Search

Perovskite solar cells (PSCs) suffer from a quick efficiency drop after fabrication, partly due to surface defects, and efficiency can be further enhanced with the passivation of surface defects. Herein, surface passivation is reviewed as a method to improve both the stability and efficiency of PSCs, with an emphasis on the chemical mechanism of surface passivation. Various molecules are utilized as surface passivants, such as halides, Lewis acids and bases, amines (some result in low-dimensional perovskite), and polymers. Multifunctional molecules are a promising group of passivants, as they are capable of passivating multiple defects with various functional groups. This review categorizes these passivants, in addition to considering the potential and limitations of each type of passivant. Additionally, surface passivants for Sn-based PSCs are discussed since this group of PSCs has poor photovoltaic performance compared to their lead-based counterpart due to their severe surface defects. Lastly, future perspectives on the usage of surface passivation as a method to improve the photovoltaic performance of PSCs are addressed to provide a direction for upcoming research and practical applications. [ABSTRACT FROM AUTHOR]

(1) Background: Air rudders are used to control the flight attitude of aircraft, and their surface quality directly affects flight accuracy and safety. (2) Method: Traditional positioning methods can only obtain defect location information at the image level but cannot determine the defect's physical surface position on the air rudder, which lacks guidance for subsequent defect repair. We propose a defect physical surface positioning method based on a camera mapping model. (3) Results: Repeated positioning experiments were conducted on three typical surface defects of the air rudder, with a maximum absolute error of 0.53 mm and a maximum uncertainty of 0.26 mm. Through hardware systems and software development, the real-time positioning function for surface defects on the air rudder was realized, with the maximum axial positioning error for real-time defect positioning being 0.38 mm. (4) Conclusions: The proposed defect positioning method meets the required accuracy, providing a basis for surface defect repair in the air rudder manufacturing process. It also offers a new approach for surface defect positioning in similar products, with engineering application value. [ABSTRACT FROM AUTHOR]

The aim of this investigation was to evaluate the effect of etching protocols on bond strength, surface roughness, and mechanical properties of a zirconia-reinforced lithium silicate (ZLS) CAD/CAM-ceramic. In total, 100 bars (ISO 6872), 75 plaques, and 25 cubes were cut from ZLS blocks(Vita Suprinity®). The surfaces were standardized, crystallized and divided into five groups: 1. control (no/treatment-C), 2. 5%-Hydrofluoric-acid (HF)/20 s (HF5%20s), 3.HF5%60s, 4.HF10%20s, and 5.HF10%60s. Flexural strength (FS) (three-point bending test, 1 mm/min), roughness (Pa), and micro-shear bond-strength (µSBS) tests were performed. The data were statistically analyzed with one-way ANOVA, Tukey's test (p ˂ 0.05) and Weibull (FS data). C showed higher Pa (1.176 ± 0.370 µm) than HF10%60s (0.627 ± 0.236 µm) and all other groups. Groups C and 20 s showed the most irregular surface patterns. The FS results were not influenced by etching protocols, while the Weibull modulus was, with the 5%HF groups being the most reliable (m: 5.63/6.70), while C and HF10%60s (m: 2.78/2.73) were the least reliable. All fractures originated from surface defects on the treated side of specimens. The 5%HF groups showed higher µSBS (20 s: 21.35 ± 4.70 MPa; 60 s: 23.50 ± 4.27 MPa) than the 10%HF groups (20 s: 14.51 ± 2.47 MPa; 60 s: 16.54 ± 3.12 MPa) and C (6.46 ± 2.71 MPa). The most prevalent failure pattern was "mixed" for etched groups, and "adhesive" for C. Etching protocols affect the evaluated properties by roughening materials' surface and, in some cases, regularizing surface defects. The best overall outcomes were achieved when applying 5%HF. [ABSTRACT FROM AUTHOR]

In this study, we utilized Selective Laser Melting (SLM) technology to fabricate a magnesium alloy, and subsequently subject it to micro-arc oxidation treatment. We analyzed and compared the microstructure, elemental distribution, wetting angle, and corrosion resistance of the SLM magnesium alloy both before and after the micro-arc oxidation process. The findings indicate that the SLM magnesium alloy exhibits surface porosity defects ranging from 2% to 3.2%, which significantly influence the morphology and functionality of the resulting film layer formed during the micro-arc oxidation process. These defects manifest as pores on the surface, leading to an uneven distribution of micropores with varying sizes across the layer. The surface roughness of the 3D-printed magnesium alloy exhibits a high roughness value of 180 nanometers. The phosphorus (P) content is lower within the film layer compared to the surface, suggesting that the Mg3(PO4)2 phase predominantly resides on the surface, whereas the interior is primarily composed of MgO. The micro-arc oxidation process enhances the hydrophilicity and corrosion resistance of the SLM magnesium alloy, thereby potentially endowing it with bioactivity. Additionally, the increased surface roughness post-treatment promotes cell proliferation. However, certain inherent defects present in the SLM magnesium alloy samples negatively impact the improvement of their corrosion resistance. [ABSTRACT FROM AUTHOR]

Strip steel surface defect recognition research has important research significance in industrial production. Aiming at the problems of defect feature extraction, slow detection speed, and insufficient datasets, YOLOv5 is improved on the basis of YOLOv5, and the YOLO-LFPD (lightweight fine particle detection) model is proposed. By introducing the RepVGG (Re-param VGG) module, the robustness of the model is enhanced, and the expressive ability of the model is improved. FasterNet is used to replace the backbone network, which ensures accuracy and accelerates the inference speed, making the model more suitable for real-time monitoring. The use of pruning, a GA genetic algorithm with OTA loss function, further reduces the model size while better learning the strip steel defect feature information, thus improving the generalisation ability and accuracy of the model. The experimental results show that the introduction of the RepVGG module and the use of FasterNet can well improve the model performance, with a reduction of 48% in the number of parameters, a reduction of 13% in the number of GFLOPs, an inference time of 77% of the original, and an optimal accuracy compared with the network models in recent years. The experimental results on the NEU-DET dataset show that the accuracy of YOLO-LFPD is improved by 3% to 81.2%, which is better than other models, and provides new ideas and references for the lightweight strip steel surface defect detection scenarios and application deployment. [ABSTRACT FROM AUTHOR]

Perovskite materials are promising for thermochemical energy storage due to their ability to undergo redox cycling over a wide temperature range. Although BaCoO3 exhibits excellent air cycling properties, its heat storage capacity in air remains suboptimal. This study introduces Na into the lattice structure to enhance oxygen vacancy formation and mobility. DFT+U simulations of the surface structure of Na-doped BaCoO3−δ indicate that incorporating Na improves surface stability and facilitates the formation of surface oxygen vacancies. NaxBa1−xCoO3−δ compounds were synthesized using a modified sol–gel method, and their properties were investigated. The experimental results demonstrate that Na doping significantly enhances the redox activity of the material. The heat storage capacity increased by above 50%, with the Na0.0625Ba0.9375CoO3−δ solid solution achieving a heat storage density of up to 341.7 kJ/kg. XPS analysis reveals that Na doping increases the concentration of surface defect oxygen, leading to more active oxygen release sites at high temperatures. This enhancement in redox activity aligns with DFT predictions. During high-temperature cycling, the distribution of Na within the material becomes more uniform, and no performance degradation is observed after 300 cycles. Even after 450 cycles, Na0.0625Ba0.9375CoO3−δ retains over 96% of its initial redox activity, significantly outperforming fresh BaCoO3−δ. These findings elucidate the mechanism by which Na doping enhances the thermochemical heat storage performance of BaCoO3−δ and provide new insights for the design of perovskite-based materials. [ABSTRACT FROM AUTHOR]

Aiming at the problem that the surface defects of blAister tablets are difficult to detect correctly, this paper proposes a detection method based on the improved U2Net. First, the features extracted from the RSU module of U2Net are enhanced and adjusted using the large kernel attention mechanism, so that the U2Net model strengthens its ability to extract defective features. Second, a loss function combining the Gaussian Laplace operator and the cross-entropy function is designed to make the model strengthen its ability to detect edge defects on the surface of blister tablets. Finally, thresholds are adaptively determined using the local mean and OTSU(an adaptive threshold segmentation method) method to improve accuracy. The experimental results show that the method proposed in this paper can reach an average accuracy of 99% and an average precision rate of 96.3%; the model test only takes 50 ms per image, which can meet the rapid detection requirements. Minor surface defects can also be accurately detected, which is better than other algorithmic models of the same type, proving the effectiveness of this method. [ABSTRACT FROM AUTHOR]

Strip steel surface defect detection has become a crucial step in ensuring the quality of strip steel production. To address the issues of low detection accuracy and long detection times in strip steel surface defect detection algorithms caused by varying defect sizes and blurred images during acquisition, this paper proposes a lightweight strip steel surface defect detection network, YOLO-SDS, based on an improved YOLOv8. Firstly, StarNet is utilized to replace the backbone network of YOLOv8, achieving lightweight optimization while maintaining accuracy. Secondly, a lightweight module DWR is introduced into the neck and combined with the C2f feature extraction module to enhance the model's multi-scale feature extraction capability. Finally, an occlusion-aware attention mechanism SEAM is incorporated into the detection head, enabling the model to better capture and process features of occluded objects, thus improving performance in complex scenarios. Experimental results on the open-source NEU-DET dataset show that the improved model reduces parameters by 34.4% compared with the original YOLOv8 algorithm while increasing average detection accuracy by 1.5%. And it shows good generalization performance on the deepPCB dataset. Compared with other defect detection models, YOLO-SDS offers significant advantages in terms of parameter count and detection speed. Additionally, ablation experiments validate the effectiveness of each module. [ABSTRACT FROM AUTHOR]

In industrial manufacturing, metal surface defect detection often suffers from low detection accuracy, high leakage rates, and false detection rates. To address these issues, this paper proposes a novel model named DSL-YOLO for metal surface defect detection. First, we introduce the C2f_DWRB structure by integrating the DWRB module with C2f, enhancing the model's ability to detect small and occluded targets and effectively extract sparse spatial features. Second, we design the SADown module to improve feature extraction in challenging tasks involving blurred images or very small objects. Finally, to further enhance the model's capacity to extract multi-scale features and capture critical image information (such as edges, textures, and shapes) without significantly increasing memory usage and computational cost, we propose the LASPPF structure. Experimental results demonstrate that the improved model achieves significant performance gains on both the GC10-DET and NEU-DET datasets, with a mAP@0.5 increase of 4.2% and 2.6%, respectively. The improvements in detection accuracy highlight the model's ability to address common challenges while maintaining efficiency and feasibility in metal surface defect detection, providing a valuable solution for industrial applications. [ABSTRACT FROM AUTHOR]

To address the challenge of detecting tiny flaws in tile defect detection, a lightweight algorithm for identifying minor defects in tile images has been developed, referred to as CTDD-YOLO. Firstly, CAACSPELAN is proposed as the core component of the backbone network for extracting features of tile defects; secondly, full-dimensional dynamic convolution ODConv is introduced at the end of the backbone network to enhance the model's ability to deal with tiny defects; next, a new neck network, CGRFPN, is proposed to improve the model's ability to represent multi-scale features and enhance the model's ability to recognize small targets in the context of large formats; finally, MPNWD is proposed to optimize the loss function to improve the model's detection accuracy further. Experiments on the Ali Tianchi tile defect detection dataset show that the CTDD-YOLO model not only has a lower number of parameters than the original YOLOv8n but also improves the mAP by 7.2 percentage points, i.e., the proposed model can more accurately recognize and deal with minor surface defects of tiles and can significantly improve the detection effect while maintaining the light weight. [ABSTRACT FROM AUTHOR]

This article delves into optimizing and modeling the input parameters for the selective laser melting (SLM) process on Inconel 625. The primary aim is to investigate the microstructure within the interlayer regions post-process optimization. For this study, 100 layers with a thickness of 40 µm each were produced. Utilizing the design of experiments (DOE) methodology and employing the Response Surface Method (RSM), the SLM process was optimized. Input parameters such as laser power (LP) and hatch distance (HD) were considered, while changes in microhardness and roughness, Ra, were taken as the responses. Sample microstructure and surface alterations were assessed via scanning electron microscopy (SEM) analysis to ascertain how many defects and properties of Inconel 625 can be controlled using DOE. Porosity and lack of fusion, which were due to rapid post-powder melting solidification, prompted detailed analysis of the flaws both on the surfaces of and in terms of the internal aspects of the samples. An understanding of the formation of these imperfections can help refine the process for enhanced integrity and performance of Inconel 625 printed material. Even slight directional changes in the columnar dendrite structures are discernible within the layers. The microstructural characteristics observed in these samples are directly related to the parameters of the SLM process. In this study, the bulk samples achieved a microhardness of 452 HV, with the minimum surface roughness recorded at 9.9 µm. The objective of this research was to use the Response Surface Method (RSM) to optimize the parameters to result in the minimum surface roughness and maximum microhardness of the samples. [ABSTRACT FROM AUTHOR]

The detection of surface defects on wood-based panels plays a crucial role in product quality control. However, due to the complex background and low contrast of defects in wood-based panel images, features extracted by traditional deep learning methods based on spatial domain processing often contain noise and blurred boundaries, which severely affects detection performance. To address these issues, we have proposed a wood-based panel surface defect detection method based on frequency domain transformation and adaptive dynamic downsampling (FDADNet). Specifically, we designed a Multi-axis Frequency Domain Weighted Information Representation Module (MFDW), which effectively decoupled the indistinguishable low-contrast defects from the background in the transform domain. Gaussian filtering was then employed to eliminate noise and blur between the defects and the background. Additionally, to tackle the issue of scale differences in defects that led to difficulties in accurate capture, we designed an Adaptive Dynamic Convolution (ADConv) module for downsampling. This method flexibly compressed and enhanced features, effectively improving the differentiation of the features of objects of varying scales in the transform space, and ultimately achieved effective defect detection. To compensate for the lack of data, we constructed a dataset of wood-based panel surface defects, WBP-DET. The experimental results showed that the proposed FDADNet effectively improved the detection performance of wood-based panel surface defects in complex scenarios, achieving a solid balance between efficiency and accuracy. [ABSTRACT FROM AUTHOR]

Detecting track geometry and rail surface defects using on-board vehicle monitoring systems is a key issue for rail infrastructure managers to increase availability and reliability while reducing the costs associated with monitoring and maintenance. Rail corrugation is one of the most common rail surface defects which grows in almost all metro, conventional and high-speed lines. This paper focuses on the development of a methodology to detect rail corrugation using axle box acceleration measurements acquired on an in-service high-speed vehicle. The main purpose of the proposed methodology is to distinguish the effect of rail corrugation on the accelerations from the other excitations that can be observed in the same wavelength range. For this purpose, the accelerations are analysed by calculating the fast Fourier transform and the spectrogram. Based on the characteristics of each excitation, the effects of modes of vibration, resonances, bridges, switches, and wheel defects are identified. From the remaining effects, which have congruent characteristics, a hypothesis of rail corrugation is formulated. The hypothesis is consolidated with multibody dynamics simulations and by comparing the corrugation indicators provided by the railway infrastructure company. [ABSTRACT FROM AUTHOR]

The use of carbon fiber reinforced polymers (CFRP) is crucial in industries, such as aerospace, automotive, and marine, due to their excellent strength-to-weight ratio and corrosion resistance. However, machining CFRP is challenging due to its abrasive nature, which can cause premature tool wear. Some of the commonly used processes for machining these materials are dry milling and abrasive water jet machining (AWJM), which offer the best alternatives from an environmental point of view. This article presents an analysis of the defects and surface quality obtained in CFRP after machining by AWJM and milling. For this purpose, combinations of relevant parameters have been chosen for each process: cutting speed and tool wear in milling and traverse feed rate and hydraulic pressure in AWJM. The results obtained have been evaluated from two points of view: macroscopically, through the evaluation of delamination, and microscopically, through the study of the roughness in terms of Ra. Furthermore, a discussion on functional, environmental, economic, and social terms has been made between both processes. In summary, each machining process generates a specific type of delamination: Type II in milling and Type I in AWJM. In addition, the best Ra results are obtained for pressures of 1200 bar in AWJM. [ABSTRACT FROM AUTHOR]

Laser metal deposition is a promising way to repair the surface defects of single-crystal components in turbo engines. Understanding the mechanisms and improving the efficiency of the repair have been long-standing problems. In this study, the influence of the substrate orientation on the laser metal deposition (LMD) was investigated and its effect on repair layer-step was examined. LMD experiments were conducted on single crystal superalloys with a normal substrate orientation (001)/[100] and with an optimized substrate orientation (101)/[10 1 ¯ ]. It reveals that the laser cladding with the optimized orientation leads to a larger height of the [001] dendrite region than that with the normal orientation. The calculated results of the growth velocity, thermal gradient, and susceptibility to CET in the dendrite-preferred growth direction indicate that, for the (101)/[10 1 ¯ ] orientation, the [001]/[100] boundary is located at relative high position in each layer, which not only decreases the formation ability of stray grain significantly, but also eliminates the appearance of the maximum susceptibility. This makes the necessary dilution position much higher, and thus, a large cladding step can be selected. Our findings could find potential applications in laser repair of single-crystal components. [ABSTRACT FROM AUTHOR]

The fatigue performance of laser powder bed fusion-fabricated Ti-6Al-4V alloy was investigated using four-point bending testing. Specifically, the effects of keyhole and lack-of-fusion porosities along with various surface roughness parameters, were evaluated in the context of pore circularity and size using 2D optical metallography. Surface roughness of Sa = 15 to 7 microns was examined by SEM, and the corresponding fatigue performance was found to vary by 102 cycles to failure. The S–N curves for the various defects were also correlated with process window examination in laser beam power–velocity (P–V) space. Basquin's stress-life relation was well fitted to the experimental S–N curves for various process parameters except keyhole porosity, indicating reduced importance for LPBF-fabricated Ti-6Al-4V alloy components. [ABSTRACT FROM AUTHOR]

This study investigates the effects of a back plate preheating assistance system and deep rolling (DR) on axial force and tunnel defects during friction stir welding (FSW). Different preheating configurations—advancing side (AS), retreating side (RS), and both sides—were examined to evaluate their impact on axial force reduction, temperature distribution, and defect minimization. Axial force measurements were taken using a dynamometer, and temperature histories were recorded with a thermal camera. The results demonstrate that a preheating temperature of 200 °C is optimal, reducing axial force by 30.24% and enhancing material flow. This temperature also facilitated deeper tool penetration, especially when preheating was applied to both sides. Preheating on the AS resulted in the smallest tunnel defects, reducing defect size by 80.15% on the RS and 96.91% on the AS compared to the non-preheated condition. While DR further reduced tunnel defects, its effectiveness was limited by the proximity of defects to the surface. These findings offer significant insights for improving the FSW process. [ABSTRACT FROM AUTHOR]

Integrating artificial intelligence (AI) technology into student training programs is strategically crucial for developing future professionals with both forward-thinking capabilities and practical skills. This paper uses steel surface defect detection as a case study to propose a simulation-based teaching method grounded in deep learning. The method encompasses the entire process from data preprocessing and model training to validation analysis and innovation optimization with the goal of deepening students' understanding of AI technology and enhancing their ability to apply it to real-world scenarios. We have designed an experimental framework that incorporates the Efficient Multi-Scale Attention (EMA) mechanism into the Backbone network. This approach helps students understand the principles of feature extraction and the core functions of attention mechanisms. Additionally, we introduced a novel architecture—Convolution 3 Dilated Convolution X (C3DX)—into the Neck network. This architecture effectively expands the network's receptive field, improves its ability to capture multi-scale information, and thus enhances defect detection accuracy. Furthermore, the implementation of the Efficient Intersection over Union (EIoU) loss function optimizes the bounding box predictions, further increasing the model's accuracy and robustness. Overall, the teaching design not only ensures that the content remains at the cutting edge of technology but also emphasizes its practicality and operability. This approach enables students to effectively apply theoretical knowledge to real-world engineering projects. [ABSTRACT FROM AUTHOR]

Strip steel serves as a crucial raw material in numerous industries, including aircraft and automobile manufacturing. Surface defects in strip steel can degrade the performance, quality, and appearance of industrial steel products. Detecting surface defects in steel strip products is challenging due to the low contrast between defects and background, small defect targets, as well as significant variations in defect sizes. To address these challenges, a two-stage attention-based feature-enhancement network (TAFENet) is proposed, wherein the first-stage feature-enhancement procedure utilizes an attentional convolutional fusion module with convolution to combine all four-level features and then strengthens the features of different levels via a residual spatial-channel attention connection module (RSC). The second-stage feature-enhancement procedure combines three-level features using an attentional self-attention fusion module and then strengthens the features using a RSC attention module. Experiments on the NEU-DET and GC10-DET datasets demonstrated that the proposed method significantly improved detection accuracy, thereby confirming the effectiveness and generalization capability of the proposed method. [ABSTRACT FROM AUTHOR]

The surfaces of ceramic products are replete with numerous defects, such as those that appear during the diamond grinding of sintered SiAlON ceramics. The defective surface layer is the reason for the low effectiveness of TiZrN coatings under abrasive and fretting wear. An obvious solution is the removal of an up to 4-µm-thick surface layer containing the defects. It was proposed in the present study to etch the layer with fast argon atoms. At the atom energy of 5 keV and a 0.5 mA/cm2 current density, the ions were converted into fast atoms and the sputtering rate for the SiAlON samples reached 20 μm/h. No defects were observed in the microstructures of coatings deposited after beam treatment for half an hour. The treatment reduced the volumetric abrasive wear by five times. The fretting wear was reduced by three to four times. [ABSTRACT FROM AUTHOR]

Pulsed eddy current thermography can detect surface or subsurface defects in steel, but in the process of combining deep learning, it is expensive and inefficient to build a complete sample of defects due to the complexity of the actual industrial environment. Consequently, this study proposes a transfer learning method based on Twin-NMF and combines it with the SimAM attention mechanism to enhance the detection accuracy of the target domain task. First, to address the domain differences between the target domain task and the source domain samples, this study introduces a Twin-NMF transfer method. This approach reconstructs the feature space of both the source and target domains using twin non-negative matrix factorization and employs cosine similarity to measure the correlation between the features of these two domains. Secondly, this study integrates a parameter-free SimAM into the neck of the YOLOv8 model to enhance its capabilities in extracting and classifying steel surface defects, as well as to alleviate the precision collapse phenomenon associated with multi-scale defect recognition. The experimental results show that the proposed Twin-NMF model with SimAM improves the detection accuracy of steel surface defects. Taking NEU-DET and GC10-DET as source domains, respectively, in the ECTI dataset, mAP@0.5 reaches 99.3% and 99.2%, and the detection accuracy reaches 98% and 98.5%. [ABSTRACT FROM AUTHOR]

The appearance quality of fair-faced concrete plays a crucial role in evaluating the engineering quality, as the abundance of small-area bubbles generated during construction diminishes the surface quality of concrete. However, existing methods are plagued by sluggish detection speed and inadequate accuracy. Therefore, this paper proposes an improved method based on YOLOv5 to rapidly and accurately detect small bubble defects on the surface of fair-faced concrete. Firstly, to address the issue of YOLOv5 in generating prior boxes for imbalanced samples, we divide the image preprocessing part into small-, medium-, and large-area intervals corresponding to the number of heads. Additionally, we propose an area-based k-means clustering approach specifically tailored for the anchor boxes within each of these intervals. Moreover, we adjust the number of prior boxes generated by k-means clustering according to the training loss function to adapt to bubbles of different sizes. Then, we introduce the ECA (Efficient Channel Attention) mechanism into the neck part of the model to effectively capture inter-channel interactions and enhance feature representation. Subsequently, we incorporate feature concatenation in the neck part to facilitate the fusion of low-level and high-level features, thereby improving the accuracy and generalization ability of the network. Finally, we construct our own dataset containing 980 images of two classes: cement and bubbles. Comparative experiments are conducted on our dataset using YOLOv5s, YOLOv6s, YOLOxs, and our method. Experimental results demonstrate that the proposed method achieves the highest detection accuracy in terms of mAP0.5, mAP0.75, and mAP0.5:0.95. Compared to YOLOv5s, our method achieves a 7.1% improvement in mAP0.5, a 3.7% improvement in mAP0.75, and a 4.5% improvement in mAP0.5:0.95. [ABSTRACT FROM AUTHOR]

Hydrogen permeation resistance in the welded region of 06Cr18Ni11Ti steel is relatively weak due to surface defects, which need high integrity surface machining. The parameters of the welding material for 06Cr18Ni11Ti steel are currently unavailable, which causes some inconvenience for simulation studies. To fill the lack of 06Cr18Ni11Ti steel weld material parameters in the relevant literature at the present stage, the quasi-static tensile test at different strain rates and notch specimen tensile tests were conducted in this paper and determined the Johnson–Cook (J-C) constitutive model parameters and Johnson–Cook failure model parameters. Subsequently, a multi-grain grinding simulation model was built based on W-M fractal dimension theory by using the determined material parameters. The influence of processing parameters on grinding heat was analyzed. Grinding experiments were conducted to analyze the influence of processing parameters on grinding heat and grinding force. By comparing the simulation and experimental results, it is revealed that the average error is 9.37%, indicating relatively small discrepancy. It is demonstrated that the grinding simulation model built in this paper could efficiently simulate the grinding process, and the determined weld material parameters of 06Cr18Ni11Ti steel have been verified to possess high accuracy and reliability. [ABSTRACT FROM AUTHOR]

This article presents the results of comparative tests of gear wheels based on the contactless and contact measurement methods. Measurements of gear wheels in accuracy classes containing deviations within the range of measurement capabilities of the GOM ATOS II optical scanner are proposed. Elementary deviations of teeth related to the involute profile were analyzed. In undertaking a non-contact gear measurement using the GOM ATOS II scanner, a new method was developed to extract parameters from the point cloud, which were then used to determine the total deviation of the profile. The results of the measurements obtained using the non-contact method were compared with the results obtained with the contact method using the Wenzel WGT 600 four-axis machine specialized for measuring gear wheels. Measurement uncertainty was also compared. The result of the conducted tests is the comparability of results for gear wheels made in accuracy class 10 according to DIN 3961/62. The proposed non-contact method shows the possibility of using it to measure gear wheels commonly used in agricultural and construction machines. The information obtained from comparing the measurement model and the nominal wheel model provides additional information about surface defects of the part which result from the production and operation process. [ABSTRACT FROM AUTHOR]

Rail surface defect detection is vital for railway safety. Traditional methods falter with varying defect sizes and complex backgrounds, while two-stage deep learning models, though accurate, lack real-time capabilities. To overcome these challenges, we propose an enhanced one-stage detection model based on CenterNet. We replace ResNet with ResNeXt and implement a multi-branch structure for better low-level feature extraction. Additionally, we integrate SKNet attention mechanism with the C2f structure from YOLOv8, improving the model's focus on critical image regions and enhancing the detection of minor defects. We also introduce an elliptical Gaussian kernel for size regression loss, better representing the aspect ratio of rail defects. This approach enhances detection accuracy and speeds up training. Our model achieves a mean accuracy (mAP) of 0.952 on the rail defects dataset, outperforming other models with a 6.6% improvement over the original and a 35.5% increase in training speed. These results demonstrate the efficiency and reliability of our method for rail defect detection. [ABSTRACT FROM AUTHOR]

The current object detection algorithm based on CNN makes it difficult to effectively capture the characteristics of subtle defects in online industrial product packaging bags. These defects are often visually similar to the texture or background of normal product packaging bags, and the model cannot effectively distinguish them. In order to deal with these challenges, this paper optimizes and improves the network structure based on YOLOv8 to achieve accurate identification of defects. First, in order to solve the long-tail distribution problem of data, a fuzzy search data enhancement algorithm is introduced to effectively increase the number of samples. Secondly, a joint network of FasterNet and SPD-Conv is proposed to replace the original backbone network of YOLOv8, which effectively reduces the computing load and improves the accuracy of defect identification. In addition, in order to further improve the performance of multiscale feature fusion, a weighted bidirectional feature pyramid network (BiFPN) is introduced, which effectively enhances the model's ability to detect defects at different scales through the fusion of deep information and shallow information. Finally, in order to reduce the sensitivity of the defect position deviation, the NWD loss function is used to optimize the positioning performance of the model better and reduce detection errors caused by position errors. Experimental results show that the FSNB_YOLOv8 model proposed in this paper can reach 98.8% mAP50 accuracy. This success not only verifies the effectiveness of the optimization and improvement of this article's model but also provides an efficient and accurate solution for surface defect detection of industrial product packaging bags on artificial assembly systems. [ABSTRACT FROM AUTHOR]

Printed circuit boards present several challenges to the detection of defects, including targets of insufficient size and distribution, a high level of background noise, and a variety of complex types. These factors contribute to the difficulties encountered by PCB defect detection networks in accurately identifying defects. This paper proposes a less-parametric model, YOLO-RRL, based on the improved YOLOv8 architecture. The YOLO-RRL model incorporates four key improvement modules: The following modules have been incorporated into the proposed model: Robust Feature Downsampling (RFD), Reparameterised Generalised FPN (RepGFPN), Dynamic Upsampler (DySample), and Lightweight Asymmetric Detection Head (LADH-Head). The results of multiple performance metrics evaluation demonstrate that YOLO-RRL enhances the mean accuracy (mAP) by 2.2 percentage points to 95.2%, increases the frame rate (FPS) by 12%, and significantly reduces the number of parameters and the computational complexity, thereby achieving a balance between performance and efficiency. Two datasets, NEU-DET and APSPC, were employed to evaluate the performance of YOLO-RRL. The results indicate that YOLO-RRL exhibits good adaptability. In comparison to existing mainstream inspection models, YOLO-RRL is also more advanced. The YOLO-RRL model is capable of significantly improving production quality and reducing production costs in practical applications while also extending the scope of the inspection system to a wide range of industrial applications. [ABSTRACT FROM AUTHOR]

Applying unmanned aerial vehicles (UAVs) and vision-based analysis methods to detect bridge surface damage significantly improves inspection efficiency, but the existing techniques have difficulty in accurately locating damage, making it difficult to use the results to assess a bridge's degree of deterioration. Therefore, this study proposes a method to generate panoramic bridge surface images using multi-view images captured by UAVs, in order to automatically identify and locate damage. The main contributions are as follows: (1) We propose a UAV-based image-capturing method for various bridge sections to collect close-range, multi-angle, and overlapping images of the surface; (2) we propose a 3D reconstruction method based on multi-view images to reconstruct a textured bridge model, through which an ultra-high resolution panoramic unfolded image of the bridge surface can be obtained by projecting from multiple angles; (3) we applied the Swin Transformer to optimize the YOLOv8 network and improve the detection accuracy of small-scale damages based on the established bridge damage dataset and employed sliding window segmentation to detect damage in the ultra-high resolution panoramic image. The proposed method was applied to detect surface damage on a three-span concrete bridge. The results indicate that this method automatically generates panoramic images of the bridge bottom, deck, and sides with hundreds of millions of pixels and recognizes damage in the panoramas. In addition, the damage detection accuracy reached 98.7%, which is improved by 13.6% when compared with the original network. [ABSTRACT FROM AUTHOR]

In general, patients' opinions on reaching ideal esthetics while restoring dental tissues is one of the most important part of the oral treatment. Unfortunately, discoloration of dental materials may occur due to intrinsic and extrinsic factors. The aim of the study was to evaluate the color stability of frequently used dental resin materials and determine the mechanism of their discoloration. The study used various characterization techniques (optical microscopy, Fourier-transform infrared spectroscopy, low-temperature N2 adsorption, diffuse reflectance spectroscopy, and luminescence) to understand the effect of surface defects on discoloration. The adsorption of model liquids on the surface was confirmed to be related to the increase in BET surface area. The study found that the adsorption of discolorants, such as coffee, tea, and wine, on the surface of the dental material follows the multilayer BET model. When the surface is smooth, the discoloration is usually within acceptable limits, with a maximum of ∆E = 3.3. The discoloration made by tea and demineralized water was within acceptable limits even after 7 days of exposure. [ABSTRACT FROM AUTHOR]

Detecting surface defects in bamboo strips is essential for producing Asian bamboo products. Currently, the detection of surface defects in bamboo strips mainly relies on manual labor. The labor intensity is high, and the detection efficiency is low. Improving the speed and accuracy of identifying bamboo strip defects is crucial in enhancing enterprises' production efficiency. Hence, this research designs a lightweight YOLOv5s neural network algorithm using the Ghost module to identify surface defects of bamboo strips. The research introduces an attention mechanism CA module to improve the recognition ability of the model target; the research also implements a C2f model to enhance the network performance and the surface quality of bamboo strips. The experimental results show that after training with the acquired image dataset, the YOLOv5s model can exert an intelligent detection effect on five common types of defects in bamboo strips, and the Ghost module makes YOLOv5s lightweight, which can effectively reduce model parameters and improve detection speed while maintaining recognition accuracy. Meanwhile, the C2f module and CA module can further leverage the model's ability to identify specific defects in bamboo strips after lightweight improvement. [ABSTRACT FROM AUTHOR]

Pore and crack formation in parts produced by additive manufacturing (AM) processes, such as laser powder bed fusion, is one of the issues associated with AM technology. Surface and subsurface cracks and pores are induced during the printing process, undermining the printed part durability. In-situ detection of defects will enable the real-time or intermittent control of the process, resulting in higher product quality. In this paper, a new eddy current-based probe design is proposed to detect these defects in parts with various defects that mimic pores and cracks in additively manufactured parts. Electromagnetic finite element analyses were carried out to optimize the probe geometry, followed by fabricating a prototype. Artificial defects were seeded in stainless steel plates to assess the feasibility of detecting various flaws with different widths and lengths. The smallest defect detected had a 0.17 mm radius for blind holes and a 0.43 mm notch with a 5 mm length. All the defects were 0.5 mm from the surface, and the probe was placed on the back surface of the defects. The surface roughness of the tested samples was less than 2 µm. The results show promise for detecting defects, indicating a potential application in AM. [ABSTRACT FROM AUTHOR]

Titanium carbide (TiC) coatings were prepared on the surface of AlFeCoCrNiCu high-entropy alloy blocks using electro-spark deposition (ESD). The microhardness and corrosion resistance of the TiC coatings prepared under different voltage and capacitance process parameters were studied. The research shows that the maximum microhardness of the TiC coating on sample 4 (working voltage of 20 V, working capacitance of 1000 μF) is 844.98 HV, which is 81.5% higher than the microhardness of the substrate. This is because the deposition energy increases with the increase in voltage, and the adhesion and aggregation between the coating and the substrate are enhanced, increasing the hardness of the coating. It is worth noting that excessive deposition energy can increase surface defects and reduce the microhardness of the coating surface. Electrochemical testing analysis shows that the corrosion current density of the TiC coating is the lowest (9.475 × 10−7 ± 0.06 × 10−7), and the coating impedance is the highest (2.502 × 103 Ω·com2). The absolute phase angle value is the highest (about 72°). The above indicates that the TiC coating prepared with a working voltage of 20 V and a working capacitance of 1000 μF has better microhardness and corrosion resistance. [ABSTRACT FROM AUTHOR]

Tungsten and its alloys have a high atomic number, high melting temperature, and high thermal conductivity, which make them fairly appropriate for use in nuclear applications in an extremely harsh radioactive environment. In recent years, there has been growing research interest in using additive manufacturing techniques to produce tungsten components with complex structures. However, the critical bottleneck for tungsten engineering manufacturing is the high melting temperature and high ductile-to-brittle transition temperature. In this study, laser powder bed fusion has been studied to produce bulk pure tungsten. And finite element analysis was used to simulate the temperature and stress field during laser irradiation. The as-printed surface as well as transverse sections were observed by optical microscopy and scanning electron microscopy to quantitatively study processing defects. The simulated temperature field suggests small-sized powder is beneficial for homogenous melting and provides guidelines for the selection of laser energy density. The experimental results show that ultra-dense tungsten bulk has been successfully obtained within a volumetric energy density of 200–391 J/mm3. The obtained relative density can be as high as 99.98%. By quantitative analysis of the pores and surface cracks, the relationships of cracks and pores with laser volumetric energy density have been phenomenologically established. The results are beneficial for controlling defects and surface quality in future engineering applications of tungsten components by additive manufacturing. [ABSTRACT FROM AUTHOR]

In this work, we enhanced the U-shaped network and proposed a method for detecting scratches on metal surfaces based on the Metal Surface Defect Detection U-Net (MSDD-UNet). Initially, we integrated a downsampling approach using a Space-To-Depth module and a lightweight channel attention module to address the loss of contextual information in feature maps that results from multiple convolution and pooling operations. Building on this, we developed an improved attention module that utilizes image frequency decomposition and cross-channel self-attention mechanisms, as well as the strengths of convolutional encoders and self-attention blocks. Additionally, this attention module was integrated into the skip connections between the encoder and decoder. The purpose was to capture dense contextual information, highlight small and fine target areas, and assist in localizing micro and fine scratch defects. In response to the severe foreground–background class imbalance in scratch images, a hybrid loss function combining focal loss and D i c e loss was put forward to train the model for precise scratch segmentation. Finally, experiments were conducted on two surface defect datasets. The results reveal that our proposed method is more advantageous than other state-of-the-art scratch segmentation methods. [ABSTRACT FROM AUTHOR]

Addressing issues such as susceptibility to background interference and variability in feature scales of fine-grained defects on metal surfaces, as well as the relatively poor versatility of the baseline model YOLOv8n, this study proposes a YOLO-ADS algorithm for metal surface defect detection. Firstly, a novel CSPNet with Average SPP-Fast Block (ASPPFCSPC) module is proposed to enhance the model's fusion and representation ability between local features and global background information. Secondly, the newly improved module C2f_SimDCNv2 is utilized to improve the ability of the model to extract multi-scale features. Finally, the Space-to-Depth (SPD) layer is introduced to prevent the loss of fine-grained information from small target features and reduce the redundancy between convolution operations. Experimental results demonstrate that the mean Average Precision (mAP) and Precision of the YOLO-ADS algorithm on the steel strip surface defect dataset NEU-DET reach 81.4% and 79.7%, which are severally increased by 3.5% and 6.1%, and the Frames Per Second (FPS) reaches 140.4. Meanwhile, the versatility and robustness of the model are verified on the industrial steel surface defect dataset GC10-DET, the industrial aluminum surface defect dataset APSPC and even the larger public benchmark dataset VOC2012, the mAP is respectively increased by 3.7%, 3.4% and 4.3%. Compared with the mainstream detection algorithms, YOLO-ADS algorithm is ahead of a certain advanced level in detection accuracy while maintaining a good real-time performance, which provides an efficient and feasible solution for the field of metal surface defect detection. [ABSTRACT FROM AUTHOR]

Railways play a pivotal role in national economic development, freight transportation, national defense, and regional connectivity. The detection of rolling contact fatigue (RCF) defects in rail tracks is essential for railway safety and maintenance. Due to its efficiency and non-contact capability in detecting surface and near-surface defects, Eddy Current Pulsed Thermography (ECPT) has garnered significant attention from researchers. However, detecting multi-layer RCF defects remains a challenge. This paper introduces a sweeping Eddy Current Pulsed Thermal-Tomography system (ECPTT) to detect multi-layer RCF defects effectively. This system utilizes varying excitation frequencies to heat defects, altering skin depth and facilitating feature extraction to distinguish multi-layer RCF defects. Skewness and thermographic signal reconstruction (TSR) values are employed as features in the experiments. These features are qualitatively analyzed to differentiate the layers and depths of multi-layer RCF defects. Additionally, five different coils were compared and analyzed quantitatively. The results indicate that the ECPTT system can effectively detect and distinguish multi-layer RCF defects, thereby providing more detailed defect information and enhancing railway safety and maintenance efficiency. [ABSTRACT FROM AUTHOR]

The persistence of Listeria monocytogenes biofilms on equipment surfaces poses a significant risk of cross-contamination, necessitating effective surface decontamination strategies. This study assessed the effectiveness of hurdle treatments combining peroxyacetic acid (PAA) and saturated steam against 7-day-old L. innocua (a non-pathogenic surrogate for L. monocytogenes) biofilms on stainless steel (SS), polyester (PET), and rubber surfaces. Results demonstrated >6 log10 CFU/coupon L. innocua reductions on SS and PET surfaces after PAA (40 ppm, 1 min) followed by steam treatment (100 °C, 6 s). On rubber surfaces, PAA (80 ppm, 1 min) followed by steam treatment (100 °C, 6 s) resulted in ~5 log10 CFU/coupon L. innocua reduction. The presence of apple juice soil reduced the efficacy of hurdle treatments, with PAA (40 ppm, 1 min) and steam exposure (6 s) resulting in 5.6, 5.8, and 4.2 log10 CFU/coupon reductions of L. innocua on SS, PET, and rubber, respectively. The efficacy of this antimicrobial combination was further reduced by surface defects, especially in the presence of organic matter. Nevertheless, the treatment still achieved >5 log10 CFU/coupon reductions of L. innocua on worn SS and PET soiled with apple juice and ~4.5 log10 CFU/coupon reduction on worn, soiled rubber surfaces. These findings highlight that PAA treatments followed by a brief steam exposure are effective strategies for controlling Listeria on food-contact surfaces. [ABSTRACT FROM AUTHOR]

Perovskite solar cells (PSCs) have demonstrated remarkable progress in performance in recent years, which has placed perovskite materials as the leading promising materials for future renewable energy applications. The solvent additive technique in perovskite composition is a simple but effective process used to improve the surface quality of the perovskite layers and to improve the performance and charge transport processes essential to the functions of PSCs. These additives can have a considerable effect on the topography, crystallinity, and surface properties of the perovskite active layer, ultimately influencing the stability of the PSCs. A "two-step spin coating" deposition method to make PSCs in ambient air laboratory conditions was employed. Acetonitrile (ACN) was conventionally utilized as a chemical additive to enhance the performance of PSCs. In this study, our film properties exhibited that the incorporation of ACN in the triple cation perovskite precursor led to the passivation of surface defects and a noticeable increase in the size of the crystal grains of the perovskite films, which led to enhanced stability of devices. The efficiency achieved for PSCs prepared with 10% ACN was 15.35%, which is 30% higher than devices prepared without ACN. In addition, devices prepared with ACN have shown a lower hysteresis index and more stable behavior compared to devices prepared without ACN. This work presents an easy, low-cost method for the fabrication of high performance PSCs prepared under ambient air laboratory conditions. [ABSTRACT FROM AUTHOR]

Cables are vital load-bearing components of cable-stayed bridges. Surface defects can lead to internal corrosion and fracturing, significantly impacting the stability of the bridge structure. The detection of surface defects from bridge cable images faces numerous challenges, including shadow disturbances due to uneven lighting and difficulties in addressing multiscale defect features. To address these challenges, this paper proposes a novel and cost-effective deep learning segmentation network, named Trans-DCN, to detect defects in the surface of the bridge cable. The network leverages an efficient Transformer-based encoder and integrates multiscale features to overcome the limitations associated with local feature inadequacy. The decoder implements an atrous Deformable Convolution (DCN) pyramid and dynamically fuses low-level feature information to perceive the complex distribution of defects. The effectiveness of Trans-DCN is evaluated by comparing it with state-of-the-art segmentation baseline models using a dataset comprising cable bridge defect images. Experimental results demonstrate that our network outperforms the state-of-the-art network SegFormer, achieving a 27.1% reduction in GFLOPs, a 1.2% increase in mean Intersection over Union, and a 1.5% increase in the F1 score. Ablation experiments confirmed the effectiveness of each module within our network, further substantiating the significant validity and advantages of Trans-DCN in the task of bridge cable defect segmentation. The network proposed in this paper provides an effective solution for downstream cable bridge image analysis. [ABSTRACT FROM AUTHOR]

Fused granular fabrication (FGF) is used in industrial applications to manufacture complex parts in a short time frame and with reduced costs. Recently, the overprinting of continuous fibre-reinforced laminates has been discussed to produce high-performance, functional structures. A hybrid process combining FGF with Automated Fibre Placement (AFP) was developed to implement this approach, where an additively manufactured structure is bonded in situ onto a thermoplastic laminate. However, this combination places great demands on process control, especially in the first printing layer. When 3D printing onto a laminate, the height of the first printed layer is decisive to the shear strength of the bonding. Manufacturing-induced surface defects of a laminate, like thermal warpage, gaps, and tape overlaps, can result in deviations from the ideal geometry and thus impair the bonding strength when left uncompensated. This study, therefore, proposes a novel process flow that uses a 3D scan of a laminate to adjust the geometry of the additively manufactured structure to achieve a constant layer height in the 3D print and, thus, constant mechanical properties. For the above-listed surface defects, only thermal warpage was found to have a significant effect on the bonding strength. [ABSTRACT FROM AUTHOR]

The current sorting process for winter jujubes relies heavily on manual labor, lacks uniform sorting standards, and is inefficient. Furthermore, existing devices have simple structures and can only be sorted based on size. This paper introduces a method for detecting surface defects on winter jujubes using convolutional neural networks (CNNs). According to the current situation in the winter jujube industry in Zhanhua District, Binzhou City, Shandong Province, China, we collected winter jujubes with different surface qualities in Zhanhua District; produced a winter jujube dataset containing 2000 winter jujube images; improved it based on the traditional AlexNet model; selected a total of four classical convolutional neural networks, AlexNet, VGG-16, Inception-V3, and ResNet-34, to conduct different learning rate comparison training experiments; and then took the accuracy rate, loss value, and F1-score of the validation set as evaluation indexes while analyzing and discussing the training results of each model. The experimental results show that the improved AlexNet model had the highest accuracy in the binary classification case, with an accuracy of 98% on the validation set; the accuracy of the Inception V3 model reached 97%. In the detailed classification case, the accuracy of the Inception V3 model was 95%. Different models have different performances and different hardware requirements, and different models can be used to build the system according to different needs. This study can provide a theoretical basis and technical reference for researching and developing winter jujube detection devices. [ABSTRACT FROM AUTHOR]

At present, no consensus has been reached on the generation mechanism of anisotropy in materials fabricated by laser powder bed fusion (LPBF), and most attention has been focused on crystallographic texture. In this paper, an analysis and test were carried out on the hardness, defect distribution, residual stress distribution, and microstructure of WE43 magnesium alloy fabricated by LPBF. The results indicate that LPBF WE43 exhibits obvious anisotropy—the hardness HV of X–Z surface (129.9 HV on average) and that of Y–Z surface (130.7 HV on average) are about 33.5% higher than that of X–Y surface (97.6 HV on average), and the endurable load is smaller in the stacking direction Z compared to the X and Y directions. The factors contributing more to the anisotropy are listed as follows in sequence. Firstly, the defect area of the X–Y projection surface is about 13.2% larger than that of the other two surfaces, so this surface shows greatly reduced mechanical properties due to the exponential relationship between the material strength and the number of defects. Secondly, for laser scanning in each layer/time, the residual stress accumulation in the Z direction is higher than that in the X and Y directions, which may directly reduce the mechanical properties of the material. Finally, more fine grains are distributed in X–Z and Y–Z surfaces when comparing them with those in an X–Y surface, and this fine-grain strengthening mechanism also contributes to the anisotropy. After T5 aging heat treatment (250 °C/16 h), a stronger crystallographic texture is formed in the <0001> direction, with the orientation density index increasing from 10.92 to 21.38, and the anisotropy disappearing. This is mainly caused by the enhancement effect of the texture in the <0001> direction on the mechanical properties in the Z direction cancelling out the weakening effect of the defects in the X–Y surface in the Z direction. [ABSTRACT FROM AUTHOR]

Surface defect inspection based on deep learning has demonstrated outstanding performance in improving detection accuracy and model generalization. However, the small scale of defect datasets always limits the application of deep models in industry. Generative models can obtain realistic samples in a very cheap way, which can effectively solve this problem and thus has received widespread attention in recent years. This paper provides a comprehensive analysis and summary of the current studies of surface defect inspection methods proposed between 2022 and 2024. First, according to the use of generative models, these methods are classified into four categories: Variational Auto-Encoders (VAEs), Generative Adversarial Networks (GANs), Diffusion Models (DMs), and multi-models. Second, the research status of surface defect inspection based on generative models in recent years is discussed from four aspects: sample generation, detection objective, inspection task, and learning model. Then, the public datasets and evaluation metrics that are commonly used for surface defect inspection are discussed, and a comparative evaluation of defect inspection methods based on generative models is provided. Finally, this study discusses the existing challenges for the defect inspection methods based on generative models, providing insights for future research. [ABSTRACT FROM AUTHOR]

Rail surface defects typically serve as early indicators of railway malfunctions, which may compromise the quality and corrosion resistance of rails, thereby endangering the safe operation of trains. The timely detection of defects is essential to ensure the safe operation of railways. To improve the classification accuracy of rail surface defect detection, this paper proposes a rail surface defects detection algorithm based on MobileNet-YOLOv7. By integrating lightweight deep learning algorithms into the engineering application of rail surface defect detection, a MobileNetV3 lightweight network is used as the backbone network for YOLOv7 to enhance both speed and accuracy in complex defect extraction. Subsequently, the efficient intersection over union (EIOU) loss function is utilized as the positional loss function to bolster system resilience. Finally, the k-means++ clustering algorithm is applied to obtain new anchor boxes. The experimental results demonstrate the effectiveness of the proposed method, achieving superior detection accuracy compared with traditional algorithms. [ABSTRACT FROM AUTHOR]

A self-aligned focusing schlieren (SAFS) system combines the field of view of a conventional schlieren system with the defocus blur of a focusing schlieren system away from the object plane. It can be assembled in a compact form, measuring 1.2 m (4 ft) in length in the described case. The depth of field is sufficiently shallow to distinguish specific spanwise features in a supersonic flow field within a 76.2 mm (3 in) wide test section. As a result, the boundary-layer perturbations on windows and window-material defects and surface imperfections are blurred. Analytical forms are derived for depth of field and vignetting of the SAFS system. A laser spark velocity measurement in Mach 2 flow is performed by tracking the blast wave of a laser spark using 500 kHz SAFS imaging with a 200 ns optical pulse width. The flow Mach number and stagnation temperature are measured by comparing the blast-wave dynamics to an analytical solution. Additionally, schlieren image velocimetry is performed by analyzing natural flow perturbations in 500 kHz SAFS images using a self-correlation method. Comparing the spectra of gas density perturbations from the core flow and a near-wall region reveals a significant difference, with high-frequency prevalence at the boundary-layer location. [ABSTRACT FROM AUTHOR]

It is of great significance in the field of engineering to repair the surface defects of ZM6 cast magnesium alloy by an arc welding method. Compared with the traditional tungsten inert gas (TIG) welding repair technology, cold metal transfer (CMT) welding repair has the advantages of low heat input, small repair deformation, and high efficiency. It is of great research value to repair the surface defects of ZM6 cast magnesium alloy by CMT welding. In this paper, the effect of CMT welding repair parameters on defect repair forming is systematically studied, and a repair process window free of unfused defects is obtained. The effects of preheating temperature of base material, wire-feeding speed, welding speed, stick-out length of welding wire and shielding gas flow on the spread of magnesium alloy melt and weld formation were investigated by a surface surfacing method. During the welding process, a camera was used to capture images of the arc and droplet features. A pit defect with a depth of 11.5 mm was machined on the surface of the casting, and the effect of five different repair paths on the formation of the repair area was studied. In order to make the repair area have better fusion, reasonable repair parameters are as follows: The preheating temperature range is 310–450 °C, the wire-feeding speed range is 5–7 m/min, the welding speed range is 8–10 mm/s, the stick-out length of the welding wire is 12 mm, the shielding gas flow rate is 20 L/min, and the repair path adopts a continuous linear reciprocating welding path. This study has important significance for guiding the development of CMT repair technology of cast magnesium alloy. [ABSTRACT FROM AUTHOR]

Wood surface defect detection is a challenging task due to the complexity and variability of defect types. To address these challenges, this paper introduces a novel deep learning approach named SiM-YOLO, which is built upon the YOLOv8 object detection framework. A fine-grained convolutional structure, SPD-Conv, is introduced with the aim of preserving detailed defect information during the feature extraction process, thus enabling the model to capture the subtle variations and complex details of wood surface defects. In the feature fusion stage, a SiAFF-PANet-based wood defect feature fusion module is designed to improve the model's ability to focus on local contextual information and enhance defect localization. For classification and regression tasks, the multi-attention detection head (MADH) is employed to capture cross-channel information and the accurate spatial localization of defects. In addition, MPDIoU is employed to optimize the loss function of the model to reduce the leakage of detection due to defect overlap. The experimental results show that SiM-YOLO achieves superior performance compared to the state-of-the-art YOLO algorithm, with a 9.3% improvement in mAP over YOLOX and a 4.3% improvement in mAP over YOLOv8. The Grad-CAM visualization further illustrates that SiM-YOLO provides more accurate defect localization and effectively reduces misdetection and omission issues. This study highlights the effectiveness of SiM-YOLO for wood surface defect detection and offers valuable insights for future research and practical applications in quality control. [ABSTRACT FROM AUTHOR]

Printed circuit board (PCB) surface defect detection is an essential part of the PCB manufacturing process. Currently, advanced CCD or CMOS sensors can capture high-resolution PCB images. However, the existing computer vision approaches for PCB surface defect detection require high computing effort, leading to insufficient efficiency. To this end, this article proposes a local and global context-enhanced lightweight CenterNet (LGCL-CenterNet) to detect PCB surface defects in real time. Specifically, we propose a two-branch lightweight vision transformer module with local and global attention, named LGT, as a complement to extract high-dimension features and leverage context-aware local enhancement after the backbone network. In the local branch, we utilize coordinate attention to aggregate more powerful features of PCB defects with different shapes. In the global branch, Bi-Level Routing Attention with pooling is used to capture long-distance pixel interactions with limited computational cost. Furthermore, a Path Aggregation Network (PANet) feature fusion structure is incorporated to mitigate the loss of shallow features caused by the increase in model depth. Then, we design a lightweight prediction head by using depthwise separable convolutions, which further compresses the computational complexity and parameters while maintaining the detection capability of the model. In the experiment, the LGCL-CenterNet increased the mAP@0.5 by 2% and 1.4%, respectively, in comparison to CenterNet-ResNet18 and YOLOv8s. Meanwhile, our approach requires fewer model parameters (0.542M) than existing techniques. The results show that the proposed method improves both detection accuracy and inference speed and indicate that the LGCL-CenterNet has better real-time performance and robustness. [ABSTRACT FROM AUTHOR]

After injection molding, plastic gears often exhibit surface defects, including those on end faces and tooth surfaces. These defects encompass a wide range of types and possess complex characteristics, which pose challenges for inspection. Current visual inspection systems for plastic gears suffer from limitations such as single-category defect inspection and low accuracy. There is an urgent industry need for a comprehensive and accurate method and system for inspecting defects on plastic gears, with improved inspection capability and higher accuracy. This paper presents an intelligent inspection algorithm network for plastic gear defects (PGD-net), which effectively captures subtle defect features at arbitrary locations on the surface compared to other models. An adaptive sample weighting method is proposed and integrated into an improved Focal-IoU loss function to address the issue of low inspection accuracy caused by imbalanced defect dataset distributions, thus enhancing the regression accuracy for difficult defect categories. CoordConv layers are incorporated into each inspection head to improve the model's generalization capability. Furthermore, a dataset of plastic gear surface defects comprising 16 types of defects is constructed, and our algorithm is trained and tested on this dataset. The PGD-net achieves a comprehensive mean average precision (mAP) value of 95.6% for the 16 defect types. Additionally, an online inspection system is developed based on the PGD-net algorithm, which can be integrated with plastic gear production lines to achieve online full inspection and automatic sorting of plastic gear defects. The entire system has been successfully applied in plastic gear production lines, conducting daily inspections of over 60,000 gears. [ABSTRACT FROM AUTHOR]

Strip steel plays a crucial role in modern industrial production, where enhancing the accuracy and real-time capabilities of surface defect classification is essential. However, acquiring and annotating defect samples for training deep learning models are challenging, further complicated by the presence of redundant information in these samples. These issues hinder the classification of strip steel surface defects. To address these challenges, this paper introduces a high real-time network, ODNet (Orthogonal Decomposition Network), designed for few-shot strip steel surface defect classification. ODNet utilizes ResNet as its backbone and incorporates orthogonal decomposition technology to reduce the feature redundancies. Furthermore, it integrates skip connection to preserve essential correlation information in the samples, preventing excessive elimination. The model optimizes the parameter efficiency by employing Euclidean distance as the classifier. The orthogonal decomposition not only helps reduce redundant image information but also ensures compatibility with the Euclidean distance requirement for orthogonal input. Extensive experiments conducted on the FSC-20 benchmark demonstrate that ODNet achieves superior real-time performance, accuracy, and generalization compared to alternative methods, effectively addressing the challenges of few-shot strip steel surface defect classification. [ABSTRACT FROM AUTHOR]