the damages in the pipes were all clearly classified with quite high probability. [ABSTRACT FROM AUTHOR]

Automated Damage Classification on Concrete Bridges Using Convolutional Neural Networks Against the background of an ageing structure stock and the constant increase in heavy traffic, frequent structural inspections of high quality are indispensable. In accomplishing this task, the use of digital methods within the framework of digitized inspections (DIs) offers great potential for improvement in terms of cost‐effectiveness and quality. An essential component of DIs is the automated detection of damage with Convolutional Neural Networks (CNNs). As part of the research project "Model‐Based Digital Structural Inspection – MoBaP", CNNs are being trained at the University of the Bundeswehr Munich for the classification of defects occurring on concrete bridges. On this domain's currently largest open‐source dataset (CODEBRIM), the best CNN achieves an exact match ratio of 74 % and thus currently defines a strong baseline. In order to also train neural networks for object detection and semantic segmentation in this domain, a separate dataset is created. This enables not only the classification but also the localisation of damage on images. In this paper, the authors discuss the procedure of training neural networks for the classification of defects on concrete bridges and show a detailed analysis of test results. In addition, the development and current status of their own dataset is presented. [ABSTRACT FROM AUTHOR]

The importance of the sustainability of wood buildings is increasing. The renewed attention highlights the need to assess the wood deterioration accurately, in the initial years of service, to optimize treatment during its lifetime and reduce maintenance costs. This study presents a methodology for inspecting and classifying damage of wood in service, relying on visual inspection and oriented to non-structural wooden components. This approach enables more affordable, widespread, and frequent monitoring of wooden elements in use, promoting their routine maintenance. The methodology was tested in the pine wood (Pinus sylvestris) facades with up to 5 years of service in a hotel building in northern Portugal. Despite its relatively brief period of operation, the building displays indications of both abiotic and biotic degradation of the wood across all its different facade orientations. Based on that, the study highlights the natural aging of Scots pine according to the building’s age, orientation, maintenance treatments, and exposure conditions. These findings provide insights into conservation plan optimization and emphasize the need for regular maintenance of wooden elements in outdoor environments, even in the early years of service.

Damage detection and the classification of carbon fiber-reinforced composites using non-destructive testing (NDT) techniques are of great importance. This paper applies an acoustic emission (AE) technique to obtain AE data from three tensile damage tests determining fiber breakage, matrix cracking, and delamination. This article proposes a deep learning approach that combines a state-of-the-art deep learning technique for time series classification: the InceptionTime model with acoustic emission data for damage classification in composite materials. Raw AE time series and frequency-domain sequence data are used as the input for the InceptionTime network, and both obtain very high classification performances, achieving high accuracy scores of about 99%. The InceptionTime network produces better training, validation, and test accuracy with the raw AE time series data than it does with the frequency-domain sequence data. Simultaneously, the InceptionTime model network shows its potential in dealing with data imbalances. [ABSTRACT FROM AUTHOR]

The seismic vulnerability assessment of existing reinforced concrete (RC) buildings is a significant source of disaster mitigation plans and rescue services. Different countries evolved various Rapid Visual Screening (RVS) techniques and methodologies to deal with the devastating consequences of earthquakes on the structural characteristics of buildings and human casualties. Artificial intelligence (AI) methods, such as machine learning (ML) algorithm-based methods, are increasingly used in various scientific and technical applications. The investigation toward using these techniques in civil engineering applications has shown encouraging results and reduced human intervention, including uncertainties and biased judgment. In this study, several known non-parametric algorithms are investigated toward RVS using a dataset employing different earthquakes. Moreover, the methodology encourages the possibility of examining the buildings' vulnerability based on the factors related to the buildings' importance and exposure. In addition, a web-based application built on Django is introduced. The interface is designed with the idea to ease the seismic vulnerability investigation in real-time. The concept was validated using two case studies, and the achieved results showed the proposed approach's potential efficiency. [ABSTRACT FROM AUTHOR]

Extracting damage-sensitive features plays an important role in all structural health monitoring applications, as it determines the metrics on which to base decision-making with regard to operation, maintenance, damage state, and so on. This article adopts the widely employed frequency response function, both its magnitude and phase, as the selected feature source and demonstrates how the damage types and locations are able to be classified by means of Bayesian recursive confidence updating. The features are estimated from the in situ acquired vibration data on a rotating machinery test-bed, and the probabilistic models that quantify feature uncertainty are the likelihood functions in a Bayesian framework, which informs the most plausible decisions based on the collected evidence. The damage classification effort in this article specifically calculates the posterior probability, considering the prior and likelihood of data observations; posterior probabilities are then fed back as prior probabilities in the next iteration as new test data are observed. There are three ball-bearing damage conditions applied to the rotary machine test-bed, and the correct model representing the correct damage types will be selected by the model with the maximum posterior confidence. Classification via posterior probability is shown in this article to outperform traditional likelihood evaluations, and the Bayesian recursive implementation distinguishes all three conditions in this work.