Search Results (91)

This study employs a deep learning-based object detection model, GoogleNet, to identify cracks in cultural heritage images. Subsequently, a semantic segmentation model, SegNet, is utilized to determine the location and extent of the cracks. To establish a scale ratio between image pixels and real-world dimensions, a parallel laser-based measurement approach is applied, enabling precise crack length calculations. The results indicate that the percentage error between crack lengths estimated using deep learning and those measured with a caliper is approximately 3%, demonstrating the feasibility and reliability of the proposed method. Additionally, the study examines the impact of iteration count, image quantity, and image category on the performance of GoogleNet and SegNet. While increasing the number of iterations significantly improves the models’ learning performance in the early stages, excessive iterations lead to overfitting. The optimal performance for GoogleNet was achieved at 75 iterations, whereas SegNet reached its best performance after 45,000 iterations. Similarly, while expanding the training dataset enhances model generalization, an excessive number of images may also contribute to overfitting. GoogleNet exhibited optimal performance with a training set of 66 images, while SegNet achieved the best segmentation accuracy when trained with 300 images. Furthermore, the study investigates the effect of different crack image categories by classifying datasets into four groups: general cracks, plain wall cracks, mottled wall cracks, and brick wall cracks. The findings reveal that training GoogleNet and SegNet with general crack images yielded the highest model performance, whereas training with a single crack category substantially reduced generalization capability. Full article

Aging port infrastructure demands frequent and reliable inspections, yet the existing automated systems often require expensive industrial drones, posing significant adoption barriers for local governments with limited resources. To address this challenge, this study develops a low-cost, automated crack detection system for port quay walls utilizing orthophotos generated from a small general-purpose drone. The system employs the YOLOR (You Only Learn One Representation) object detection algorithm, enhanced by two novel image processing techniques—overlapping tiling and pseudo-altitude slicing—to overcome the resolution limitations of low-cost cameras. While official guidelines for port facilities designate 3 mm as an inspection threshold, our system is specifically designed to achieve a higher-resolution detection capability for cracks as narrow as 1 mm. This approach ensures reliable detection with a sufficient safety margin and enables the proactive monitoring of crack progression for preventive maintenance. The effectiveness of the proposed image processing techniques was validated, with an F₁ score-based analysis revealing key trade-offs between maximizing detection recall and achieving a balanced performance depending on the chosen simulated altitude. Furthermore, evaluation using real-world inspection data demonstrated that the proposed system achieves a detection performance comparable to that of a well-established commercial system, confirming its practical applicability. Crucially, by mapping the detected cracks to real-world coordinates on georeferenced orthophotos, the system provides a foundation for advanced, data-driven asset management, allowing for the quantitative tracking of deterioration over time. These results confirm that the proposed workflow is a practical and sustainable solution for infrastructure monitoring. Full article

In order to determine the failure reason for the non-working area of a cracked A-pillar hot-stamping die insert, various instruments were used to detect the properties and microstructures of the cracks and matrix. The results show that the cracks are located in the area where the oxidative corrosion is more serious, and the cracks do not appear in the pitting area, verifying that crack initiation is related to the stress concentration on the upper half of the inner wall of the cooling channel. Meanwhile, pores and cracks exist in the grain boundary and crystal, making the impact energy of the die steel poor. Therefore, crack initiation and propagation easily occur along the brittle oxide layer. In summary, the die insert is damaged by stress-induced corrosion. In engineering applications of hot-stamping dies, we should pay more attention to the cracking of the cooling channel caused by stress and corrosion. Full article

The historical Lingnan gray brick buildings in Macau, a World Heritage Site, are facing severe deterioration due to prolonged disrepair, manifesting as cracks, breakages, moss adhesion, and other types of surface damage. These issues threaten not only the structural stability of the buildings but also the conservation of cultural heritage. To address the inefficiencies and low accuracy of traditional manual inspections, this study proposes an automated recognition and quantitative detection method for wall surface damage based on the YOLOv8 deep learning object detection model. A dataset comprising 375 annotated images collected from 162 gray brick historical buildings in Macau was constructed, covering eight damage categories: crack, damage, missing, vandalism, moss, stain, plant, and intact. The model was trained and validated using a stratified sampling approach to maintain a balanced class distribution, and its performance was comprehensively evaluated through metrics such as the mean average precision (mAP), F1 score, and confusion matrices. The results indicate that the best-performing model (Model 3 at the 297th epoch) achieved a mAP of 61.51% and an F1 score up to 0.74 on the test set, with superior detection accuracy and stability. Heatmap analysis demonstrated the model’s ability to accurately focus on damaged regions in close-range images, while damage quantification tests showed high consistency with manual assessments, confirming the model’s practical viability. Furthermore, a portable, integrated device embedding the trained YOLOv8 model was developed and successfully deployed in real-world scenarios, enabling real-time damage detection and reporting. This study highlights the potential of deep learning technology for enhancing the efficiency and reliability of architectural heritage protection and provides a foundation for future research involving larger datasets and more refined classification strategies. Full article

Deep learning has made remarkable progress in the field of crack segmentation, particularly in handling large-scale datasets and complex images, owing to the substantial computational power currently available. However, existing methods still face significant challenges when processing images with low contrast, fine cracks, or strong noise interference. This paper introduces a novel semantic diffusion model capable of generating synthetic crack images from segmentation masks. The proposed model outperforms state-of-the-art semantic synthesis models across multiple benchmark datasets, demonstrating enhanced crack segmentation performance in complex backgrounds and addressing a critical challenge in engineering crack detection. Additionally, a new crack width calculation method is proposed, which further optimizes the measurement accuracy of crack width by leveraging the medial axis of the segmentation mask, thereby improving the model’s ability to describe crack morphology. To comprehensively evaluate the model’s performance, the dataset was categorized, and a detailed analysis of crack width errors was conducted for different regions. Specifically, the median and interquartile range (IQR) of width errors were calculated for four distinct regions: the central wall, corner edges, oblique intersections, and wall and column surfaces. Experimental results demonstrate that the proposed model excels in all regions, particularly in complex areas such as corner edges and oblique intersections, where the error is significantly lower than that of existing methods. These innovations collectively advance crack segmentation technology and provide a new solution for efficient crack detection in practical applications. Full article

Damage assessment methods fall into contact and non-contact approaches. Contact methods, like physical measurements, material sampling, and ultrasonic testing, provide detailed data but are time-consuming and require specialized equipment. In contrast, non-contact methods assess damage remotely, allowing for faster, safer, and large-scale evaluations, especially useful in post-disaster scenarios. However, there are currently no standardized non-contact methods for assessing damage levels in confined masonry walls after damaging seismic events in Peru. On the other hand, an experimental database of cyclic loading tests on confined masonry walls is available, supporting numerical simulations with calibrated mathematical models to estimate damage levels. This research extends the application of this database by analyzing the crack pattern imagery from the tested walls and correlating it with the lateral deformation (drift) to identify the damage levels. A high-accuracy crack measurement technique was developed, combining a convolutional neural network to generate a binary crack mask and a binary search algorithm to extract polylines and convert them into length measurements, achieving a detection accuracy of 78%. The measured crack patterns were normalized into an index, which was then correlated with the amplitude of the lateral deformation in each hysteretic loop. Finally, a relationship was established between drift and the damage level index. These findings contribute to the development of a rapid, non-contact damage assessment method for confined masonry walls in seismic-prone regions. Full article

The article presents research on the application of computed tomography with an incomplete dataset to the problem of examining the internal structure of walls. The case of incomplete information in computed tomography often occurs in various applications, e.g., when examining large objects or when examining hard-to-reach objects. Algorithms dedicated to this type of problem can be used to detect anomalies (defects, cracks) in the walls, among other artifacts. Situations of this type may occur, for example, in old buildings, where special caution should be exercised. The approach presented in the article consists of a non-standard solution to the problem of reconstructing the internal structure of the tested object. The classical approach involves constructing an appropriate system of equations based on X-rays, the solution of which describes the structure. However, this approach has a drawback: solving such systems of equations is computationally very complex, because the algorithms used, combined with incomplete information, converge very slowly. In this article, we propose a different approach that eliminates this problem. To simulate the structure of the tested object, we use a hybrid algorithm that is a combination of a metaheuristic optimization algorithm (Group Teaching Optimization Algorithm) and a numerical optimization method (Hook-Jeeves method). In order to solve the considered inverse problem, a functional measuring the fit of the model to the measurement data is created. The hybrid algorithm presented in this paper was used to find the minimum of this functional. This paper also shows computational examples illustrating the effectiveness of the algorithms. Full article

The infrastructure construction of bridges is growing rapidly, and the quality of concrete structures is becoming increasingly stringent. However, the issue of cracks in concrete structures remains prominent. In on-site bridge crack detection, the traditional crack identification techniques fail to meet demands due to their inefficiency, inaccuracy, and the challenges posed by high-altitude conditions. In response to this, this paper proposes a bridge crack multi-task integration algorithm based on YOLOv8 object detection and DeepLabv3+ semantic segmentation. This integrated approach offers advantages such as high precision and low inference time. Testing wall cracks using this method, compared to the original approach, resulted in a 10.18% improvement in IOU and a 9.64% improvement in the F1 score. Regarding the detection model, it was deployed on edge computing devices. By applying the TensorRT inference acceleration framework, the camera FPS increased to 9.66, a 59.97% improvement compared to the version without the acceleration framework. This enabled accurate, real-time bridge crack detection on the edge computing devices. Furthermore, the edge computing device was also applied in a self-developed drone, which was tested on-site at the Donghai Bridge, providing a new solution for safe and reliable structural inspection. Full article

This study proposes a cyber–physical framework for the integration of a heterogeneous swarm of robots, sensors, microrobots, and AR for structural health monitoring and confined space inspection based on the application’s unique challenges. The structural issues investigated are cracks in the walls, deformation of the structures, and damage to the culverts and devices commonly used in buildings. The PC and augmented reality interfaces are incorporated for human–robot collaboration to provide the necessary information to the human user while teleoperating the robots. The proposed interfaces use edge computing and machine learning to enhance operator interactions and to improve damage detection in confined spaces and challenging environments. The proposed swarm inspection framework is called HeSARIC. Full article

The diaphragm wall plays an important role in the safe construction of foundation pits, and it is crucial to accurately monitor its deformation in real time. Traditional monitoring methods often face challenges in achieving distributed monitoring, and the cost of using fiber optic sensors for real-time and distributed monitoring can be prohibitively high. To improve the monitoring efficiency and accuracy of the deep deformation of the diaphragm wall, this paper proposes a hybrid monitoring method that combines ultra-weak fiber Bragg grating (UWFBG) technology and traditional FBG sensors. This distributed–discrete optical fiber monitoring approach allows for continuous, high-resolution data collection along the diaphragm wall while providing targeted, real-time measurements at critical locations. Fiber optic crack testing of concrete beam structures was carried out to verify the method of evaluating the health status of structures using distributed fiber optic data. An engineering case study was developed to validate the feasibility of this method. The results demonstrated that the hybrid approach effectively captures the overall deformation distribution of the diaphragm wall while enabling real-time monitoring of key areas, including the detection of crack initiation and propagation. The proposed method offers a significant advancement in deformation monitoring, providing enhanced accuracy, spatial coverage, and the ability to detect both macro-scale trends and micro-scale anomalies, which is particularly beneficial for complex underground structures. Full article

Recently, artificial intelligence (AI) has been adopted in a number of Internet of Things (IoT) application systems to enhance intelligence. We have developed a ready-made server with rich built-in functions to collect, process, display, analyze, and store data from various IoT devices, the SEMAR (Smart Environmental Monitoring and Analytics in Real-Time) IoT application server platform, in which various AI techniques have been implemented to enhance its capabilities. In this paper, we present an application of SEMAR to a drone-based wall inspection system using an object detection AI model called You Only Look Once (YOLO). This system aims to detect wall cracks at high places using images taken via a camera on a flying drone. An edge computing device is installed to control the drone, sending the taken images through the Kafka system, storing them with the drone flight data, and sending the data to SEMAR. The images are analyzed via YOLO through SEMAR. For evaluations, we implemented the system using Ryze Tello for the drone and Raspberry Pi for the edge, and we evaluated the detection accuracy. The preliminary experiment results confirmed the effectiveness of the proposal. Full article

After rolling, TP2 copper tubes exhibit defects such as sawtooth marks, cracks, and uneven wall thickness after joint drawing, which severely affects the quality of the finished copper tubes. To study the effect of drawing process parameters on wall thickness uniformity, an ultrasonic detection platform for measuring the wall thickness of rolled copper tubes was constructed to verify the accuracy of the experimental equipment. Using the detected data, a finite element model of drawn copper tubes was established, and numerical simulation studies were conducted to analyze the influence of parameters such as outer die taper angle, drawing speed, and friction coefficient on drawing force, maximum temperature, average wall thickness, and wall thickness uniformity. To address the problem of the large number of finite element model meshes and low solution efficiency, the wall thickness uniformity was predicted using a radial basis function (RBF) neural network, and parameter optimization was performed using the particle swarm optimization (PSO) algorithm. The research results show that the RBF neural network can accurately predict wall thickness uniformity, and using the PSO optimization algorithm, the best parameter combination can reduce the wall thickness uniformity after drawing in finite element simulation. Full article

At present, researchers in the field of pipeline inspection focus on pipe wall defects while neglecting pipeline defects in special situations such as welds. This poses a threat to the safe operation of projects. In this paper, a multi-node fusion and modal projection algorithm of steel pipes based on guided wave technology is proposed. Through an ANSYS numerical simulation, research is conducted to achieve the identification, localization, and quantification of axial cracks on the surface of straight pipelines and internal cracks in circumferential welds. The propagation characteristics and vibration law of ultrasonic guided waves are theoretically solved by the semi-analytical finite element method in the pipeline. The model section is discretized in one-dimensional polar coordinates to obtain the dispersion curve of the steel pipe. The T(0,1) mode, which is modulated by the Hanning window, is selected to simulate the axial crack of the pipeline and the L(0,2) mode to simulate the crack in the weld, and the correctness of the dispersion curve is verified. The results show that the T(0,1) and L(0,2) modes are successfully excited, and they are sensitive to axial and circumferential cracks. The time–frequency diagram of wavelet transform and the time domain diagram of the crack signal of Hilbert transform are used to identify the echo signal. The first wave packet peak point and group velocity are used to locate the crack. The pure signal of the crack is extracted from the simulation data, and the variation law between the reflection coefficient and the circumferential and radial dimensions of the defect is calculated to evaluate the size of the defect. This provides a new and feasible method for steel pipe defect detection. Full article

Cracks represent one of the most common types of damage in building structures and it is crucial to detect cracks in a timely manner to maintain the safety of the buildings. In general, tiny cracks require focusing on local detail information while complex long cracks and cracks similar to the background require more global features for detection. Therefore, it is necessary for crack detection to effectively integrate local and global information. Focusing on this, a local–global feature adaptive fusion network (LGFAF-Net) is proposed. Specifically, we introduce the VMamba encoder as the global feature extraction branch to capture global long-range dependencies. To enhance the ability of the network to acquire detailed information, the residual network is added as another local feature extraction branch, forming a dual-encoding network to enhance the performance of crack detection. In addition, a multi-feature adaptive fusion (MFAF) module is proposed to integrate local and global features from different branches and facilitate representative feature learning. Furthermore, we propose a building exterior wall crack dataset (BEWC) captured by unmanned aerial vehicles (UAVs) to evaluate the performance of the proposed method used to identify wall cracks. Other widely used public crack datasets are also utilized to verify the generalization of the method. Extensive experiments performed on three crack datasets demonstrate the effectiveness and superiority of the proposed method. Full article

Cracks pose a critical challenge in the preservation of historical buildings worldwide, particularly in fair-faced walls, where timely and accurate detection is essential to prevent further degradation. Traditional image processing methods have proven inadequate for effectively detecting building cracks. Despite global advancements in deep learning, crack detection under diverse environmental and lighting conditions remains a significant technical hurdle, as highlighted by recent international studies. To address this challenge, we propose an enhanced crack detection algorithm, CL-YOLOv8 (ConvNeXt V2-LSKA-YOLOv8). By integrating the well-established ConvNeXt V2 model as the backbone network into YOLOv8, the algorithm benefits from advanced feature extraction techniques, leading to a superior detection accuracy. This choice leverages ConvNeXt V2’s recognized strengths, providing a robust foundation for improving the overall model performance. Additionally, by introducing the LSKA (Large Separable Kernel Attention) mechanism into the SPPF structure, the feature receptive field is enlarged and feature correlations are strengthened, further enhancing crack detection accuracy in diverse environments. This study also contributes to the field by significantly expanding the dataset for fair-faced wall crack detection, increasing its size sevenfold through data augmentation and the inclusion of additional data. Our experimental results demonstrate that CL-YOLOv8 outperforms mainstream algorithms such as Faster R-CNN, YOLOv5s, YOLOv7-tiny, SSD, and various YOLOv8n/s/m/l/x models. CL-YOLOv8 achieves an accuracy of 85.3%, a recall rate of 83.2%, and a mean average precision (mAP) of 83.7%. Compared to the YOLOv8n base model, CL-YOLOv8 shows improvements of 0.9%, 2.3%, and 3.9% in accuracy, recall rate, and mAP, respectively. These results underscore the effectiveness and superiority of CL-YOLOv8 in crack detection, positioning it as a valuable tool in the global effort to preserve architectural heritage. Full article