Types Of Defects Research Articles

MAA-YOLOv8: enhanced steel surface defect detection through multi-head attention mechanism and lightweight feature fusion

In the process of industrial production, product defects often arise due to improper operations among other reasons, rendering the detection of such flaws an indispensable procedure. However, the vast array of defect types, coupled with their complex characteristics, poses ongoing challenges for contemporary defect detection algorithms within industrial settings. To solve this problem, the present study introduces an enhanced steel surface defect detection model based on the modified YOLOv8 algorithm-termed the MAA-YOLOv8 model-to augment the accuracy and practicality of the algorithm. Initially, a multi-head attention mechanism was incorporated into the C2f to bolster the feature extraction capabilities within the backbone network and diversify the attention maps. Secondly, in the neck structure, we design a multi-channel feature fusion module (McPAN) to solve the problem of balance between computational efficiency and the ability to capture useful features. A series of experiments conducted on the NEU-DET dataset reveal that the MAA-YOLOv8 model achieves a mean Average Precision (mAP) of 94.4%, representing an enhancement of 11.1% over the original YOLOv8s model. The MAA-YOLOv8 model proposed in this study substantially elevates the performance of steel surface defect detection while ensuring the speed of detection.

Enhancing structural integrity of refractories during manufacturing through integration of UPV and acoustic nonlinearity measurements

ABSTRACT This paper addresses the critical need for robust quality assurance in commercial refractories, emphasizing the role of Ultrasonic Pulse Velocity (UPV) testing in assessing material integrity. Traditionally, UPV testing has become a standard practice for evaluating refractory, ceramic, and concrete materials after production. However, this study introduces an innovative approach by advocating the integration of UPV tests at an intermediate stage prior to temperature curing. The primary objective is to predict the performance of refractory samples under compressive loading, examine intrinsic damages, and analyse ultrasonic characteristics in both time and frequency domains. Experimental investigations introduce damages, including artificial voids simulating various defect types, both before and during heat treatment. Analysis of UPV, Root Mean Squared (RMS) values of frequency spectra, and the acoustic nonlinearity parameter (ANP) reveals substantial differences between healthy and damaged regions. The mean UPV and RMS values consistently decrease in damaged regions, indicating sensitivity to defect severity. The ANP is sensitive to damage size, especially with higher frequency transducers detecting subtle changes more effectively. These findings emphasise the potential for proactive testing at an intermediate stage in the manufacturing process, enhancing the structural integrity and overall quality of refractory materials.

Analysis Of Defects In Laminated Doors Using Failure Mode And Effect Analysis (FMEA) And Fault Tree Analysis (FTA)

Quality control is an crucial part of the production process because product quality must meet established standards. Based on drawback that happen in the laminating door production process, prioritizing different failure types is essential to reduce the occurrence of defects in the same production process. To enhance product quality and minimize defects, consider implementing by using Failure Mode and Effect Analysis (FMEA) and Fault Tree Analysis (FTA). The purpose of this study is to identify the types of factors causing product defects in the laminating door production process and provide recommended actions in the improve phase to minimize the number of defects. This study analyzes six types of defects in laminating door products. The results show that operator errors are the dominant cause, influenced by environmental conditions and an unsupportive work system. Based on the Risk Priority Number (RPN) values, the defects with the highest values are glue not sticking (RPN 294) caused by machine factors, cracks (RPN 252) by method factors, groove size not meeting specifications (RPN 245) by man factors, peeling paint (RPN 180) by method factors, scratches on the laminate surface (RPN 175) by man factors, and imprecise joints (RPN 120) by man factors. Improvement suggestions include operator training, machine maintenance, replacement of inadequate equipment, selection of appropriate raw materials, and implementation of clear Standard Operating Procedures.

Mid-term outcomes of minimally invasive surgery for partial atrioventricular septal defect in children

Objective: This study aims to describe the mid-term outcomes of minimally invasive surgery for partial atrioventricular septal defect in children. Summary: Partial atrioventricular septal defect is one of the three types of atrioventricular septal defect, accounting for about 3.5% of congenital heart disease. Traditionally, complete repair has been performed via sternotomy. However, with the advancement of minimally invasive surgical techniques in treating congenital heart conditions, we conducted this study to assess the feasibility and mid-term outcomes of this approach. Subjects and methods: This descriptive study spanned from January 2018 to December 2023, involving 30 patients diagnosed with partial atrioventricular septal defect who underwent minimally invasive complete repair. The cohort comprised 12 males and 18 females, with an average age of 18 months and average weight of 10.3 kg. The mean diameter of the primary atrial septal defect was 15 mm. Eight patients (26.7%) exhibited moderate to severe mitral regurgitation, and the average pulmonary artery pressure was 37 mmHg. Results: The average durations of cardiopulmonary bypass and aortic cross-clamp were 82 minutes and 58 minutes, respectively. None of the patients required sternotomy. The average time of artificial ventilator post-surgery was 6.9 hours, with a mean hospital stay of 7.6 days. Postoperative echocardiography showed promising results: complete closure of atrial septal defect, with 90% of patients having absent or mild mitral valve regurgitation, only 10% experienced moderate mitral valve regurgitation. The average follow-up period was 38 months, during which there were no postoperative fatalities. One patient required reoperation due to severe mitral regurgitation from an anterior cleft. Conclusion: Minimally invasive surgery for partial atrioventricular septal defect in children can be safely performed, yielding favorable mid-term outcomes during follow-up.

EfficientNet-ECA: A lightweight network based on efficient channel attention for class-imbalanced welding defects classification

Welding defects recognition is crucial for ensuring weldment quality in robot arc welding. Nevertheless, due to unbalanced data distributions, limited computing resources in factory, as well as intraclass variability and interclass similarity among different welding defects, it is difficult to extract the most discriminative defect features from welding molten pool images on site, resulting in weak class-imbalanced defect recognition performance. To address the above issue, a novel lightweight network named EfficientNet-ECA is proposed for recognizing and classifying welding defects according to molten pool images of robot arc welding. Firstly, the EfficientNet-ECA network based on Efficient Channel Attention (ECA) is designed to extract the most discriminative features of different defects from molten pool images, where ECA is employed to enhance cross-channel information interactions. Secondly, a dynamic equalized focal loss function is proposed to both rebalance the loss contribution of class-imbalanced data of different defects and improve defects recognition accuracy. Subsequently, a class-imbalanced dataset containing eight typical welding defects is constructed to evaluate the EfficientNet-ECA model. Finally, the proposed model is comprehensively analyzed through ablation studies and compared with the existing state-of-the-art lightweight models, and results show that the proposed method exhibits better effectiveness and generalizability in classifying class-imbalanced defects across different welding scenarios, achieving the highest accuracy of 95.84% on a self-constructed AL5083 dataset and 96.50% on a publicly available SS304 dataset. Moreover, with fewer parameters and less complexity, the proposed method is more suitable for online welding quality monitoring in factory.

Non-uniform critical current and stacking effect remedy for multi-filament REBCO tapes with potential defects

The high aspect ratio of REBCO tapes has a significant impact on several characteristics in high-temperature superconducting applications, such as critical current and AC loss. Narrow filamentary technology can effectively reduce the impact of magnetic field dependence and enhance the electromagnetic performance of REBCO tapes. However, the existing methods are constrained by the trade-off between the narrow degree of REBCO filaments and high current capacity. Meanwhile, when processing REBCO tapes for large-scale magnets, there is a great possibility that local defects are lurking. A striated narrow-stacked (NS) structure is proposed based on the existing narrowing methods to address these challenges. To verify the validity of this structure, it is imperative to explore the non-uniform critical current and stacking effect on performance for multi-filament REBCO tapes with potential defects. This article introduces a magnetic extended network (MEN) model to analyze the electrical characteristics of striated NS structures with different types of potential defects. Then, by coupling with a 3D finite element method electromagnetic module, the calculation results of the MEN model are visualized and used to analyze the electromagnetic characteristics including current sharing mechanism, magnetic field distribution, and critical current compensation due to stacking effect. It is found that stack structures successfully provide the performance remedy for multi-filament REBCO tapes with potential defects. This study aims to promote the narrowing improvement of REBCO tapes in high-field magnets and high-current applications.

High-accuracy and lightweight weld surface defect detector based on graph convolution decoupling head

Abstract The essence of the difficulties for weld surface detection is that there is a lot of interference information during detection. This study aims to enhance the detection accuracy while keeping great deployment capabilities of a detection model for weld surface defects. To achieve this goal, an improved Yolo-GCH model is proposed based on the stable and fast Yolo-v5. The improvements primarily involve introducing a graph convolution network combined with a self-attention mechanism in the head part (i.e., GCH). This component focuses on improving the insufficient recognition capability of CNN for similar defects in complex environments. Furthermore, to address the presence of potentially ambiguous samples in complex welding environments, the label assignment strategy of simOTA is implemented to optimize the anchor frame. Additionally, a streamlined structure, aiming to improve model detection speed while minimizing performance impact, has been designed to enhance the applicability of the model. The results demonstrate that the cooperation of GCH and simOTA significantly improves the detection performance while maintaining the inference speed. These strategies lead to a 2.5% increase in mAP@0.5 and reduce the missing detection rates of weld and 8 types of defects by 32.9% and 84.1% respectively, surpassing other weld surface detection models. Furthermore, the impressive applicability of the model is verified across four scaled versions of Yolo-v5. Based on the proposed strategies, the FPS increases by more than 30 frames in the fast s and n versions of Yolo-v5. These results demonstrate the great potential of the model for industrial applications.

DMWMNet: A novel dual-branch multi-level convolutional network for high-performance mixed-type wafer map defect detection in semiconductor manufacturing

Wafer map defect detection plays an important role in semiconductor manufacturing by identifying root causes and accelerating process adjustments to ensure product quality and reduce unnecessary expenditures. However, existing methods have some limitations, such as low accuracy in mixed-type defect detection and poor recognition of similar defects and weak features. In this article, a novel dual-branch multi-level convolutional network (DMWMNet) is proposed for high-performance mixed-type wafer map defect detection. By fully considering the interrelationships between basic defects, defect number, and defect type, the network is designed to include two efficient parallel Branches and a Fusion classifier. Detecting defect types using basic defect discrimination and defect number detection is helpful for ameliorating problems with high complexity and low accuracy caused by multiple defect categories and feature overlaps. Furthermore, a composite loss function based on focal loss is employed to improve the network’s capacity to recognize weak features and similar defects. Experimental results on the MixedWM38 dataset show that DMWMNet has favorable mixed-type defect detection performance compared to other methods, with accuracy, precision, recall, F1 score, and MCC of 98.99%, 98.94%, 99.03%, 98.98%, and 98.97%, respectively.

Physico-Chemical Properties of Copper-Doped Hydroxyapatite Coatings Obtained by Vacuum Deposition Technique.

The hydroxyapatite and copper-doped hydroxyapatite coatings (Ca10-xCux(PO4)6(OH)2; xCu = 0, 0.03; HAp and 3CuHAp) were obtained by the vacuum deposition technique. Then, both coatings were analyzed by the X-ray diffraction (XRD), scanning electron microscopy (SEM), atomic force microscopy (AFM), X-ray photoelectron spectroscopy (XPS), Fourier transform infrared spectroscopy (FTIR) and water contact angle techniques. Information regarding the in vitro antibacterial activity and biological evaluation were obtained. The XRD studies confirmed that the obtained thin films consist of a single phase associated with hydroxyapatite (HAp). The obtained 2D and 3D SEM images did not show cracks or other types of surface defects. The FTIR studies' results proved the presence of vibrational bands characteristic of the hydroxyapatite structure in the studied coating. Moreover, information regarding the HAp and 3CuHAp surface wettability was obtained by water contact angle measurements. The biocompatibility of the HAp and 3CuHAp coatings was evaluated using the HeLa and MG63 cell lines. The cytotoxicity evaluation of the coatings was performed by assessing the cell viability through the MTT assay after incubation with the HAp and 3CuHAp coatings for 24, 48, and 72 h. The results proved that the 3CuHAp coatings exhibited good biocompatible activity for all the tested intervals. The ability of Pseudomonas aeruginosa 27853 ATCC (P. aeruginosa) cells to adhere to and develop on the surface of the HAp and 3CuHAp coatings was investigated using AFM studies. The AFM studies revealed that the 3CuHAp coatings inhibited the formation of P. aeruginosa biofilms. The AFM data indicated that P. aeruginosa's attachment and development on the 3CuHAp coatings were significantly inhibited within the first 24 h. Both the 2D and 3D topographies showed a rapid decrease in attached bacterial cells over time, with a significant reduction observed after 72 h of exposure. Our studies suggest that 3CuHAp coatings could be suitable candidates for biomedical uses such as the development of new antimicrobial agents.

First-principles prediction of point defect energies and concentrations in the tantalum and hafnium carbides

First-principles calculations are combined with a statistical–mechanical model to predict the equilibrium point-defect concentrations in the refractory carbides TaC and HfC as a function of temperature and chemical composition. Several different types of point defects (vacancies, interstitials, antisite atoms) and their clusters are treated in a unified manner. The defect concentrations either strictly follow or can be closely approximated by Arrhenius functions with parameters predicted by the model. The model is general and applicable to other carbides, nitrides, borides, or similar chemical compounds. Implications of this work for understanding the diffusion mechanisms in TaC and HfC are discussed.

Clinical characteristics and outcome of omphalocele and gastroschisis: a 20-year multicenter regional experience.

Omphalocele and gastroschisis are the most common types of abdominal wall defects. Comprehensive local experience helps parents to make decisions on the pregnancy and foresee the disease journey. A retrospective review of abdominal wall defect patients in all three pediatric surgical centers in Hong Kong between January 2003 and February 2023 was conducted. All patients consecutively diagnosed with omphalocele and gastroschisis were included, excluding other forms. Data of demographics and short- and long-term outcome parameters were collected. A total of 99 cases were reviewed and 85 patients met the inclusion criteria. Diagnoses include omphalocele major (n = 49, 57.6%), omphalocele minor (n = 22, 25.9%) and gastroschisis (n = 14, 16.5%), with mean gestational age 37weeks (SD 2.2) and birth weight 2.7kg (SD 0.6). Omphalocele is most commonly associated with cardiovascular (n = 28, 39.4%) and chromosomal defects (n = 11, 15.5%). Surgical procedures including primary repair (n = 38, 53.5%), staged closure (n = 30, 42.3%) with average 8.6days (SD 4.7) of silo reduction, and conservative management (n = 3, 4.2%) were performed. The mortality rate was 14.1% (n = 10) and the complication rate was 36.6% (n = 26). The majority of patients had normal intellectual development (92.5%) and growth (79.2%) on the latest follow-up. For gastroschisis, one patient (7.1%) had intestinal atresia. Surgical procedures included primary repair (n = 9, 64.3%) and staged closure (n = 5, 35.7%) with average 8days (SD 3.5) of silo reduction. Complication rate was 21.4% (n = 3), with one mortality (7.1%). All patients had normal intellectual development and growth. The mean follow-up time of this series is 76.9months (SD 62.9). Most abdominal wall defects in our series were managed surgically with a good overall survival rate and long-term outcome. This information is essential during antenatal and postnatal counseling for parents.

Associations between hypopharyngeal defect closure and quality of life in long-term total laryngectomy survivors.

Few studies have examined health-related quality of life (HRQOL) outcomes in long-term total laryngectomy survivors in relation to the type of hypopharyngeal defect. A cross-sectional study was performed in long-term total laryngectomy survivors, treated between 2000 and 2020. The primary outcome was HRQOL, assessed using the FACE-Q Head and Neck Cancer Module, in relation to the type of hypopharyngeal closure (primary closure, partial or circumferential reconstruction). Seventy-nine survivors were included with a median follow-up of 92.1 months (IQR 75.6-140.2 months). Patients requiring partial hypopharyngeal reconstruction (n = 18) scored significantly worse than patients with primary closure (n = 51) on 4 of 13 FACE-Q domains: functional domains of eating (p = 0.03), speech (p = 0.05), and swallowing (p = 0.03), and the psychological domain of speaking-related distress (p = 0.02). No statistically significant differences were found between the circumferential hypopharyngeal defect reconstruction group (n = 10). Stricture occurrence was the only clinical factor associated with worse eating, speaking, swallowing, eating-related distress, and cancer worry in multivariable analyses. Several functional and psychological domains were significantly worse following partial hypopharyngeal reconstruction than in patients who received primary closure. Efforts to reduce stricture rates to enhance reconstructive outcomes following total laryngectomy merit further research.

Spirometry findings of chronic lung disease in high-altitude residents of Ladakh (>11000 feet above sea level)

Ladakh is a hilly Himalayan dry desert, situated at an altitude of >11000 feet. Studies have demonstrated that the spirometric values of high-altitude residents are significantly higher than those of low-landers. This is a retrospective observational study that analyzes the spirometry pattern in chronic lung diseases among people from Ladakh. Enrolled subjects were clinic-radiologically diagnosed and had at least one spirometry report. The spirometric parameters were analyzed for normal and abnormal patterns of lung function. The abnormal patterns were further classified into types of ventilator defects and their severity. A total of 122 cases were included, with 67 (55%) men. The mean age was 52.2±15.4 years. The most common diseases were chronic obstructive pulmonary disease (COPD) in 51 cases (41%), and asthma in 41 (33%). The median predicted percentage of forced vital capacity (FVC) was 116% (63-179%) with >100% in 105 (85%) patients. The median predicted percentage of the forced expiratory volume in the 1st second (FEV1) was 113% (99-175%) with >100% in 90 (74%) patients. FVC was reduced in 9 (7%) cases, normal in 62 (51%), and more than normal in 49 (42%), with 11 (9%) cases having >150% of the predicted percentage. FEV1 was reduced in 9 (8%) cases, normal in 67 (55%), and more than normal in 46 (37%) cases, with >150% predicted seen in 10 (8%) cases. Similarly, overall, the predicted percentages of both FVC and FEV1 were >100% in all obstructive airway diseases as well as in the separate COPD and asthma subgroups. FVC and FEV1 amongst chronic lung disease patients from Ladakh were more than normal in the majority. These higher values of spirometry led to incorrect disease severity classifications and disease patterns. We propose that studies should be done to devise local reference equations for spirometry for Himalayan high-altitude residents of India.

Topologically-protected optical bistability based on two-dimensional photonic crystal L6 nanocavity dimer array

We numerically investigate the optical bistability from a two-dimensional photonic crystal L6 nanocavity dimer array structure configured under the Su-Schrieffer-Heeger model. The localized electric field in the topological edge state is highly enhanced, which gives rise to strong nonlinear phenomena such as optical bistability. In comparison, a topologically trivial nanocavity is also designed and its field strength distribution and optical bistable response are also simulated. In order to test the robustness, three types of defects and interferences are introduced in both the topologically non-trivial and trivial cavities. Benefiting from the topological feature, the proposed topological cavity exhibits superior optical bistable performance with low threshold power and high switching contrast compared to that in the trivial cavity. Our work suggests what we believe to be a novel avenue toward the insertion of optical bistable devices with high robustness into future photonic integrated circuits and photonic neural networks.

Stochastic Defect Localization for Cooperative Additive Manufacturing Using Gaussian Mixture Maps

Abstract Robotic additive manufacturing (RAM) offers significant improvements in maximum build volume compared to conventional bounded designs (e.g., gantry) by leveraging high degrees-of-freedom machines and multi-robot cooperation. However, cooperative RAM suffers from the same defect generation challenges as conventional systems, necessitating improvements in the detection and prevention of flaws within fabricated components. Quality assurance can be further bolstered through the integration of AM models, which utilize sensor feedback to localize defects, vastly reducing false positives. This research explores defect localization through a novel dynamic defect model created from simulated sensing data. In particular, two cooperative robots are simulated to estimate defect parameters, while observing the workspace and accurately classifying different regions of the part, generating a Gaussian mixture map that identifies and assigns appropriate actions based on defect types and characteristics. The experimental result shows that the implementation of the dynamic defect model and selective reevaluation achieved an effective defect detection accuracy of 99.9%, an improvement of 9.9% without localization. The proposed framework holds potential for application in domains that utilize high degrees-of-freedom machines and collaborative agents, offering scalability, improved fabrication speeds, and enhanced mechanical properties.

The Role of Point Defects in Heterojunction Photocatalysts: Perspectives and Outlooks

AbstractThe development of efficient photocatalysts is a mainstay for the advancement of photocatalytic technology. Heterojunction photocatalysts can overcome the inherent limitations of single photocatalysts, integrating the advantages of each component, and achieving efficient separation of photogenerated charges, making them a research focus in the field of photocatalysis. The role of point defects in photocatalytic reactions is diverse and can significantly influence the performance of photocatalysts. This review comprehensively summarizes the latest advancements in point defect engineering for the modulation of heterojunction photocatalysts. First, the types of point defects and their impact on photocatalytic processes are introduced. Subsequently, the common types of heterojunction photocatalysts are presented. Then, in accordance with recent research progress, the regulatory mechanisms of point defects within heterojunction photocatalysts are outlined, with a particular focus on their functions on surface/interfacial properties and photogenerated charge transfer processes. Finally, the challenges faced by point defect engineering in optimizing heterojunction photocatalysts and promising solutions are proposed. This review provides an in‐depth understanding of the role of point defect engineering in heterojunction photocatalysts, with the expectation of offering insights into the development of highly active photocatalytic materials.

A dataset for deep learning based detection of printed circuit board surface defect

Printed circuit board (PCB) may display diverse surface defects in manufacturing. These defects not only influence aesthetics but can also affect the performance of the PCB and potentially damage the entire board. Thus, achieving efficient and highly accurate detection of PCB surface defects is fundamental for quality control in fabrication. The rapidly advancing deep learning (DL) technology holds promising prospects for providing accurate and efficient detection methods for surface defects on PCB. To facilitate DL model training, it is imperative to compile a comprehensive dataset encompassing diverse surface defect types found on PCB at a significant scale. This work categorized PCB surface defects into 9 distinct categories based on factors such as their causes, locations, and morphologies and developed a dataset of PCB surface defect (DsPCBSD+). In DsPCBSD+, a total of 20,276 defects were annotated manually by bounding boxes on the 10,259 images. This openly accessible dataset is aimed accelerating and promoting further researches and advancements in the field of DL-based detection of PCB surface defect.

Tribological behavior of graphene/h-BN vdW heterostructures: the role of defects at the BN layer

Molecular dynamics simulations and first principles calculations were performed to study the tribological behavior of graphene/h-BN (G/h-BN) heterostructures with vacancy and Stone–Wales (SW) defect under uniform normal load, revealing the mechanism of the effect of defect types on friction, and discussing the coupling effect of temperature and interfacial defects on the tribological behavior of G/h-BN heterostructures. Under the normal force of 0.2 nN/atom, the friction force of the four systems is 0.0057, 0.0096, 0.0077, and 0.26 nN, respectively. The friction force of SW defect heterostructure is 45 times that of perfect interface heterostructure. The influence of defect type on friction force is SW > SV > DV. By observing the dynamic change of the Z-direction coordinate position of the sliding layer atoms, the slip potential energy curves and the evolution law of the moiré pattern, the relationship between the structural morphology and the energy change of different defective heterostructures and the frictional behavior was investigated comprehensively and intuitively for the first time. From the perspective of atomic strain, the deformation of heterostructures at the atomic level was quantified. The results showed that at 300 K and 0 K, the maximum strain of atoms in the sliding layer was 11.25% and 9.85%, respectively. The thermal perturbation mainly occurs in the out-of-plane direction, which in turn affects the friction. Through density functional theory, it is found that under uniform load, it is difficult to form bonds between the graphene sliding layer and the substrate layer when the defects are in the h-BN substrate layer, which has less influence on the friction of the system, thus making the defective heterostructures also remainsuperlubricity state. These results provide a new understanding of the interfacial friction of G/h-BN defective heterostructure.

Acoustic Sensors for Monitoring and Localizing Partial Discharge Signals in Oil-Immersed Transformers under Array Configuration.

Partial discharge (PD) is one of the major causes of insulation accidents in oil-immersed transformers, generating a large number of signals that represent the health status of the transformer. In particular, acoustic signals can be detected by sensors to locate the source of the partial discharge. However, the array, type, and quantity of sensors play a crucial role in the research on the localization of partial discharge sources within transformers. Hence, this paper proposes a novel sensor array for the specific localization of PD sources using COMSOL Multiphysics software 6.1 to establish a three-dimensional model of the oil-immersed transformer and the different defect types of two-dimensional models. "Electric-force-acoustic" multiphysics field simulations were conducted to model ultrasonic signals of different types of PD by setting up detection points to collect acoustic signals at different types and temperatures instead of physical sensors. Subsequently, simulated waveforms and acoustic spatial distribution maps were acquired in the software. These simulation results were then combined with the time difference of arrival (TDOA) algorithm to solve a system of equations, ultimately yielding the position of the discharge source. Calculated positions were compared with the actual positions using an error iterative algorithm method, with an average spatial error about 1.3 cm, which falls within an acceptable range for fault diagnosis in transformers, validating the accuracy of the proposed method. Therefore, the presented sensor array and computational localization method offer a reliable theoretical basis for fault diagnosis techniques in transformers.

Fabric defect detection based on feature enhancement and complementary neighboring information

Abstract Fabric defect detection is a crucial aspect of quality control in the textile industry. Given the complexities of fabric backgrounds, the high similarity between patterned backgrounds and defects, and the variety of defect scales, we propose a fabric defect detection method based on feature enhancement and complementary neighboring information . The core of this method lies in two main components: the feature enhancement module and the neighboring information complementation strategy. The feature enhancement module includes two sub-modules: similarity feature enhancement(SFE) and edge detail feature enhancement(EDFE). The SFE aims to capture the similarities between features to strengthen the distinction between defects and complex backgrounds, thereby highlighting the correlations among defects and the differences between defects and the background. The EDFE focuses on improving the network's ability to capture the edge details of fabrics, preventing edge information from becoming blurred or lost due to deeper network layers. The neighboring information complementation strategy consists of shallow-level information complementation(SLIC) and top-down information fusion complementation(TDIFC). The SLIC integrates newly introduced shallow features with neighboring features that have a smaller semantic gap, injecting richer detail information into the network. The TDIFC adaptively guides the interaction of information between adjacent feature maps, effectively aggregating multi-scale features to ensure information complementarity between features of different scales. Additionally, to further optimize model performance, we introduced partial convolution(PConv) in the backbone of the feature extraction network. PConv reduces redundant computations and decreases the model's parameter count. Experimental results show that our proposed method achieved an mAP@50 of 82.4%, which is a 6.6% improvement over the baseline model YOLOv8s. The average inference frame rate reached 61.8 FPS, meeting the real-time detection requirements for fabric defects. Moreover, the model demonstrated good generalization capabilities, effectively adapting to detecting defects in different types and colors of fabrics.