Accuracy Of Damage Detection Research Articles

Challenges in Damage Detection for Real-time Monitoring and Predictive Maintenance Methodology

Damage detection techniques offer a sophisticated and effective way to monitor and assess the health of engineering systems, but they come with challenges related to model accuracy, sensor data quality, and the detection of subtle or distributed damage. Advances in computational methods, sensor technology, and hybrid techniques continue to improve the practical application of these methods, making them increasingly relevant in real-time condition monitoring and predictive maintenance systems. The proposed methodology aims to develop damage detection systems that play a key role in enabling real-time monitoring and early identification of potential problems. This approach significantly reduces the need for conventional checks, leading to time and cost savings. By predicting the remaining service life of components, the methodology helps optimize maintenance schedules and prevent unexpected failures. Additionally, the use of smart materials and sensors enhances the accuracy and efficiency of damage detection, allowing more proactive, data-driven damage detection and monitoring systems.

Delamination damage identification through multi-input data using impact echo and study of model efficiency

ABSTRACT This paper describes delamination damage identification using a robust multi-input deep convolutional neural network (MI – DCNN) model. By incorporating various impact echo signals, including time-domain, frequency-domain, and short-time Fourier transform (STFT) data, the proposed model captures a wider range of signal characteristics, thus improving the accuracy of damage detection. The study compares four different damage identification models applied to six artificially created delamination cases with varying depths and sizes. Among the models, the MI – DCNN that leverages frequency-domain and STFT data achieves the highest testing accuracy at 89.7%. Furthermore, the study explores the trade-off between model accuracy and computation time, concluding that optimal performance is achieved using 200 × 200 resolution images and 100 input samples. To assess real-world applicability, the model’s performance was validated using previously collected field data from a concrete wall, where known defect areas were identified through core sampling. These findings provide valuable insights for improving damage detection in non-destructive testing techniques, offering practical implications for enhancing structural health monitoring systems, where both accuracy and computational efficiency are critical.

Monitoring the Degree of Gansu Zokor Damage in Chinese Pine by Hyperspectral Remote Sensing

Chinese pine has been extensively planted in the Loess Plateau, but it faces significant threats from Gansu zokor. Traditional methods for monitoring rodent damage rely on manual surveys to assess damage rates but are time-consuming and often underestimate the actual degree of damage, particularly in mildly affected pines. This study proposes a remote sensing monitoring method that integrates hyperspectral analysis with physiological and biochemical parameter models to enhance the accuracy of rodent damage detection. Using ASD Field Spec 4, we analyzed spectral data from 125 Chinese pine needles, measuring chlorophyll (CHC), carotenoid (CAC), and water content (WAC). Through correlation analysis, we identified sensitive vegetation indices (VIs) and red-edge parameters (REPs) linked to different levels of damage. We report several key results. The 680 nm spectral band is instrumental in monitoring damage, with significant decreases in CHC, CAC, and WAC corresponding to increased damage severity. We identified six VIs and five REPs, which were later predicted using stepwise regression (SR), support vector machine (SVM), and random forest (RF) models. Among all models, the vegetation index-based RF model exhibited the best predictive performance, achieving coefficient of determination (R2) values of 0.988, 0.949, and 0.999 for CHC, CAC, and WAC, with root mean square errors (RMSEs) of 0.115 mg/g, 0.042 mg/g, and 0.007 mg/g, and mean relative errors (MREs) of 8.413%, 9.169%, and 1.678%. This study demonstrates the potential of hyperspectral remote sensing technology for monitoring rodent infestations in Chinese pines, providing a reliable basis for large-scale assessments and effective management strategies for pest control.

Improved EMAT Sensor Design for Enhanced Ultrasonic Signal Detection in Steel Wire Ropes.

This study is focused on optimizing electromagnetic acoustic transducer (EMAT) sensors for enhanced ultrasonic guided wave signal generation in steel cables using CAD and modern manufacturing to enable contactless ultrasonic signal transmission and reception. A lab test rig with advanced measurement and data processing was set up to test the sensors' ability to detect cable damage, like wire breaks and abrasion, while also examining the effect of potential disruptors such as rope soiling. Machine learning algorithms were applied to improve the damage detection accuracy, leading to significant advancements in magnetostrictive measurement methods and providing a new standard for future development in this area. The use of the Vision Transformer Masked Autoencoder Architecture (ViTMAE) and generative pre-training has shown that reliable damage detection is possible despite the considerable signal fluctuations caused by rope movement.

Efficient Structural Damage Detection with Minimal Input Data: Leveraging Fewer Sensors and Addressing Model Uncertainties

In the field of structural damage detection through vibration measurements, most existing methods demand extensive data collection, including vibration readings at multiple levels, strain data, temperature measurements, and numerous vibration modes. These requirements result in high costs and complex instrumentation processes. Additionally, many approaches fail to account for model uncertainties, leading to significant discrepancies between the actual structure and its numerical reference model, thus compromising the accuracy of damage identification. This study introduces an innovative computational method aimed at minimizing data requirements, reducing instrumentation costs, and functioning with fewer vibration modes. By utilizing information from a single vibration sensor and at least three vibration modes, the method avoids the need for higher-mode excitation, which typically demands specialized equipment. The approach also incorporates model uncertainties related to geometry and mass distribution, improving the accuracy of damage detection. The computational method was validated on a steel frame structure under various damage conditions, categorized as single or multiple damage. The results indicate up to 100% accuracy in locating damage and up to 80% accuracy in estimating its severity. These findings demonstrate the method’s potential for detecting structural damage with limited data and at a significantly lower cost compared to conventional techniques.

A Deep Learning-based Method of Investigating Rammed-earth Wall Damage on the Ming Great Wall Military Defense System

The collection, detection, and statistical analysis of massive damage information from large cultural heritage sites is an important issue that affects the progress, depth, and quality of cultural heritage protection efforts. The Ming Great Wall of China, known for its vast size, poses a significant challenge to protection efforts. Conventional methods for collecting and recognizing damage information from the wall are nearly impossible due to its scale. The limitation has significantly hindered efforts to safeguard the vulnerable rammed-earth walls of the Ming Great Wall. To address this issue, we developed new technical schemes that combine the efficiency of unmanned aerial vehicles (UAV) for low-altitude surveying and mapping with the accuracy of artificial intelligence detection. This enables the efficient collection, detection, and statistical analysis of a massive amount of damage data from the Great Wall sites. The system achieved an average damage detection accuracy of 0.838, as measured by the average precision (AP). Additionally, the system's average effective detection range exceeded 91.5%, while reducing manual labor time by about 95%. These results provide accurate, efficient, and timely data and technical support for efforts such as status investigation, condition evaluation, protection and maintenance, and budgeting for the Great Wall sites. Furthermore, this research proposes a potential approach for gathering and analyzing data from other large-scale cultural heritage sites.

A multitask framework with self-attention mechanism for simultaneous detection of axial pressure, shear deformation, and rupture damage in rubber bearings

Base-isolated structures can effectively control structural response, of which rubber bearings are key components. To ensure the proper functioning of rubber bearings, it is important to accurately detect their state. In previous studies, a smart rubber bearing has been proposed to monitor the axial pressure, shear deformation, and rupture damage of rubber bearings. However, owing to the small dataset and limited ability of the prediction model, two problems exist in previous research: (1) the axial pressure, shear deformation, and rupture damage cannot be detected simultaneously and (2) the detection accuracy is not sufficiently high for practical applications. This study solves these problems in three aspects. First, it addresses the issue of limited data by researching and comparing three data augmentation methods. Second, a multitask framework with a self-attention mechanism is established to simultaneously detect axial compression, shear deformation, and rupture damage. Finally, we introduce a two-stage optimization method based on Bayesian optimization and a grid search for the network structure and optimization. The root-mean-square errors for predicting the axial pressure and shear deformation in the test set are 0.19 MPa and 2.04%, which reduced the error by up to 56.8% and 73.0%, respectively, compared to conventional deep neural network models. In addition, the accuracy of rupture damage detection reached 100%.

Composite delamination damage location based on non-orthogonal air-coupled ultrasonic guided waves and Artifact-Reduction damage index

This study focuses on the localization of delamination damage in composite materials. Due to the attenuation of the air-coupled ultrasound at the gas–solid coupling interface, the signal-to-noise ratio of the air-coupled ultrasonic signal is low, which results in low accuracy of damage detection. This paper proposes a method to locate delamination damage in composite materials. This method uses non-orthogonal Air-coupled Ultrasonic Guided Waves for B-scan; an artifact-reduction damage index (ARDI) is designed with the proportion of the scan paths containing damage information to the entire scan paths. These two exquisite designs improve detection accuracy. Finally, the probability of damage occurrence is calculated, and the detection of the damage location is achieved, with the positioning error of the damage being less than 1.5%.

A Hybrid GAN-Inception Deep Learning Approach for Enhanced Coordinate-Based Acoustic Emission Source Localization

In this paper, we propose a novel approach to coordinate-based acoustic emission (AE) source localization to address the challenges of limited and imbalanced datasets from fiber-optic AE sensors used for structural health monitoring (SHM). We have developed a hybrid deep learning model combining four generative adversarial network (GAN) variants for data augmentation with an adapted inception neural network for regression-based prediction. The experimental setup features a single fiber-optic AE sensor based on a tightly coiled fiber-optic Fabry-Perot interferometer formed by two identical fiber Bragg gratings. AE signals were generated using the Hsu-Nielsen pencil lead break test on a grid-marked thin aluminum plate with 35 distinct locations, simulating real-world structural monitoring conditions in bounded isotropic plate-like structures. It is demonstrated that the single-sensor configuration can achieve precise localization, avoiding the need for a multiple sensor array. The GAN-based signal augmentation expanded the dataset from 900 to 4500 samples, with the Wasserstein distance between the original and synthetic datasets decreasing by 83% after 2000 training epochs, demonstrating the high fidelity of the synthetic data. Among the GAN variants, the standard GAN architecture proved the most effective, outperforming other variants in this specific application. The hybrid model exhibits superior performance compared to non-augmented deep learning approaches, with the median error distribution comparisons revealing a significant 50% reduction in prediction errors, accompanied by substantially improved consistency across various AE source locations. Overall, this developed hybrid approach offers a promising solution for enhancing AE-based SHM in complex infrastructures, improving damage detection accuracy and reliability for more efficient predictive maintenance strategies.

Bridge Surface Defect Localization Based on Panoramic Image Generation and Deep Learning-Assisted Detection Method

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.

SigBERT: vibration-based steel frame structural damage detection through fine-tuning BERT

PurposeThis article introduces SigBERT, a novel approach that fine-tunes bidirectional encoder representations from transformers (BERT) for the purpose of distinguishing between intact and impaired structures by analyzing vibration signals. Structural health monitoring (SHM) systems are crucial for identifying and locating damage in civil engineering structures. The proposed method aims to improve upon existing methods in terms of cost-effectiveness, accuracy and operational reliability.Design/methodology/approachSigBERT employs a fine-tuning process on the BERT model, leveraging its capabilities to effectively analyze time-series data from vibration signals to detect structural damage. This study compares SigBERT's performance with baseline models to demonstrate its superior accuracy and efficiency.FindingsThe experimental results, obtained through the Qatar University grandstand simulator, show that SigBERT outperforms existing models in terms of damage detection accuracy. The method is capable of handling environmental fluctuations and offers high reliability for non-destructive monitoring of structural health. The study mentions the quantifiable results of the study, such as achieving a 99% accuracy rate and an F-1 score of 0.99, to underline the effectiveness of the proposed model.Originality/valueSigBERT presents a significant advancement in SHM by integrating deep learning with a robust transformer model. The method offers improved performance in both computational efficiency and diagnostic accuracy, making it suitable for real-world operational environments.

Best reconstruction frequency for time-reversal process of Lamb waves and its determination from a single measurement

This article presents a theoretical framework for the concept of the best reconstruction frequency (BRF) of Lamb waves in elastic plates and its significance in the context of structural health monitoring (SHM). The time-reversal process (TRP) of Lamb waves has been widely explored for baseline-free damage detection in thin-walled structures. Previous studies have indicated that the accuracy of damage detection can be significantly improved by exciting Lamb waves at a frequency where the time-reversibility in the undamaged state is maximum within a desired frequency range. This frequency, termed the BRF, has been determined phenomenologically in prior research but lacked a rigorous theoretical foundation. In this study, the BRF is derived as the frequency at which the amplitude dispersion of the main mode of the reconstructed signal after the TRP is minimized. Accordingly, a method is put forth to determine this frequency from a single measurement using a broadband excitation eliminating the need to compute the similarity between the reconstructed and input waveforms at different excitation frequencies. The developed theory is validated with experiments conducted on an aluminium plate with Lamb waves generated and sensed by surface-bonded piezoelectric patch transducers. Notably, the study establishes that the BRF is a system property specific to a given transducer-plate-adhesive system and is independent of the distance between transducers. This characteristic makes it suitable for identifying damage locations when employing multiple sensing paths. The findings constitute an important milestone in understanding the TRP of Lamb waves and developing robust SHM technologies based on it.

Structural Damage Detection through Dual-Channel Pseudo-Supervised Learning

Structural damage detection is crucial for maintaining the health and safety of buildings. However, achieving high accuracy in damage detection remains challenging, especially in noisy environments. To improve the accuracy and noise robustness of damage detection, this study proposes a novel method that combines the Conformer model and the dual-channel pseudo-supervised (DCPS) learning strategy for structural damage detection. The DCPS learning strategy improves the stability and accuracy of the model in noisy environments. It enables the model to input acceleration signals with different noise levels into each branch of the dual-channel network, thereby learning noise-robust features. The Conformer model, as the backbone network, integrates the advantages of convolutional neural networks (CNNs) and Transformers to effectively extract both local and global features from acceleration signals. The proposed method is validated using a four-story single-span steel-frame building model and the IASC-ASCE simulated benchmark structure. The results show that the proposed method achieves a higher classification accuracy than existing structural damage detection methods. Compared to the single Conformer-based method, this method improves the accuracy by 1.57% and 4.93% for the two validation structures, respectively. Moreover, the proposed method benefits from the DCPS learning strategy’s ability to achieve superior noise robustness compared to other methods. The proposed method holds potential value for improving the accuracy of damage detection and noise robustness in scenarios such as maintenance and extreme events.

Automated ultrasonic scattering energy method for evaluation of small-sized cracking damage in concrete

The aim of this study was to develop an automatic ultrasonic scattering energy method (USEM) to evaluate small-scale damage to concrete. The automated system measured Leaky Rayleigh waves from the specimens. Herein, the energy of the scattering portion of waves caused by cracks was extracted using a 2D Fourier transform. USEM has the advantage of detecting cracking damage smaller than the applied ultrasonic wavelength, which is problematic when conventional ultrasonic methods are applied to concrete. The proposed methodology was evaluated using laboratory-scale specimens and a concrete bridge exposed to freeze–thaw cycles in the field. The results of the extracted scattering energy demonstrated that the USEM is sufficiently sensitive to detect and localize subwavelength damages of 0.05 mm in concrete. Furthermore, the proposed USEM was compared with conventional ultrasonic pulse velocity with respect to the accuracy of damage detection.

Image acquisition technology for unmanned aerial vehicles based on YOLO - Illustrated by the case of wind turbine blade inspection

Wind energy, as a renewable energy source, is becoming increasingly important. The maintenance and damage detection of wind turbine blades are particularly crucial. For this purpose, the study aims to optimize the You Only Look Once (YOLO) processing algorithm for drone images to improve the detection efficiency. Firstly, the damage images captured by drones are preprocessed and optimized, including deblurring, noise reduction, and image enhancement. Subsequently, the YOLOv5 model is improved in terms of structure and regression function, and a novel damage detection model is proposed. The research results indicated that the minimum loss function value of the improved model was 2.75, the average accuracy was 95 %, and the highest intersection over union was 91 %. After simulation testing, the detection effect of this model on abrasion, crackle, edge cracking, and coating peeling images was significantly better than other models in the same series. Its average time was as short as 2.43 s, reaching a maximum frame rate of 35.46. From this, the combination of drone image technology and improved image processing algorithm has a positive impact on improving the operational efficiency and safety of wind turbine blades. Compared with the traditional methods, the proposed model has significant advantages in terms of accuracy and real-time performance of damage detection, providing a new technical means for efficient maintenance of wind turbines. Meanwhile, the method shows high robustness and reliability in different types of damage detection, demonstrating the extensive potential in practical applications.

Road damage detection and classification using deep neural networks

In addressing the challenges of enhancing road damage detection efficiency and accuracy, this paper introduces an optimized YOLOv8 model suitable for embedded systems. The model significantly enhances precision, recall, and mean Average Precision (mAP), achieving 65.7% mAP on the RDD2022 dataset, thereby surpassing models such as Faster R-CNN and SSD. This advancement is attributed to the integration of a Deformable Attention Transformer, a GSConv-powered slim-neck module, and the MPDIoU loss function. These innovations not only contribute to the model's high performance but also set a new benchmark in road damage detection technology, thereby paving the way for future enhancements in the field.

Transfer learning-based Gaussian process classification for lattice structure damage detection

This study presents a novel approach for real-time vision-based structural health monitoring, focusing on evaluating the deformation state of lattice structures. The structures are renowned for their remarkable recovery capabilities and exhibit similar mechanical responses under compressive loads. Despite these characteristics, quickly assessing the health status of the applied structure using knowledge from another related lattice structure is usually time-consuming and impractical. To address this, we propose to combine Gaussian process classification with transfer learning, termed TL-GPC, to detect damage states under compressive loads while also achieving uncertainty quantification. By employing structural deformations captured via the optical flow algorithm as inputs, the internal transfer kernel factor in TL-GPC is tailored to model knowledge transfer between source and target domain inputs. Experimental results show that the proposed TL-GPC model can deliver higher damage detection accuracy while ensuring stable uncertainty quantification in scenarios with limited and unbalanced experimental data.

Damage detection method for square steel tube based on CS-NME algorithm via ultrasonic guided waves

The utilization of ultrasonic guided wave (UGW) technology has garnered considerable attention in non-destructive testing field, particularly for steel components. However, for square steel tubes with noncircular cross sections, this method encounters severer frequency dispersion, which hampers the accuracy of damage identification. To address this issue, the approach utilizing the normal mode expansion (NME) method combined with cuckoo search (CS) algorithm to develop a layout strategy for ultrasonic transducer position and length is proposed, which enables single mode excitation of UGW while reducing the interference from redundant clutter signals, thereby enhancing the accuracy of damage detection. The efficacy of the proposed approach is evaluated via numerical simulations and laboratory experiments. The results show that this method can significantly reduce the interference of other modes by optimizing the location and length of ultrasonic transducers, and successfully detect the hole and crack damage on the square steel tube.

Machine learning-based improvement of crack localization in concrete structures

Acoustic emission (AE) method is useful for damage detection in structures. However, processing the massive amount of AE data with traditional analysis methods is time-consuming. Therefore, machine learning (ML) integration provides a more rational and efficient solution by accelerating the data analysis and improving the damage detection accuracy. This study aims to improve source localization, which provides to identify cracking patterns by signal-based analysis, by training the ML model with the AE dataset for accurate damage diagnosis of concrete structures. Analyzes were conducted on the ML model using AE data collected on a concrete member under laboratory conditions. In this way, the ML model that learned signals with multi-variable wave characteristics and parameters was integrated into the source localization algorithm and thus, AE source location results were enhanced. Furthermore, due to its ability to identify damaged areas, this approach is essential for structural safety by providing early damage detection and accurate localization of cracks. This integration of the machine learning model with AE data will be considered as an advanced tool for the effective monitoring of damages in structures.

Enhancing acoustic emission analysis for corrosion damage detection in reinforced concrete by k-nearest neighbors method

The Acoustic Emission (AE) method is considered a significant tool for detecting damage in reinforced concrete structures caused by reinforcement corrosion. However, processing a large amount of AE data using traditional analysis methods is time-consuming. Therefore, integrating machine learning (ML) techniques into this process offers a more logical and effective solution to expedite data analysis and enhance damage detection accuracy. This study aims to train an ML model for detecting corrosion damage in reinforced concrete structures using an AE dataset. In pursuit of this goal, it seeks to enhance source localization that contributes to identifying crack patterns through signal-based analysis methods. AE data obtained from a reinforced concrete structural element subjected to accelerated corrosion testing in laboratory conditions have undergone detailed analyses with the ML model. In this context, an ML model capable of learning signals with various wave characteristics and parameters has been successfully integrated into the source localization algorithm, significantly improving AE source localization outcomes. Furthermore, this method is critical for structural safety as it enables the early detection of reinforcement corrosion and precise localization of cracks. The integration of this machine learning model with AE data serves as a valuable tool developed for more effective monitoring of damage in structures.