Detection Of Defects In Structures Research Articles

IoT-Machine Learning-Based Structural Health Monitoring System for Detection of Cracks in Bridges

The deteriorating condition of infrastructure, particularly bridges, poses significant challenges to public safety and necessitates the development of advanced monitoring systems for early detection of structural defects. This paper proposes a novel approach by integrating Internet of Things (IoT) technology with machine learning (ML) algorithms for real-time structural health monitoring, focusing on the detection of cracks in bridges. The proposed system employs a network of IoT sensors strategically deployed on the bridge structure to collect diverse data related to environmental conditions, strain, and vibrations. These sensors provide a continuous stream of data, creating a comprehensive dataset for analysis. Machine learning algorithms, specifically designed for anomaly detection, are applied to this dataset to identify patterns indicative of potential structural issues. This system is designed and implemented using ML and IoT. The excitation results shows that the designed system accuracy and efficiency of crack detection is improved and further enhance overall structural resilience. Furthermore, the integration of a real-time alerting mechanism allows for immediate notification of detected anomalies.

Degradation monitoring of multilayer ceramic capacitors during high accelerated lifetime testing using ultrasound

Multilayer ceramic capacitors (MLCCs) are vital circuitry components where long-term stability at high temperature and fields is critical to device operation. High accelerated lifetime testing (HALT) statistically investigates reliability and lifetime of MLCCs through exposure to temperatures and voltages exceeding normal operating conditions. The long-term reliability of the dielectric layers in MLCCs strongly depends on potential variability in the dielectric microstructure, such as cracking, which can be challenging to detect. Nondestructive ultrasonic evaluation is sensitive to microstructural changes through measurements of wave scattering. This work uses high frequency (100 MHz) focused ultrasonic scattering methods to nondestructively monitor structural and microstructural changes in MLCCs from the pristine to the failed state during HALT to understand structural origins of electrical failure. Printed circuit board mounted MLCCs were electrically and ultrasonically characterized in a pristine state and during various degraded states before and after electrical failure under HALT. Evidence of damage pre-HALT was ultrasonically indicated by high attenuation regions on the ultrasonic maps suggesting that the mounting process may induce damage. The high attenuation regions in the pristine samples evolved throughout HALT indicating that the damage in the pristine state might be the spatial origin of part failure, which underscores the impact and importance of detection of structural defects on the reliability of MLCCs.

Deep Learning Architecture for Computer Vision-based Structural Defect Detection

Deep Learning Architecture for Computer Vision-based Structural Defect Detection

Mechanical Structure Defect Detection after High Temperature Based on Image Processing

Mechanical Structure Defect Detection after High Temperature Based on Image Processing

Thermal integrity profiling of cast-in-situ piles in sand using fiber-optic distributed temperature sensing

Defects in cast-in-situ piles have an adverse impact on load transfer at the pile‒soil interface and pile bearing capacity. In recent years, thermal integrity profiling (TIP) has been developed to measure temperature profiles of cast-in-situ piles, enabling the detection of structural defects or anomalies at the early stage of construction. However, using this integrity testing method to evaluate potential defects in cast-in-situ piles requires a comprehensive understanding of the mechanism of hydration heat transfer from piles to surrounding soils. In this study, small-scale model tests were conducted in laboratory to investigate the performance of TIP in detecting pile integrity. Fiber-optic distributed temperature sensing (DTS) technology was used to monitor detailed temperature variations along model piles in sand. Additionally, sensors were installed in sand to measure water content and matric suction. An interpretation method against available DTS-based thermal profiles was proposed to reveal the potential defective regions. It shows that the temperature difference between normal and defective piles is more obvious in wet sand. In addition, there is a critical zone of water migration in sand due to the water absorption behavior of cement and temperature transfer-induced water migration in the early-age concrete setting. These findings could provide important insight into the improvement of the TIP testing method for field applications.

UAS IR-Thermograms Processing and Photogrammetry of Thermal Images for the Inspection of Building Envelopes

Infrared thermography techniques (IRT) are increasingly being applied in non-invasive structural defect detection and building inspection, as they provide accurate surface temperature (ST) and ST contrast (Delta-T) information. The common optional or off-the-shelf installation, of both low- and high-resolution thermal cameras, on commercial UAS further facilitates the application of IRT by enabling aerial imaging for building envelope surveys. The software used in photogrammetry is currently accurate and easy to use. The increasing computational capacity of the hardware allows three-dimensional models to be obtained from conventional photography, thermal, or even multispectral imagery with very short processing times, further improving the possibilities of analysing buildings and structures. Therefore, in this study, which is an extension of a previous work, the analysis of the envelope of a wine cellar, using manual thermal cameras, as well as cameras installed on board an Unmanned Aerial System (UAS), will be presented. Since the resolution of thermal images is much lower than that of conventional photography, and their nature does not allow for accurate representation of three-dimensional objects, a new, but simple, digital image pre-processing method will be presented to provide a more detailed 3D model. Then, the three-dimensional reconstruction, based on thermal imagery, of the building envelope will be performed and analysed. The limitations of each technique will be also detailed, together with the anomalies found and the proposed improvements.

Promoting intense mechanoluminescence by strengthening C-H⋯π interactions in thioxanthene derivatives

Pure organic mechanoluminescent (ML) materials are a kind of new environmentally friendly material that can be mechanically stimulated by external force, which has the potential to apply in stress imaging, health monitoring and structural defect detection. However, the mechanism of ML process in organic materials is still unclear and the molecular designing strategies for these materials remain insufficient. Herein, through simply strengthening intermolecular C-H⋯π interactions in the ML-inactive thioxanthene derivatives TxPh, the thiophene modified compound TxPhTh showed bright ML. The stronger C-H⋯π interactions suppressed the nonradiative transition channels during the ML process, and also boosted the photoluminescence quantum yield (PLQY) of crystalline TxPhTh. In addition, the molecular arrangements were switched from centrosymmetric (TxPh) to non-centrosymmetric (TxPhTh). Photophysical studies, detailed single-crystal and TD-DFT calculations were performed. These results provided a new path for designing ML materials and promoted the investigation of ML mechanism.

Theoretical and experimental investigations on control parameters of piezo-based vibro-acoustic modulation health monitoring of contact acoustic nonlinearity in a sandwich beam

Contact-type defects are prevalent in composite constructions and sandwich panels due to failure mechanisms such as bolt loosening and delamination. Contact acoustic nonlinearity is a manifestation of such defects that nonlinear health monitoring systems can detect. Vibro-acoustic modulation (VAM) is a well-established technique for the early detection of nonlinear defects in structures. It employs bi-tone excitation to reveal damage-induced nonlinearity, which results in the appearance of sidebands in the response spectrum. The objective of this research is to use PZT-based excitation to monitor bolt loosening in a sandwich beam in real-time. To address the limited capacity of the PZT transducers to excite the nonlinear mechanism, a sensitivity analysis (SA) for input factors of VAM testing was conducted to improve damage detection using the results. The Morris approach is used to investigate the sensitivity of VAM damage metrics derived analytically in the frequency domain. To reduce the number of tests required for the experimental SA, the response surface methodology (RSM) is applied. The analysis of variance and Fischer's statistics are used to calculate the SA of experimental damage indices. In RSM computations, the discrete influence of excitation frequencies on the modulation sidebands is addressed. For reliable SA of experimental results, the effect of background noise is taken into account. The findings of this study may be applied to the selection of appropriate damage metrics in real-world applications of VAM health monitoring systems, as well as the effective tuning of input control parameters to maximize damage detectability.

Intelligent Structural Defect Reconstruction Using the Fusion of Multi-Frequency and Multi-Mode Acoustic Data

Quantitative detection of defects in structures is always a hot research topic in the field of guided wave inverse scattering. Research studies on how to effectively extract the defect-related information encompassed in the multi-frequency and multi-modes scattered wave signals for reconstructions of defects have been paid attention in recent decades. In this paper, a novel deep learning-based quantitative guided wave inverse scattering technique has been proposed to intelligently realize the end-to-end mapping of the multi-frequency, multi-modes scattered signals to defect profiles with high levels of accuracy and efficiency. Based on the manifold distribution principle, the data patterns of scattered SH-wave signals have been investigated, owing to leveraging the capability of the intelligent encoder-projection-decoder neural network. Following that, the manifold-learning oriented network has been trained using the data generated by the modified boundary element method. Several numerical examples have been examined to demonstrate the correctness and efficiency of the proposed reconstruction approach. It has been concluded that this novel data-driven technique intelligently enables the high-quality solution to inverse scattering problems and provides a valuable insight into the development of practical approaches to quantitative detection using multi-frequency and multi-modal acoustic data from scattered ultrasonic guided waves.

Structural Defect Detection Technology of Transmission Line Damper Based on UAV Image

Overhead transmission lines suffer from extended exposure to harsh weather conditions. Metal dampers, a crucial protective fitting in the line, can effectively suppress the conductor’s vibration energy and prevent Aeolian vibration and ice shedding. To ensure the safety of operation of the damper, we are proposing a detection method for structural defect damper based on spatial relationship. First, the unmanned aerial vehicle (UAV) aerial damper images are processed with relative total variation (RTV) transform to obtain an enhanced image with a smooth texture and prominent foreground main structure. Second, the enhanced image is corrected by rotation so that the conductor remains horizontal. Next, based on the endpoint coordinates of the conductor, a foreground preselection box for improved GrabCut segmentation is automatically generated to extract the object dampers. Finally, the spatial relationship between the damper components in the segmentation results is regarded as the motive force of the damper structural defect diagnosis model to detect damage, inversion, slight, and serious deformation defects in sequence. We analyzed the performance of the proposed method through actual field tests, and the results demonstrated that the identification accuracy of the method is 95.76% when applied to a small sample set, which is higher than other existing methods based on traditional image techniques and deep learning defect detection, and can effectively identify different structural defects of dampers and provide reliable data for transmission line condition monitoring.

An Inventive Method to Fabric Part Structural Defect Detection Using Frame Harmonizing

Using a frame harmonizing based approach, this paper examines paper defects. In the textiles industry, the quick cutting and sewing of fabric has resulted in a lot of small mistakes, making this task extremely difficult. Especially these deformities won't be quickly recognized by specialists as well as programming. A novel frame harmonizing method is used in our system to find flaws in the fabric production process. Transformation and filtering techniques are used for the inputted fabric image frame. The conventional outline extraction method Berkeley edge detector is used to extract the edge map. Contour-based features are extracted and classified by K-Nearest Neighbour (KNN) classifier. The experimentation with real-time data set produced the outstanding performance results when compared with state of the art methods.

SDNET2021: Annotated NDE Dataset for Subsurface Structural Defects Detection in Concrete Bridge Decks

Annotated datasets play a significant role in developing advanced Artificial Intelligence (AI) models that can detect bridge structure defects autonomously. Most defect datasets contain visual images of surface defects; however, subsurface defect data such as delamination which are critical for effective bridge deck evaluations are typically rare or limited to laboratory specimens. Three Non-Destructive Evaluation (NDE) methods (Infrared Thermography (IRT), Impact Echo (IE), and Ground Penetrating Radar (GPR)) were used for concrete delamination detection and reinforcement corrosion detection. The authors have developed a unique NDE dataset, Structural Defect Network 2021 (SDNET2021), which consists of IRT, IE, and GPR data collected from five in-service reinforced concrete bridge decks. A delamination survey map locating the areas, extent and classes of delamination served as the ground truth for annotating IRT, IE and GPR field tests’ data in this study. The IRT were processed to create an ortho-mosaic maps for each deck and were aligned with the ground truth maps using image registration, affine transformation, image binarization, morphological operations, connected components and region props techniques to execute a semi-automatic pixel–wise annotation. Conventional methods such as Fast Fourier transform (FFT)/peak frequency and B-Scan were used for preliminary analysis for the IE and GPR signal data respectively. The quality of NDE data was verified using conventional Image Quality Assessment (IQA) techniques. SDNET2021 dataset consists of 557 delaminated and 1379 sound IE signals, 214,943 delaminated and 448,159 sound GPR signals, and about 1,718,083 delaminated and 2,862,597 sound IRT pixels. SDNET2021 addresses one of the major gaps in benchmarking, developing, training, and testing advanced deep learning models for concrete bridge evaluation by providing a publicly available annotated and validated NDE dataset.

Vibration-based and computer vision-aided nondestructive health condition evaluation of rail track structures

In railway engineering, monitoring the health condition of rail track structures is crucial to prevent abnormal vibration issues of the wheel–rail system. To address the problem of low efficiency of traditional nondestructive testing methods, this work investigates the feasibility of the computer vision-aided health condition monitoring approach for track structures based on vibration signals. The proposed method eliminates the tedious and complicated data pre-processing including signal mapping and noise reduction, which can achieve robust signal description using numerous redundant features. First, the method converts the raw wheel–rail vibration signals directly into two-dimensional grayscale images, followed by image feature extraction using the FAST-Unoriented-SIFT algorithm. Subsequently, Visual Bag-of-Words (VBoW) model is established based on the image features, where the optimal parameter selection analysis is implemented based on fourfold cross-validation by considering both recognition accuracy and stability. Finally, the Euclidean distance between word frequency vectors of testing set and the codebook vectors of training set is compared to recognize the health condition of track structures. For the three health conditions of track structures analyzed in this paper, the overall recognition rate could reach 96.7%. The results demonstrate that the proposed method performs higher recognition accuracy and lower bias with strong time-varying and random vibration signals, which has promising application prospect in early-stage structural defect detection.

A defect detection method for topological phononic materials based on few-shot learning

Topological phononic materials have been widely used in many fields, such as topological antennas, asymmetric waveguides, and noise insulation. However, due to the limitations of the manufacturing process, topological protection is vulnerable to some severe defects that may affect the application effect. Therefore, the quality inspection of topological materials is essential to ensure reliable results. Due to the low contrast and irregularity of defects and the similarity of topological phononics, they are difficult to recognize by traditional image processing algorithms, so manual detection is still mainstream at present. But manual detection requires experienced inspectors, which is expensive and time-consuming. In addition, topological materials are expensive to produce, and there is no large publicly available dataset, but deep learning usually relies on large datasets for training. To solve the above problems, we propose an automatic deep learning topology structure defect detection method (ADLTSDM) in this work, which could classify not only the structure of topological materials but also detect the defects of topological phononics based on a small dataset. ADLTSDM exploits the prior knowledge of the topological material structure and achieves an augmentation factor of more than 100 times through the random and fixed interval screenshot algorithm, thus enabling the training of deep neural networks with only two raw data. For defect detection, ADLTSDM has an accuracy of more than 97% and improves detection speed by more than 38% compared with manual detection. For structure classification, ADLTSDM can achieve an accuracy of over 99% and seven times faster speed compared with manual classification. Besides, the detection standard of ADLTSDM is unified, so the accuracy will not be affected by the experience of the inspectors, which has more potential in high-throughput industrial applications.

Multiple structural defect detection for reinforced concrete buildings using YOLOv5s

Building inspection and maintenance are becoming increasingly essential means by which to consider the deterioration problems of old, reinforced concrete (RC) buildings. While such inspection work can be conducted with the aid of computer vision-based technology, this technology remains challenged, since real-world structural defects and environmental conditions are varied and complex. In recent years, object detection algorithms have improved to achieve greater speed and accuracy with the help of deep learning. In this paper, an advanced object detector, YOLOv5s, was successfully applied to the recognition of common structural defects including cracks, delamination, exposed reinforcement, rust stains, spalling, tile cracks, tile delamination, and tile loss. Compared with the other advanced object detectors of YOLO (i.e., YOLOv5m, YOLOv5l, YOLOv5x, YOLOv4, and YOLOv3) based on the built data set, the YOLOv5s algorithm shows an obvious advantage for defect detection, achieving 64.5% and 67.0% mean average precision (mAP) for training and testing, respectively. It also takes less than 0.1 seconds to detect a defect on an image. The lightweight and high detection performance of the YOLOv5s algorithm shows great promise for potential deployment on an onboard inspection device, such as an unmanned aerial vehicle (UAV) or a robot, to achieve real-time structural inspection.

A review on pavement distress and structural defects detection and quantification technologies using imaging approaches

Pavement distress detection (PDD) plays a vital role in planning timely pavement maintenance that improves pavement service life. In order to promote the development of PDD technologies and find out the insufficiencies in PDD field, this paper reviews the technical development history and characteristics of various PDD technologies, which contributes to the current state of research on PDD. First, processes of PDD are briefly introduced. The PDD technologies based on radar ranging, 2D image, laser ranging and 3D structured light are illustrated. The newest 3D PDD technology based on interference fringe, which has better accuracy, is in progress. The principles and implementation processes of these methods are discussed. Finally, the shortcomings of these technologies in the field of PDD are concluded. Recommendations for future development are provided. The research results show that various PDD technologies have been continuously improved, developed, over the past decade, and have achieved a series of results. However, the measurements from existing PDD technologies can not be metrological traced to acquire the true dimensions of pavement distresses. The lack of metrological traceability technology in the PDD field needs to be further solved. In order to achieve more accurate and efficient PDD, the metrological traceability technology of PDD systems has become the future development direction in this field.

High gain metamaterial loaded antipodal tapered slot antenna over 20–40 GHz for imaging applications

We propose a novel high gain antipodal tapered slot antenna over 20–40 GHz for high resolution imaging applications. We design the radiating fins of the antenna as elliptical and circular shape for inner and outer tapers respectively. We incorporate isosceles trapezoid-shaped dielectric lens in the antenna and load it with an anisotropic left-handed metamaterial unit cells to obtain high gain and stable radiation pattern. The antenna is printed on RT/Duroid 5880 substrate and occupies a volume of 30 × 55 × 0.254 mm3. The measured results show good agreement with the simulation results over 20–40 GHz. The proposed antenna has a compact size and exhibits improved gain and stable radiation pattern as compared to the other state-of-the-art designs. We demonstrate the suitability of the proposed antenna for imaging applications such as concealed weapon detection and detection of defects in structures using simulation-based case studies. The retrieved images show that the proposed antenna can be used effectively for high resolution imaging applications.

Wave mixing with the fundamental mode of edge waves for evaluation of material nonlinearities

The measurement of material and geometric nonlinearities is of great interest as these nonlinearities can be linked to mechanical damage and applied stress. Current experimental techniques often utilise the growth rate of the second or mixed harmonics of bulk, Rayleigh, or Lamb waves in the ultrasonic range to conduct measurements. However, there are many challenges in obtaining the nonlinearities from experimental data as all these waves experience spatial or/and frequency dispersion. This paper focuses on the application of the fundamental mode of edge waves (ES0), which is a natural analogue of Rayleigh waves, for the measurement of material nonlinearity. The ES0 wave mode (as well as other modes of edge waves) is guided by the edge of a plate, and it is therefore spatially nondispersive and not affected by the interior of the structure. These features can be important for practical implementations e.g. for the evaluation of fatigue damage and detection of structural defects, which typically initiate from free surfaces. However, this wave mode is weakly dispersive in the frequency domain and has a significant energy decay at high frequencies. Among the outcomes of this paper are the experimental generation of higher order and mixed harmonics with the fundamental mode of edge waves, as well as the evaluation of material nonlinearity. The latter is shown to be independent of the frequency and type of harmonic used.

Effect of mechanical properties and geometric dimensions on electromechanical impedance signatures for adhesive joint integrity monitoring

Adhesive joints are prone to damage, which may be difficult to detect using Nondestructive Test. Structural Health Monitoring techniques, such as the Electromechanical Impedance Spectroscopy (EMIS), allow for continuous monitoring and early detection of structural defects. Developing efficient damage detection algorithms requires simulations of adhesive structures, which require elastic and damping properties under high frequency range. Tests were performed for crash-resistant and silicone adhesives. Numerical simulations with said properties were compared with experimental impedance measurements from Single Lap Joints (SLJ). This allowed for the estimation of adhesive properties, but numerical results for SLJs with silicone adhesive diverged from experimental results.

Tactile-Based Fabric Defect Detection Using Convolutional Neural Network With Attention Mechanism

This paper proposes a fabric structure defect detection method based on the vision-based tactile sensor. The result will be robust by using the tactile sensor regardless of dyeing patterns which can influence the result if some other sensors are used, e.g., vision perception. It also reduces the influence of ambient light on defect detection. Therefore, the proposed method can be more robust and universal than conventional visual methods. A robotic arm equipped with the tactile sensors was used to automate and standardize the data collection process and construct fabric datasets. In addition, a convolutional neural network integrated with attention mechanism in the channel domain was developed to detect fabric types. The proposed network employed frequency domain filtering to remove or weaken the influence of normal fabric texture information to improve defect detection efficiency and accuracy. Finally several experiments were conducted to demonstrate the proposed method’s superiority to a visual defect detection method for detecting structural defects. In addition, the efficiency of the proposed method is evaluated. Experimental results show that the proposed method is feasible and efficient to meet the real-world detection requirements.