Local Defects Research Articles

Effects of defects on the high-temperature performance of selective laser melting K418 superalloys: An in-situ 3D X-ray analysis

Defects are inevitable in selective laser melting process, significantly impacting the mechanical properties of materials and reducing their service life. In this study, the effects of various defects and their distribution on the high-temperature mechanical performance of the selective laser melted K418 superalloys were investigated via an in-situ 3D X-ray analysis and finite element method. The results showed that the selective laser melting process can significantly enhance the strength of the K418 sample, while degrading the fracture elongation. The sphericity and location of defects are the two key parameters influencing the mechanical performance. The defects with low sphericity at the sub-surface resulted in elevated local stress and strain, accounting for the significant degradation in fracture elongation. Locally increased stress and accumulated strain around lack of fusion defects at the sub-surface contribute to the initiation and propagation of crack. This study provides inspiration for understanding the correlation between the defects and mechanical properties.

Finite element simulation and experimental study of the coupling acoustic field characteristics of ultrasonic waves with internal defects inside microelectronic packaging

The miniaturization, ultra-thin and multi-layer complex structure of microelectronic packaging complicates the coupling acoustic field of ultrasonic waves and internal defects in the packaging, making accurate defect detection very difficult. In this paper, the finite element models of flip chip (FC) packaging and ball grid array (BGA) packaging are established to investigate the coupling acoustic field characteristics of ultrasonic waves and defects. In addition, based on the ultrasonic pitch and catch technique, the coupling laws of ultrasonic waves of different frequencies and the defects of different types, positions and sizes are analyzed by simulation, and the relationship between the relative amplitudes of the bottom waves and the sizes of different defects is revealed. Two specimens of microelectronic packaging are designed and fabricated to carry out the experimental studies using an ultrasonic signal acquisition system. The simulation and experimental results show that the relationship between the defects with small changes in the same location and the relative amplitudes of the bottom waves is basically linear, while the relationship between the solder ball extension defects with large changes and the relative amplitudes of the bottom waves is basically logarithmic, which provides a theoretical guidance for accurate evaluation of the type, size and location of defects in the practical detection.

Dynamic behavior and spatio-temporal mechanical characteristics of the individual cavitation bubble on hydraulic concrete wall

This study endeavors to delve into the dynamics and consequent mechanical responses induced by an individual cavitation bubble proximal to a concrete surface. Employing the laser-induced cavitation bubbles experimental method, the dynamic behavior of a cavitation bubble near horizontal smooth and locally defective concrete surfaces is systematically investigated. Using computational fluid dynamics (CFD) simulations, the impulsive pressure induced by bubble collapse within a specific surface range is quantitatively investigated. Our results reveal that the presence of local defects on the concrete surface activates gas nuclei within the defects upon bubble shock wave emission. Gas nuclei near the surface center penetrate the bubble, prolonging the bubble’s pulsation period and reducing microjet velocities. During bubble collapse, significant concentrated stresses due to microjets near the surface center may trigger instantaneous brittle failure of the concrete surface. Moreover, shock waves form high-pressure zones within a certain range of the surface. When the dimensionless distance γ ranges from 1.1 to 1.2, a superposition phenomenon of microjets and shock waves is observed, compared to individual effects, enhancing the impulse at central point below the bubble, prolonging the duration of pressure within the specific surface horizontal range, but simultaneously accelerating the pressure’s horizontal attenuation rate along the surface. Compared to the center pressure of the wall surface, the impulse of average pressure better reflects the surface’s pressure response.

Improved calculation method for fault characteristic frequency of bearing with local defect on rolling element considering kinematic characteristics of raceways

The fault characteristic frequency of rolling bearing (RB) is widely used in fault diagnosis, and the theoretical values of fault characteristic frequencies currently used for studying local defect on rolling element (LDRE) are derived based on the self-rotation speed of the rolling element (RE). However, particularly in the case of supporting bearings, the inner raceway is rotated with the shaft while the outer raceway is fixed. This results in different kinematic properties of different raceways in contact with LDRE. Therefore, based on the different types of kinematic characteristics, fault characteristic frequencies of RE contacting with the different raceways have been derived respectively. The proposed frequencies are proved by experiment results and the benchmark data sets of bearing. Because the transmission path generated by LDRE contacting with the outer raceway is shorter than that generated by the inner raceway, the vibration response generated by LDRE contacting the outer raceway are more obvious. Therefore, combining the characteristic frequency of LDRE contacting with the inner raceway(fFRCI) with that of LDRE contacting with the outer raceway(fFRCO) can reduce misdiagnosis rate. The proposed fFRCO and fFRCI will provide a theoretical foundation for the fault diagnosis and condition monitoring of RBs.

Variations of the residual magnetic fields of X70 pipeline steels with double defects

The aim of this research is to correlate residual magnetic fields (RMFs) with double defects in ferromagnetic steels. Specimens of X70 pipeline steels were machined into smooth plates with two types of defect (single and double defects) for comparison. Tensile tests were carried out to detect the RMF signals on the surface of the defective specimens. The variation of the tangential component of the RMF signals was presented and magnetic parameters were defined to investigate the abnormal magnetic changes of the two types of defect. It was found that the peak value of the tangential component was not influenced by defect types and the valley value was capable of evaluating the interaction effect between defects. Correlation between the RMF signals and the location of double defects was also investigated. This research will promote the investigation of defect clusters in ferromagnetic steels based on the metal magnetic memory (MMM) technique.

Functional outcome after arthroscopic mosaicplasty for localised osteochondral defects in the knee

Background: Knee injuries are commonly encountered in active sports persons as well as nonathletes, with approximately 60% of patients having cartilage damage with or without associated ligament and meniscal injuries. In this study, we report on the functional outcome of autologous osteochondral grafting in localised cartilage lesions of the knee. MethodsA longitudinal follow-up study was conducted on 50 patients aged between 18-55 years with symptomatic focal cartilage defect in the knee of size less than 2.0 cm2 after necessary inclusion/exclusion criteria. Management involved arthroscopic autologous osteochondral grafting. The donor cartilage was from the non–weight-bearing region of the ipsilateral knee. Other associated intra-articular injuries were addressed in the same sitting. The patients were followed up after 6 weeks, 3 months and 6 months and clinical status documented by the Lysholm Knee Function Scale (LKFS). ResultsMost patients were young active males. Clinical presentation involved pain in all participants, followed by joint line tenderness. There was at least one associated injury to other intra-articular structures in 52% of the patients. The commonest associated injury was anterior cruciate ligament (ACL) tear followed by meniscus tear. The mean size of the focal cartilage defect was 1.013 cm2, ranging from 0.8 cm2 to 1.6 cm2. The mean preoperative LKFS was 56.97 ± 1.38 (standard error). There was a statistically (p < 0.001) as well as clinically significant (clinically important difference >13.0 and patient acceptable symptomatic state >70.0) improvement in the mean Lysholm score, which was 70 ± 1.32, 81.3 ± 1.12 and 92.1 ± 1.11 at the end of 6 weeks, 3 months and 6 months respectively. Eighty-four percent of the patients showed excellent functional outcome at 6 months (LKFS >90), whereas 8% and 4% had good and fair outcomes, respectively, at 6 months (LKFS: 70–90). Two patients (4%) who had failed ACL reconstruction had poor outcome (LKFS <70)at 6 months. ConclusionMosaicplasty is an excellent procedure for managing cartilage defects of small to medium sizes, less than 2.0 cm2. The short-term results are satisfying and can accelerate rehabilitation of sports injuries. It is noteworthy that instability is a contra-indication for the procedure to succeed.

Numerical investigation of bandgap characteristics in integrated metallic metafilters for nonlinear guided wave applications

Guided waves propagating in nonlinear media, featuring second harmonic generation, represent a promising avenue for early-stage damage detection due to their high sensitivity and long-range propagation capabilities. However, nonlinear ultrasonic measurements are hindered by nonlinearities induced by the experimental system, necessitating careful calibrations that have restricted their application to laboratory settings. While several phononic crystal and metamaterial designs have been devised to enhance nonlinear-based ultrasonic testing, most are tailored for suppressing second harmonics within a frequency range of 100–300 kHz, primarily utilizing low-frequency excitation. In this paper, we propose a metallic ring-shaped metafilter designed to explore high-order bandgaps. To fully understand the bandgap characteristics, we begin by analyzing mode shapes, providing insights into the underlying wave mechanics. The efficacy of the designed filter is subsequently assessed through 3D time step elastodynamic simulations. In addition, this study underscores the significance of parameters such as the number of rings employed in the filter, signal duration, and bandgap width in optimizing its performance. Furthermore, the observed mode conversion phenomena from S0 to A0 guided wave modes underscore the filter’s capacity to influence guided wave propagation. The defect localization technique, based on the time difference of arrival of second-order wave modes, accurately predicts the defect location with an error margin of less than 0.2%. The present investigation showcases advancements in the sensitivity of nonlinear-based guided wave testing for characterizing microstructural changes, promising substantial potential for detecting incipient damage in practical structural health monitoring applications.

High-resolution weld defect detection with RSU-MLP and dynamic kernel supervision

The challenges posed by high-resolution X-ray images of weld defects—including fuzzy features, multi-scale variability, small targets, and sample imbalance—create significant obstacles for accurate defect localization. Traditional deep learning methods typically emphasize global image characteristics, often neglecting local and multi-scale information, which leads to the inaccurate detection of small defects. To address this issue, we propose a novel high-resolution weld defect detection method called RSU-MLP. This method combines the RSU-MLP network with multi-scale feature extraction technology to effectively capture both local and global image features. Additionally, we design a dynamic kernel adaptive segmentation head based on a hybrid extended convolutional attention mechanism, which adaptively adjusts the receptive field size of the convolutional kernel, thereby enhancing detection capabilities for defects of varying scales. Furthermore, an in-depth supervision mechanism is introduced to monitor and learn defects at different levels of the network, leading to improved detection performance. Experimental results on real high-resolution welding datasets demonstrate that the proposed method achieves promising results in welding defect detection. Compared to traditional approaches, this method provides more accurate detection and identification of various welding defects, achieving DICE and Jaccard scores of 75.97% and 64.01%, respectively. This represents the best performance, demonstrating both robustness and generalization capabilities. Consequently, it offers a reliable automated detection method for producing high-quality welded products.

Design and implementation of a nondestructive testing system for magnetic field imaging based on machine learning

This study presents the design of a nondestructive testing (NDT) system for detecting metal defects using a magnetic field sensor array. The system integrates a hardware-software detection framework that includes parallel computation and processing cores, along with multiple anisotropic magnetoresistance (AMR) sensors. These AMR sensors capture subtle variations in the magnetic field, which serve as the foundation for defect identification. The system enables synchronized data acquisition from multiple AMR sensors, achieving multi-axis data fusion and parallel signal processing. Furthermore, the detection system gathers defect features to train an NDT system based on machine learning (ML). Subsequently, ML-generated defect imaging features are processed through an imaging framework, producing magnetic field imaging (MFI) for precise defect localization. The study tested six different metal samples with various defect sizes and types to validate the system. The results demonstrate the system’s ability to accurately detect and identify different defects, highlighting the high precision of magnetic field detection and the overall effectiveness of the proposed system for NDT.

Time-varying Meshing Stiffness Calculation of Spur Gears with Asymmetric Spalling Defects

Gear systems are subjected to repeated loads during long-term operation, and factors such as insufficient lubricant to increase friction between gears, resulting in elevated temperatures and wear, are highly susceptible to tooth spalling. Tooth spalling is a common form of failure in gear failure. In previous studies, the vibration response of a gear pair with spalling defects at the tooth center near the pitch circle has been investigated. However, the location of the spalling defects offset from the center of the tooth flank is rarely studied. Tooth spalling faults occur in the pitch circle, but not necessarily in the center of the tooth, often formed on both sides of the center of the tooth and torsion in the meshing process. the symmetric and asymmetric rectangular spalling defects are considered, the torsional deformation is introduced. “torsional stiffness” is introduced into the overall TVMS due to the spalling defect. Therefore, it is meaningful to grasp the reasons for the formation of tooth spalling.

High-performance surface defect detection of aluminum substrate based on event camera

Abstract Traditional industrial surface defect detection often employs CCD/CMOS cameras, but they are difficult to detect the minute defects on aluminum substrates in highly dynamic industrial scenes due to their nature. Event camera is a novel high-resolution vision sensor which measures per-pixel brightness changes in an asynchronous manner and outputs as event information flow (EIF). Small and weak defects on aluminum substrate can be captured by event camera effectively, but the EIF contain a large amount of noise, making it difficult to perform accurate and high-precision defect detection. To address this problem, we propose a frame aggregation method to realize good event information flow processing (EIFP), and then use an improved circle detection method to locate the aluminum substrate in each frame, removing abundant event information outside the aluminum substrate. Subsequently, we enhance the event signals under different frames based on optical flow tracking using multiple features, and construct a semi-supervised detector based on pseudo-labels to achieve high-precision defect localization. Finally, considering the small inter-class differences in defects on the surface of aluminum substrates, we construct a defect class corrector based on ensemble learning to enhance the ability to determine defect classes, achieving high-precision automatic quality inspection of aluminum substrate surfaces. The performance of our method is compared with other advanced methods based on event camera data of aluminum substrates in real industrial scenarios. The experimental results show that our method has improved the detection accuracy by about 10% and the classification accuracy by about 25% compared to the original state-of-the-art methods.

Experimental Study on Quick‐Locking Reinforcement Model for Local Defects in Pipelines in the Rich Water Area

ABSTRACTThe management of local defects in municipal pipelines in water‐rich areas remains a significant challenge, particularly under high‐pressure conditions. This study investigates the performance of quick‐lock steel sleeves as a trenchless repair method through full‐scale experiments on five different pipeline diameters. The experiments focus on the failure modes and critical buckling pressure of the sleeves under external pressure. A novel design model based on structural reliability theory was developed and validated against experimental results. The results show a close match between the calculated and experimental buckling pressures, with a ratio ranging from 0.87 to 1.15. These findings provide valuable insights for the design and application of quick‐lock sleeves in high‐pressure municipal networks. This study contributes to improving the reliability and effectiveness of pipeline repair technologies, offering practical solutions for addressing pipeline leakage and instability in challenging environments.

Defect characteristics-based low-cycle fatigue life prediction model for additive manufactured Ti-6Al-4 V alloys

Volumetric defect is a significant factor that influences the fatigue life assessment accuracy in additive manufactured (AM) metals. In order to accurately assess the effects of volumetric defects on fatigue property of AM alloys, this study investigates the influence of geometric characteristics such as size, location, and shape of volumetric defects on low-cycle fatigue (LCF) properties. The results indicate that these factors have a significant influence on the fatigue life of material, and the volumetric defect location is found to be the most critical factor. In order to identify the critical volumetric defects on the fatigue fracture, a defect characteristic parameter “P” is proposed to characterize the influence of volumetric defect characteristics on the fatigue performance of material. Subsequently, a low-cycle fatigue life prediction model for AM metals that considers the geometrical characteristics of volumetric defects is established based on the relationship between P-parameter and low-cycle fatigue life. The accuracy of the prediction model is within 1.5x error band, which is significantly improved compared to the Manson-Coffin (M−C) model and Smith-Watson-Topper (SWT) model.

Localized Bearing Fault Analysis for Different Induction Machine Start-Up Modes via Vibration Time-Frequency Envelope Spectrum.

Bearings are the most vulnerable component in low-voltage induction motors from a maintenance standpoint. Vibration monitoring is the benchmark technique for identifying mechanical faults in rotating machinery, including the diagnosis of bearing defects. The study of different bearing fault phenomena under induction motor transient conditions offers interesting capabilities to enhance classic fault detection techniques. This study analyzes the low-frequency localized bearing fault signatures in both the inner and outer races during the start-up and steady-state operation of inverter-fed and line-started induction motors. For this aim, the classic vibration envelope spectrum technique is explored in the time-frequency domain by using a simple, resampling-free, Short Time Fourier Transform (STFT) and a band-pass filtering stage. The vibration data are acquired in the motor housing in the radial direction for different load points. In addition, two different localized defect sizes are considered to explore the influence of the defect width. The analysis of extracted low-frequency characteristic frequencies conducted in this study demonstrates the feasibility of detecting early-stage localized bearing defects in induction motors across various operating conditions and actuation modes.

D2-SPDM: Faster R-CNN-Based Defect Detection and Surface Pixel Defect Mapping with Label Enhancement in Steel Manufacturing Processes

The steel manufacturing process is inherently continuous, meaning that if defects are not effectively detected in the initial stages, they may propagate through subsequent stages, resulting in high costs for corrections in the final product. Therefore, detecting surface defects and obtaining segmentation information is critical in the steel manufacturing industry to ensure product quality and enhance production efficiency. Specifically, segmentation information is essential for accurately understanding the shape and extent of defects, providing the necessary details for subsequent processes to address these defects. However, the time-consuming and costly process of generating segmentation annotations poses a significant barrier to practical industrial applications. This paper proposes a cost-efficient segmentation labeling framework that combines deep learning-based anomaly detection and label enhancement to address these challenges in the steel manufacturing process. Using ResNet-50, defects are classified, and faster region convolutional neural networks (faster R-CNNs) are employed to identify defect types and generate bounding boxes indicating the defect locations. Subsequently, recursive learning is performed using the GrabCut algorithm and the DeepLabv3+ model based on the generated bounding boxes, significantly reducing annotation costs by generating segmentation labels. The proposed framework effectively detects defects and accurately defines them, even in randomly collected images from the steel manufacturing process, contributing to both quality control and cost reduction. This study presents a novel approach for improving the quality of the steel manufacturing process and is expected to enhance overall efficiency in the steel manufacturing industry.

PDeT: A Progressive Deformable Transformer for Photovoltaic Panel Defect Segmentation.

Defects in photovoltaic (PV) panels can significantly reduce the power generation efficiency of the system and may cause localized overheating due to uneven current distribution. Therefore, adopting precise pixel-level defect detection, i.e., defect segmentation, technology is essential to ensuring stable operation. However, for effective defect segmentation, the feature extractor must adaptively determine the appropriate scale or receptive field for accurate defect localization, while the decoder must seamlessly fuse coarse-level semantics with fine-grained features to enhance high-level representations. In this paper, we propose a Progressive Deformable Transformer (PDeT) for defect segmentation in PV cells. This approach effectively learns spatial sampling offsets and refines features progressively through coarse-level semantic attention. Specifically, the network adaptively captures spatial offset positions and computes self-attention, expanding the model's receptive field and enabling feature extraction across objects of various shapes. Furthermore, we introduce a semantic aggregation module to refine semantic information, converting the fused feature map into a scale space and balancing contextual information. Extensive experiments demonstrate the effectiveness of our method, achieving an mIoU of 88.41% on our solar cell dataset, outperforming other methods. Additionally, to validate the PDeT's applicability across different domains, we trained and tested it on the MVTec-AD dataset. The experimental results demonstrate that the PDeT exhibits excellent recognition performance in various other scenarios as well.

Experimental Study on the Mechanical Properties of Squat RC Shear Walls with Corrosion Along the Base

In corrosive environments containing chloride and sulfate, the corrosion of steel bars is common along the base of squat RC shear walls (SRCSW) due to problems such as construction quality, concrete stress concentration, local defects, and accumulation of water and corrosive media. In this paper, three SRCSWs are designed and constructed and their mechanical properties assessed. One side of each SRCSW was exposed to a corrosive environment for 70 days, while the other side was subject to the same conditions over different corrosion times (i.e., 0 day, 42 days, and 70 days). Then, the corrosion-induced cracking process, the mechanical properties of SRCSWs corroded along the base, the relationship between the mass loss of total steel bars (MLTSB) in the corroded area and the wall mechanical properties, and the relationship between the average width of corrosion-induced cracks (CICs) and the wall mechanical properties were studied through an accelerated corrosion test and a loading failure test. The results indicate that the area of corrosion-induced cracking on SRCSWs increased with the corrosion time, and the cracking area on the different SRCSWs was approximately identical when the SRCSWs were exposed to the same corrosion time. When the degree of corrosion was different, the loading failure characteristics of the SRCSWs were obviously different, but the failure mode always corresponded to shear failure. The load–displacement curves of the SRCSWs with different degrees of corrosion along the base basically coincided and were linear when the loading was in the elastic stage. Compared to SW-1, the peak load of SW-2 decreased by 4.0%, but that of SW-3 increased by 2.7%. Compared to SW-1, the yield loads of SW-2 and SW-3 decreased by 22.4% and 11.8%, respectively. When the MLTSB increased from 13.05% to 16.71%, the crack, yield, and peak loads of the SRCSWs corroded along the base decreased by 8.8%, 22.4%, and 6.8%, respectively. The cracking, yield, and peak loads of the SRCSWs corroded along the base decreased linearly with the increase in MLTSB and the average width of the CICs, and the corresponding fitting relations were established. The results of this study can serve as a reference for the durability design of SRCSWs in corrosive environments.

Cl− skeleton modification and K+ charge compensation construct Eu2+ subcrystalline luminescent structure in NaAlSiO4

In this work, the highly homogeneous NaAlSiO4 structure was constructed by glass relaxation crystallization method. The evolution of the subcrystalline luminescence structure was examined by using Eu2+ as a structural probe. The optimization of luminescent properties and phase structure changes of Cl− substitution, Eu2+ occupancy and K+ charge compensation were studied by XRD, EDS, PL spectra, PLE spectra and luminescence thermal stability analysis. The research revealed the AB layer spacing of the crystal stretched and the hexatomix ring opened by Cl− directionally replace O2−(O5), inducing more Eu2+ to selectively occupy the Na+(I) site, resulting in local charge defects in the lattice. The transition emission efficiency of Eu2+ was increased by 50 % with introducing K+ for directional charge compensation. In comparison with NaAlSiO4:2%Eu2+, the NaAlSiO3.96Cl0.04:2%Eu2+-8K+ phosphor showed a 20.82 % increase in ΔE, indicating improved thermal sensitivity in this phosphor series, which holds promising potential for application in LED devices.

Effect of Deposition Temperature on Zn Interstitials and Oxygen Vacancies in RF-Sputtered ZnO Thin Films and Thin Film-Transistors.

ZnO thin films were deposited using RF sputtering by varying the argon:oxygen gas flow rates and substrate temperatures. Structural, optical and electrical characterization of ZnO thin films were systematically carried out using X-Ray diffraction (XRD), scanning electron microscopy (SEM), UV-visible spectroscopy, X-Ray photoelectron spectroscopy (XPS) and Hall measurements. Film deposited at room temperature and annealed at 300 °C exhibited low O2 incorporation with localized defects and a high percentage of Zn interstitials. A large crystalline size and fewer grain boundaries resulted in a high Hall mobility of 46.09 cm2/V-s Deposition at higher substrate temperatures resulted in improvement in O2 incorporation through the annihilation of localized defects and decrease in oxygen vacancies and Zn interstitials. Urbach tails within the bandgap were identified using the absorption spectrum and compared with the % defects from XPS. Bottom-gate thin-film transistors were subsequently fabricated on a SiO2/p-Si substrate using the combination of RF sputtering, wet etching and photolithography. Variation in the substrate temperature showed performance enhancement in terms of the leakage current, threshold voltage, sub-threshold swing and ION/IOFF ratio. Thin-film transistor (TFT) devices deposited at 300 °C resulted in an O2-rich surface through chemisorption, which led to a reduction in the leakage current of up to 10-12 A and a 10-fold reduction in the sub-threshold swing (SS) from 30 V to 2.8 V. Further TFT optimization was carried out by reducing the ZnO thickness to 50 nm, which resulted in a field-effect mobility of 1.1 cm2/V-s and ION/IOFF ratio of 105.

Road Defect Identification and Location Method Based on an Improved ML-YOLO Algorithm.

The conventional method for detecting road defects relies heavily on manual inspections, which are often inefficient and struggle with precise defect localization. This paper introduces a novel approach for identifying and locating road defects based on an enhanced ML-YOLO algorithm. By refining the YOLOv8 object detection framework, we optimize both the traditional convolutional layers and the spatial pyramid pooling network. Additionally, we incorporate the Convolutional Block Attention to effectively capture channel and spatial features, along with the Selective Kernel Networks that dynamically adapt to feature extraction across varying scales. An optimized target localization algorithm is proposed to achieve high-precision identification and accurate positioning of road defects. Experimental results indicate that the detection accuracy of the improved ML-YOLO algorithm reaches 0.841, with a recall rate of 0.745 and an average precision of 0.817. Compared to the baseline YOLOv8 model, there is an increase in accuracy by 0.13, a rise in recall rate by 0.117, and an enhancement in average precision by 0.116. After the high detection accuracy of road defects was confirmed, generalization experiments were carried out on the improved ML-YOLO model in the public data set. The experimental results showed that compared with the original YOLOv8n, the average precision and recall rate of all types of ML-YOLO increased by 0.075, 0.121, and 0.035 respectively, indicating robust generalization capabilities. When applied to real-time road monitoring scenarios, this algorithm facilitates precise detection and localization of defects while significantly mitigating traffic accident risks and extending roadway service life. A high detection accuracy of road defects was achieved.