Practical Inspection Research Articles

Exploring the Effects of Attention Mechanisms on Road Crack Detection and Classification

Pavement cracks are a prevalent form of roadway distress that pose significant safety hazards, necessitating prompt detection and repair. Due to the extensive road network, traditional image processing-based crack detection methods exhibit limitations in recognition accuracy and speed. To address these challenges, this paper proposes an efficient pavement crack detection model based on YOLOv8, termed YOLOv8-ACD (YOLOv8 - Attention for Cracks Detecting), which integrates a global attention mechanism. YOLOv8-ACD enhances detection efficiency and accuracy by focusing on crack identification while filtering out most irrelevant information. We evaluated YOLOv8-ACD on the RDD2022 dataset, and experimental results demonstrate significant improvements in key performance metrics, such as F1-Score and mean Average Precision (mAP), compared to the original YOLOv8 and other mainstream models. The real-time processing capability of this model makes it suitable for practical road inspection and maintenance, effectively reducing the workload of maintenance personnel and enhancing roadway safety.

A Novel Defect Quantification Method Utilizing Multi-Sensor Magnetic Flux Leakage Signal Fusion

In the assessment of pipeline integrity using magnetic flux leakage (MFL) detection, it is crucial to quantify defects accurately and efficiently using MFL signals. However, in complex detection environments, traditional defect inversion methods exhibit low quantification accuracy and efficiency due to the complexity of their algorithms or excessive reliance on a priori knowledge and expert experience. To address these issues, this study presents a novel defect quantification method based on multi-sensor signal fusion (MSSF). The method employs a multi-sensor probe to fuse the MFL signals under multiple lift-off values, enhancing the diversity of defect information. This enables defect-opening profile recognition using the characteristic approximation approach (CAA). Subsequently, the MSSF method is based on a 3D magnetic dipole model and integrates the structural features of multi-sensor probes to develop an algorithm. This algorithm iteratively determines the defect depth at multiple data acquisition points within the defect region to obtain the maximum defect depth. The feasibility of the MSSF quantification method is validated through finite element simulation and physical experiments. The results demonstrate that the proposed method achieves accurate defect quantification while enhancing efficiency, with the number of iterations for each defect depth calculation point consistently requiring fewer than 15 iterations. For rectangular metal loss, perforation, and conical defects, quantification errors are less than 10%, meeting practical inspection requirements.

A fast deployable model for crack identification with laser thermography testing

This paper presents a novel feature extraction method, enabling efficient training and deployment of neural networks for rapid identification of crack defects in Laser Array Spot Thermography (LAST). We trained the crack defect identification model based on pixel-level features, encoding each pixel as a feature vector using Frangi filter, and classifying them using a neural network. Experimental results demonstrate that Frangi features are an effective method for distinguishing cracks, speckles, and background noise interference in the experiment. Furthermore, the model only requires a small region of interest (ROI) as training samples to achieve effective training and efficient crack identification under the same detection conditions, allowing for rapid deployment in practical inspections.

A fast visual onsite method for detection and quantitation of food additives using an engineered metal nanohybrid-based catalyst

Unsafe food additives pose a significant threat to global health, especially in developing countries. Many existing methods rely on clean laboratories, complicated optics equipment, trained personnel and lengthy detection time, which are not suitable for onsite food safety inspections in emergency situations, peculiarly in impoverished areas. In this paper, a fast and visual onsite method is designed for the detection and quantification of additives in food safety by engineering a nanohybrid (MoS2/SDBS/Cu-CuFe2O4)-based catalysis. Interestingly, the nanohybrid presents peroxidase-like mimetic activity toward the substrate containing 3,3′,5,5′-tetramethylbenzidine (TMB) and hydrogen peroxide (H2O2), which are then integrated simply into a detection kit. The blue oxidated TMB in this kit can be converted completely to colorless by some bio-molecule additives in commercial food, such as glutathione (GSH), cysteine (Cys), and ascorbic acid (AA). Remarkably, this process takes just less than 2 min and the detection limits are 2.8 nM, 5.5 nM and 47 nM, respectively. These results show excellent repeatability with a statistical analysis with (*P < 0.05) over 30 tests. Next, the images of the color changes can be captured clearly using a smartphone by red–green–blue (RGB) channels, which provides an opportunity for the development of field-operation device. Additionally, our approach is applied to some targets-indicative foods, showing a recovery range between 95.8 % and 104.2 %, offering an attractive and promising pathway for future practical food safety inspection applications. More importantly, this method can easily be extended to the detection of reducing substances in other analytical fields.

Design and Testing of an Autonomous Navigation Unmanned Surface Vehicle for Buoy Inspection

In response to the inefficiencies and high costs associated with manual buoy inspection, this paper presents the design and testing of an Autonomous Navigation Unmanned Surface Vehicle (USV) tailored for this purpose. The research is structured into three main components: Firstly, the hardware framework and communication system of the USV are detailed, incorporating the Robot Operating System (ROS) and additional nodes to meet practical requirements. Furthermore, a buoy tracking system utilizing the Kernelized Correlation Filter (KCF) algorithm is introduced. Secondly, buoy image training is conducted using the YOLOv7 object detection algorithm, establishing a robust model for accurate buoy state recognition. Finally, an improved Line-of-Sight (LOS) method for USV path tracking, assuming the presence of an attraction potential field around the inspected buoy, is proposed to enable a comprehensive 360-degree inspection. Experimental testing includes validation of buoy image target tracking and detection, assessment of USV autonomous navigation and obstacle avoidance capabilities, and evaluation of the enhanced LOS path tracking algorithm. The results demonstrate the USV’s efficacy in conducting practical buoy inspection missions. This research contributes insights and advancements to the fields of maritime patrol and routine buoy inspections.

Imaging of biological tissues with terahertz microscopy based on a cross-filament

Terahertz (THz) imaging technology has shown powerful potential for applications in biological sensing due to characteristics of the THz radiation. However, the measurement accuracy is always restricted by the low spatial resolution of THz imaging. In this work, a THz microscopy based on a cross-filament was utilized to inspect different biological tissues. A quasi sub-wavelength resolution was realized without approaching the sampe surface with any actual devices. By using the technique, fine tissue structures of two plant leaves and two animal bodies were precisely identified and analyzed from their temporal, spectral, and absorption images. Furthermore, possible optimization solutions were also discussed in detail for enhancing the imaging performance. This work demonstrated a novel and practical inspection method for pushing the development of THz biological applications.

Anisotropy and compaction gradient assessment on rammed earth specimens through sonic tomography approach

Rammed earth is a traditional construction technique that has recently gained attention because of its benefits from an ecological perspective. The conservation of the existing valuable cultural heritage sites and the quality control of new constructions built with this material require the development and application of practical inspection techniques. This paper explores the application of sonic tests and sonic tomography as practical tools for monitoring the state of conservation of existing structures and the identification of heterogeneities or damaged areas. Two groups of 6 rammed earth specimens were manufactured and tested. The manufacturing process of each group allowed the application of compression loads and the identification of the Sonic Wave Propagation Velocities along directions parallel and perpendicular to the compaction forces during manufacturing. The SWPV were identified for the different paths between 9 measuring points located at two opposite sides of the specimens, leading to up to 6 different planes for each specimen. The SWPV are identified by identifying the Time-of-Flight of the elastic wave between each pair of excitation and receiver points. A discretized coloured map of the SWPV distribution for each plane defined by the measurement points array is obtained by the application of an algorithm already developed by the authors to obtain tomographic images for other materials and applications. The SWPV are identified after 2 different increasing values of a uniform compressive load is applied to each specimen. The results show that the analysis of the SWPV and tomographic images is sensitive to heterogeneities, such as compaction gradients from the manufacturing process, and also to the accumulated damage in the solid. The paper demonstrates that the proposed technique can be potentially used for a qualitative inspection of the state of conservation of specific rammed earth constructions.

Multiscale finite element analysis of layer interface effects on cracking in semi-flexible pavements at different temperatures

This paper presents comprehensive research work on the crack initiation behavior of Semi Flexible Pavements (SFP) with the help of a one-way coupled multiscale modelling approach. The study focuses on elucidating the influence of layer interface conditions on potential cracking patterns under different temperature conditions. By integrating material properties at both local (mixture) and global (pavement) scales using a local de-homogenization approach, the interlocking effect was addressed within the asphalt binder's mesoscale properties. CT-image based mesostructure was employed to reconstruct the Representative Volume Element (RVE). Cohesive Zone Model (CZM) was utilized to simulate cracking initiation within the RVEs, with simulation results validated against practical engineering inspections. Additionally, a potential macroscopic failure index was introduced for SFP. It was found that the typical macroscopic failure indexes utilized for AC pavement may not be suitable for SFP due to the higher degree of heterogeneity. Analysis showed that SFP layer's coarse aggregate and cement grout at the bottom may experience compressive stress, while asphalt binder beneath the tire load may face high tensile stresses. Regardless of the interface conditions, top-down cracking was found to be the dominating failure mode in SFP. Besides, the vulnerable area in bonded interface SFP shifts from under tire load to the adjacent area with the rise in pavement temperature, while bottom-up cracking may appear only in unbonded interface SFP under low temperature conditions. Subsequent analysis demonstrated that top-down cracking is prominent in bonded interface SFP, especially at higher temperatures, compared to unbonded interface SFP. It is expected that critical observations for SFP highlighted above will certainly help in understanding critical failure modes and, hence, designing and constructing durable SFP structures.

Insulation Resistance Degradation Models of Extruded Power Cables under Thermal Ageing

Insulation resistance (IR) is an essential metric indicating insulation conditions of extruded power cables. To deliver reliable IR simulation as a reference for practical cable inspection, in this paper, four IR degradation models for cross-linked polyethylene-insulated cables under thermal ageing are presented. In addition, the influences of methodologies and temperature profiles on IR simulation are evaluated. Cable cylindrical insulation is first divided into sufficiently small segments whose temperatures are simulated by jointly using a finite volume method and an artificial neural network to model the thermal ageing experiment conditions. The thermal degradation of IR is then simulated by dichotomy models that randomly sample fully degraded segments based on an overall insulation (layer) ageing condition estimation and discretization models that estimate the gradual degradation of individual segments, respectively. Furthermore, uniform and non-uniform temperature profiles are incorporated into dichotomy and discretization models, respectively, for a comparison. The IR simulation results are not only compared between different models, but also discussed around the sensitivity of IR simulation to segment sizes and degradation rates. This provides cable assessment engineers with insights into model behaviour as a reference for their selection of appropriate IR degradation models.

Probabilistic inspection planning for fatigue cracks in floating production, storage, and offloading units

Probabilistic inspection planning for fatigue cracks in floating production, storage, and offloading units

The globalized fish Industry: Employing DNA-barcoding and NIRS technology to combat counterfeiting and safeguard traditional agro-food products

Traditional food plays a crucial role in showcasing the culture and heritage of its producers. The identification of the Traditional agro-Food Product (TFP) “Seppia bianca di Chioggia”, which is derived from Italian traditional cuttlefish, was performed through genetic analysis utilizing mitochondrial cytochrome c oxidase I subunit gene (COI) sequences and near-infrared spectroscopy (NIRS). The set samples were obtained from the shores of Chioggia (Adriatic Sea), and a comparison was made with cuttlefishes collected from Cesenatico (Adriatic Sea) and the coastal regions of France (Atlantic Ocean). The primary objective was to differentiate the TFP from samples sourced from nearby production areas and distant geographic locations that are commonly sold in Italy. A total of 368 cuttlefishes were analysed for NIRS data, whereas a subset of 75 samples were randomly selected and analysed for COI sequences to assess cuttlefish origin and TFP certification. Genetic and NIRS models were then tested on the same set of samples using a machine learning approach through the hold-out validation method. Additionally, an external validation was performed using a new set of cuttlefishes (labelled fished in shore of Chioggia or in Atlantic Ocean) collected from the daily fish market located in Chioggia (Venice, Italy). Both technologies showed excellent accuracy (100%) in discriminating fishing origin between the Adriatic Sea and Atlantic Ocean. However, the genetic information was not sufficient to differentiate cuttlefishes between the closest fishing areas within the Adriatic Sea (balanced accuracy = 50–83.5%) and did not provide information about the production system (TFP certification), while it showed the highest performance of genetic membership assignment (≥96%) among untreated cuttlefishes collected in the fish market. However, the NIRS model completely differentiated (accuracy = 100%) samples according to the specificity of the treatment nature (simple skinned products vs. TFP preparations), while it was unable to differentiate cuttlefish origin in untreated samples collected in the fish market (accuracy = 50%). The present results demonstrated that NIRS represents a rapid, fast, green and nondestructive approach to support on-site, practical inspection to authenticate and promote TFP protection that mirrors a niche product as a result of the synergy between natural resources and cultural heritage.

A systematic approach to pixel-level crack detection and localization with a feature fusion attention network and 3D reconstruction

Automated detection and localization of surface cracks by using deep learning and computer vision (CV) techniques are conducive to efficient structural condition assessment. However, insufficient feature resolution in deep architecture networks leads to misclassification and inaccurate segmentation of cracks. Furthermore, accurately localizing cracks within the overall structure is crucial for understanding the extent of damage to structural safety and durability. To address these challenges, this paper proposes a systematic approach for pixel-level surface crack detection and localization. The approach is based on a novel Feature Pyramid and Attention Feature Fusion Network (FPAFFN) and 3D reconstruction techniques. Two attention mechanisms named Attention Refinement Module (ARM) and Feature Fusion Module (FFM) are embedded in FPAFFN to strengthen the extraction and fusion of semantic and detailed information. With the cracks annotated images produced by FPAFFN, COLMAP and an open Multi-View Stereo are adapted to reconstruct the 3D model of the cracked structural components. Experimental studies on benchmark datasets CRACK500 and Cracktree200 and manually captured images validate the effectiveness of FPAFFN. The ARM and FFM embedded in FPAFFN enhance the feature learning efficiency and lead to a 3 % rise in the mean intersection ratio (mIoU). FPAFFN demonstrates remarkable generalization capability in detecting images with disturbances and outperforming other well-known crack detection methods in delineating crack edges and details. A subsequent experimental study on a damaged concrete slab shows that the proposed approach is capable of systematically detecting and localizing cracks. Therefore, it is promising to apply the proposed approach to practical structural inspection.

Vision Image Monitoring on Transportation Infrastructures: A Lightweight Transfer Learning Approach

Vision monitoring of distress has emerged as a new trend in intelligent transportation infrastructure systems, including roads and bridges. Recently, transfer learning methods and lightweight networks have been used to realize efficient distress identification without large amount of human-labor work. This paper proposed an engineering approach that integrated transfer learning with lightweight models to classify and detect concrete bridge distresses. Two datasets named Distress Dataset of Asphalt Pavement (DDAP) with 2500 asphalt pavement distresses images and Distress Dataset of Concrete Bridge (DDCB) with 906 concrete bridge distresses images were used. The lightweight models MobileNet and MobileNet-SSD were employed to conduct 6 comparative experiments for exploring the model performance with different transfer learning modes (Mode I and II) and procedures (one-step and two-step procedure) in classification and detection tasks. Based on the comparison of the results, the optimum model for two tasks was respectively recognized. For classification task, the model directly transferred specific parameters of partial convolution layers from ImageNet-based model achieved the highest accuracy of 97.8%. For detection task, the two-step transfer learning model using an intermediate transfer learning step trained by DDAP reached a mean average precision of 87.16%. The proposed approach has the application potential for practical road inspection work in intelligent transportation infrastructure maintenance.

Frequency Characteristics Analysis of Remote Field Eddy Current Testing on Ferromagnetic Pipes

Pipes made of ferromagnetic alloys are widely installed in petrochemical plants and the steel plants. To implement non-destructive corrosion inspections on these pipes, remote field eddy current testing (ECT) which installs a search coil inside the pipe is a practical inspection method. Remote field ECT has the advantage of being able to detect external surface defects while the distance between the detection coil and the excitation coil is twice of the outer diameter of the testing pipe. Nevertheless, the inspection principle such as the frequency characteristics etc. of ECT signals have not been elucidated, inspection devices based on remote field ECT had not been employed widely. In this paper, we measured the frequency characteristics of ferromagnetic pipes with artificial outer surface defects by remote field ECT, and then detailed finite element analysis are carried out by using the nonlinear eddy current analysis to clarify the inspection principle of the remote field ECT. In both measurement and analysis, peak signal occurs directly under the defect and the optimal frequency range are the same. The phase angle of flux density due to the excitation current and flux density due to eddy current are found to greatly affect the frequency characteristics.

Crack inspection in tunnel structures by fusing information from a 3D light detection and ranging and pan-tilt-zoom camera system

This study proposes a practical crack inspection method for tunnel structures by fusing measurements from two novel sensors: 3D light detection and ranging (LiDAR) and pan-tilt-zoom (PTZ) camera. The proposed method comprises three phases: prerequisite phase, real-time measurement phase, and inspection phase. First, the 3D LiDAR and the PTZ camera is combined to generate 3D point cloud data (PCD) with RGB data prior to extract the plane contained the crack. Second, the PTZ camera tracked the crack of interest at the pre-registered location. Specifically, several signal processing methods including the Hough transform and random sample consensus are addressed to effectively recognize the crack of interest. Then, the pan and tilt of the camera are controlled to track the crack of interest and record the crack at several magnifications of the zoom automatically because the optimal magnification value of the zoom is unknown in practical field applications. Third, crack propagation rate is estimated by calculating the length of the crack using information on the crack recorded in previous measurements. Cracks in a recorded image are extracted by addressing a multiscale multilevel mask deep convolutional neural network (MSML Mask DCNN) and pixel-based clustering method. The MSML Mask DCNN constructs distinct feature maps to effectively extract features of cracks and the pixel-based clustering method effectively eliminate cracks not of interest to accurately calculate the crack propagation rate for the crack of interest. Finally, the crack propagation rate was calculated through statistical analysis with several images at different zoom magnifications to secure high accuracy. Field experiments demonstrate that the proposed method is effective to inspect cracks. Systematic analysis on experiments also revealed that all methods deployed in the crack inspection enable ensures high accuracy and robustness in field applications. Consequently, the proposed crack inspection system and method provide a cost-effective and autonomous solution for crack inspection of tunnel structures.

An ultrasonic in-line inspection data processing method considering invalid data caused by sensor failure

Ultrasonic in-line inspection is one of the most widely adopted nondestructive testing methods for defect detection in pipelines. In practical industrial scenes, pipeline specification varies, sensor failure occurs frequently, and the number of pipeline defect samples is scarce. How to detect defects without false detection caused by invalid data and with limited labeled samples is a challenging problem in this area. An ultrasonic in-line inspection data processing method considering invalid data caused by sensor failure is proposed in this paper to enhance the accuracy of the defect and its profile detection. Firstly, the multi-channel data is aggregated according to sampling time. The data dimension is reduced, and the accuracy of the invalid waveform detection adopting isolation forest arithmetic is improved. The methods are adopted for the invalid waveforms replacement with two-dimensional cubic spline interpolation using adjacent sensors. Secondly, a natural breakpoint method is adopted to locate the echo peaks. Residual wall thickness is evaluated by calculating the time difference between the echo peaks. A fast pseudo-colorization method based on sliding windows and a morphological image processing method are proposed to detect defects and their profiles efficiently utilizing the residual wall thickness. Finally, practical in-line inspection data is utilized to evaluate the performance. The experiment results illustrate that the detection accuracy is enhanced on different sizes of pipelines without requiring labeled samples.

Few-shot learning for image-based bridge damage detection

Autonomous bridge visual inspection is a real-world challenge due to various materials, surface coatings, and changing light and weather conditions. Traditional supervised learning relies on massive annotated data to establish a robust model, which requires a time-consuming data acquisition process. This work proposes a few-shot learning (FSL) approach based on improved ProtoNet for damage detection with just a few labeled examples. Feature embedding is achieved through cross-domain transfer learning from ImageNet instead of episodic training. The ProtoNet is improved with embedding normalization to enhance transduction performance based on Euclidean distance and a linear classifier for classification. The approach is explored on a public dataset through different ablation experiments and achieves over 94% mean accuracy for 2-way 5-shot classification via the pre-trained GoogleNet after fine-tuning. Moreover, the proposed fine-tuning methods based on a fully connected layer (FCN) and Hadamard product are demonstrated with better performance than the previous method. Finally, the approach is validated using real bridge inspection images, demonstrating its capability of fast implementation for practical damage inspection with weakly supervised information.

Shape-Consistent One-Shot Unsupervised Domain Adaptation for Rail Surface Defect Segmentation

Deep neural networks have greatly improved the performance of rail surface defect segmentation when the test samples have the same distribution as the training samples. However, in practical inspection scenarios, the rail surface exhibits variations in appearance due to different service time and natural conditions. Conventional deep learning models show limited generalization in scenes with distribution differences. To address this problem, we propose a novel one-shot unsupervised domain adaptation framework. Specifically, we introduce a shape consistent style transfer module that performs pixel-level distribution alignment between the training and test images. Based on the one-shot test image, the training image is reconstructed to have the same appearance as the test image. Meanwhile, we employ a multi-task learning strategy to prevent content distortion of the reconstructed images. To improve the robustness of the model to distribution differences, we design an edge-aware defect segmentation model and train the model using the reconstructed training images. The experimental results show that our method effectively improves the robustness of the model to distribution differences and achieves satisfying results in the task of rail surface defect segmentation.

Propagation characteristics of ultrasonic in SLM manufactured AlSi10Mg

Porosity is a crucial quality evaluation criterion in metal additive manufacturing. To investigate the propagation characteristics of ultrasonic longitudinal waves with different incident frequencies in AlSi10Mg prepared by selective laser melting, specimens with varying porosity were created using printing process adjustments. Ultrasonic longitudinal wave tests and COMSOL simulations based on 2.5 MHz, 3.5 MHz, 5 MHz, and 7.5 MHz incident frequencies were carried out to establish a linear relationship between average wave velocity, average attenuation coefficient, and porosity at different frequencies. Results indicate that sound velocity and porosity are inversely proportional for each frequency longitudinal wave, while the attenuation coefficient is proportional to the porosity. Linear fitting expressions suggest that the best fit for both sound velocity and attenuation coefficient occurs at 5 MHz. Simulation results demonstrate that using 5 MHz as the incident frequency can better balance detection sensitivity and linearity. These findings provide more data support for establishing the intrinsic connection between acoustic parameters and porosity of AlSi10Mg prepared by selective laser melting in the selected area and serve as a reference for selecting ultrasonic incident frequencies in practical inspection.

Custom Transient Finite Element Method and Ray Tracing Hybridization Strategies for Ultrasonic Testing Modelling

The transient spectral element method (SEM) is a specific high order finite element method that is particularly accurate and fast with a low memory footprint, hence enabling 3D ultrasonic testing simulations on a standard PC. However, particular care in its settings and hybridization with a semi-analytical solution remains a major challenge when seeking for both practicality and performance. A natural hybrid strategy consists of coupling a field calculated by ray tracing in the defect-free object to a SEM subdomain wherein the perturbation is enclosed, then synthesizing the signal with a reciprocity argument. The difficulty is to define the suited coupling strategy when the flaw response interacts with the back wall. In a highly heterogeneous medium, it may even become necessary to widen the numerical domain to the entire thickness of the inspected object and, therefore, to ensure the performance of the SEM through a custom discretization strategy. Here we present different customized uses of the SEM for practical ultrasonic inspection applications and discuss how they complement the ray tracing solution.