Intelligent inspection of transmission lines enables efficient automated fault detection by integrating artificial intelligence,robotics,and other related technologies.It plays a key role in ensuring power grid safety...Intelligent inspection of transmission lines enables efficient automated fault detection by integrating artificial intelligence,robotics,and other related technologies.It plays a key role in ensuring power grid safety,reducing operation and maintenance costs,driving the digital transformation of the power industry,and facilitating the achievement of the dual-carbon goals.This review focuses on vision-based power line inspection,with deep learning as the core perspective to systematically analyze the latest research advancements in this field.Firstly,at the technical foundation level,it elaborates on deep learning algorithms for intelligent transmission line inspection based on image perception,covering object detection algorithms,semantic segmentation algorithms,and other relevant methodologies.Secondly,in application practice,it summarizes deep learning-based intelligent inspection applications across six dimensions—including detection of power insulators and their defects,transmission tower detection,power line feature extraction,metal fitting and defect detection,thermal fault diagnosis of power components,and safety hazard detection in power scenarios,and further lists relevant public datasets.Finally,in response to current challenges,it identifies five key future research directions,such as the deep integration of multiple learning paradigms,multi-modal data fusion,collaborative application of large and small models,cloud-edge-end collaborative integration,and multi-agent cluster control.This paper reviews and analyzes numerous deep learning-based intelligent detectionmethods for aerial images,comprehensively explores the application of deep learning in Unmanned Aerial Vehicle(UAV)inspection scenarios,and thus provides valuable theoretical and practical references for scholars engaged in smart grid automated inspection research.展开更多
Images taken in dim environments frequently exhibit issues like insufficient brightness,noise,color shifts,and loss of detail.These problems pose significant challenges to dark image enhancement tasks.Current approach...Images taken in dim environments frequently exhibit issues like insufficient brightness,noise,color shifts,and loss of detail.These problems pose significant challenges to dark image enhancement tasks.Current approaches,while effective in global illumination modeling,often struggle to simultaneously suppress noise and preserve structural details,especially under heterogeneous lighting.Furthermore,misalignment between luminance and color channels introduces additional challenges to accurate enhancement.In response to the aforementioned difficulties,we introduce a single-stage framework,M2ATNet,using the multi-scale multi-attention and Transformer architecture.First,to address the problems of texture blurring and residual noise,we design a multi-scale multi-attention denoising module(MMAD),which is applied separately to the luminance and color channels to enhance the structural and texture modeling capabilities.Secondly,to solve the non-alignment problem of the luminance and color channels,we introduce the multi-channel feature fusion Transformer(CFFT)module,which effectively recovers the dark details and corrects the color shifts through cross-channel alignment and deep feature interaction.To guide the model to learn more stably and efficiently,we also fuse multiple types of loss functions to form a hybrid loss term.We extensively evaluate the proposed method on various standard datasets,including LOL-v1,LOL-v2,DICM,LIME,and NPE.Evaluation in terms of numerical metrics and visual quality demonstrate that M2ATNet consistently outperforms existing advanced approaches.Ablation studies further confirm the critical roles played by the MMAD and CFFT modules to detail preservation and visual fidelity under challenging illumination-deficient environments.展开更多
Video emotion recognition is widely used due to its alignment with the temporal characteristics of human emotional expression,but existingmodels have significant shortcomings.On the one hand,Transformermultihead self-...Video emotion recognition is widely used due to its alignment with the temporal characteristics of human emotional expression,but existingmodels have significant shortcomings.On the one hand,Transformermultihead self-attention modeling of global temporal dependency has problems of high computational overhead and feature similarity.On the other hand,fixed-size convolution kernels are often used,which have weak perception ability for emotional regions of different scales.Therefore,this paper proposes a video emotion recognition model that combines multi-scale region-aware convolution with temporal interactive sampling.In terms of space,multi-branch large-kernel stripe convolution is used to perceive emotional region features at different scales,and attention weights are generated for each scale feature.In terms of time,multi-layer odd-even down-sampling is performed on the time series,and oddeven sub-sequence interaction is performed to solve the problem of feature similarity,while reducing computational costs due to the linear relationship between sampling and convolution overhead.This paper was tested on CMU-MOSI,CMU-MOSEI,and Hume Reaction.The Acc-2 reached 83.4%,85.2%,and 81.2%,respectively.The experimental results show that the model can significantly improve the accuracy of emotion recognition.展开更多
In a multiple voltage source converter(VSC)system,the nonlinear characteristics of phase-locked loops(PLLs)and their interactions have a significant influence on the synchronization stability of converters.In this pap...In a multiple voltage source converter(VSC)system,the nonlinear characteristics of phase-locked loops(PLLs)and their interactions have a significant influence on the synchronization stability of converters.In this paper,these influences are investigated from the perspective of the time domain.First,a novel time-domain model of the multi-VSC system is obtained by using a multi-scale method.On this basis,a stability criterion is proposed to assess the synchronization stability of the system.Then,the accuracy of the time-domain model and its stability criterion in various conditions are discussed.Moreover,the negative impact of the interaction on the system is quantified.Finally,the above theoretical analysis is also verified in the controller hardware-in-the-loop(CHIL)experiments.展开更多
Camouflaged Object Detection(COD)aims to identify objects that share highly similar patterns—such as texture,intensity,and color—with their surrounding environment.Due to their intrinsic resemblance to the backgroun...Camouflaged Object Detection(COD)aims to identify objects that share highly similar patterns—such as texture,intensity,and color—with their surrounding environment.Due to their intrinsic resemblance to the background,camouflaged objects often exhibit vague boundaries and varying scales,making it challenging to accurately locate targets and delineate their indistinct edges.To address this,we propose a novel camouflaged object detection network called Edge-Guided and Multi-scale Fusion Network(EGMFNet),which leverages edge-guided multi-scale integration for enhanced performance.The model incorporates two innovative components:a Multi-scale Fusion Module(MSFM)and an Edge-Guided Attention Module(EGA).These designs exploit multi-scale features to uncover subtle cues between candidate objects and the background while emphasizing camouflaged object boundaries.Moreover,recognizing the rich contextual information in fused features,we introduce a Dual-Branch Global Context Module(DGCM)to refine features using extensive global context,thereby generatingmore informative representations.Experimental results on four benchmark datasets demonstrate that EGMFNet outperforms state-of-the-art methods across five evaluation metrics.Specifically,on COD10K,our EGMFNet-P improves F_(β)by 4.8 points and reduces mean absolute error(MAE)by 0.006 compared with ZoomNeXt;on NC4K,it achieves a 3.6-point increase in F_(β).OnCAMO and CHAMELEON,it obtains 4.5-point increases in F_(β),respectively.These consistent gains substantiate the superiority and robustness of EGMFNet.展开更多
Accurate and efficient detection of building changes in remote sensing imagery is crucial for urban planning,disaster emergency response,and resource management.However,existing methods face challenges such as spectra...Accurate and efficient detection of building changes in remote sensing imagery is crucial for urban planning,disaster emergency response,and resource management.However,existing methods face challenges such as spectral similarity between buildings and backgrounds,sensor variations,and insufficient computational efficiency.To address these challenges,this paper proposes a novel Multi-scale Efficient Wavelet-based Change Detection Network(MewCDNet),which integrates the advantages of Convolutional Neural Networks and Transformers,balances computational costs,and achieves high-performance building change detection.The network employs EfficientNet-B4 as the backbone for hierarchical feature extraction,integrates multi-level feature maps through a multi-scale fusion strategy,and incorporates two key modules:Cross-temporal Difference Detection(CTDD)and Cross-scale Wavelet Refinement(CSWR).CTDD adopts a dual-branch architecture that combines pixel-wise differencing with semanticaware Euclidean distance weighting to enhance the distinction between true changes and background noise.CSWR integrates Haar-based Discrete Wavelet Transform with multi-head cross-attention mechanisms,enabling cross-scale feature fusion while significantly improving edge localization and suppressing spurious changes.Extensive experiments on four benchmark datasets demonstrate MewCDNet’s superiority over comparison methods:achieving F1 scores of 91.54%on LEVIR,93.70%on WHUCD,and 64.96%on S2Looking for building change detection.Furthermore,MewCDNet exhibits optimal performance on the multi-class⋅SYSU dataset(F1:82.71%),highlighting its exceptional generalization capability.展开更多
Tomato is a major economic crop worldwide,and diseases on tomato leaves can significantly reduce both yield and quality.Traditional manual inspection is inefficient and highly subjective,making it difficult to meet th...Tomato is a major economic crop worldwide,and diseases on tomato leaves can significantly reduce both yield and quality.Traditional manual inspection is inefficient and highly subjective,making it difficult to meet the requirements of early disease identification in complex natural environments.To address this issue,this study proposes an improved YOLO11-based model,YOLO-SPDNet(Scale Sequence Fusion,Position-Channel Attention,and Dual Enhancement Network).The model integrates the SEAM(Self-Ensembling Attention Mechanism)semantic enhancement module,the MLCA(Mixed Local Channel Attention)lightweight attention mechanism,and the SPA(Scale-Position-Detail Awareness)module composed of SSFF(Scale Sequence Feature Fusion),TFE(Triple Feature Encoding),and CPAM(Channel and Position Attention Mechanism).These enhancements strengthen fine-grained lesion detection while maintaining model lightweightness.Experimental results show that YOLO-SPDNet achieves an accuracy of 91.8%,a recall of 86.5%,and an mAP@0.5 of 90.6%on the test set,with a computational complexity of 12.5 GFLOPs.Furthermore,the model reaches a real-time inference speed of 987 FPS,making it suitable for deployment on mobile agricultural terminals and online monitoring systems.Comparative analysis and ablation studies further validate the reliability and practical applicability of the proposed model in complex natural scenes.展开更多
Driven by rapid advances in deep learning,object detection has been widely adopted across diverse application scenarios.However,in low-light conditions,critical visual cues of target objects are severely degraded,posi...Driven by rapid advances in deep learning,object detection has been widely adopted across diverse application scenarios.However,in low-light conditions,critical visual cues of target objects are severely degraded,posing a significant challenge for accurate low-light object detection.Existing methods struggle to preserve discriminative features while maintaining semantic consistency between low-light and normal-light images.For this purpose,this study proposes a DL-YOLO model specially tailored for low-light detection.To mitigate target feature attenuation introduced by repeated downsampling,we design aMulti-Scale FeatureConvolution(MSF-Conv)module that captures rich,multi-level details via multi-scale feature learning,thereby reducing model complexity and computational cost.For feature fusion,we integrated the C3k2-DWRmodule by embedding the Dilation-wise Residual(DWR)mechanism into the 2-core optimized Cross Stage Partial(C3)framework,achieving efficient feature integration.In addition,we replace conventional localization losses with WIoU(Weighted Intersection over Union),which dynamically adjusts gradient gain according to sample quality,thereby improving localization robustness and precision.Experiments on the ExDark dataset demonstrate that DL-YOLO delivers strong low-light detection performance.The relevant code is published at https://github.com/cym0997/DL-YOLO.展开更多
The main cable is the primary load-bearing component of a suspension bridge,continuously exposed to harsh environmental conditions,such as wind and rain,throughout the year.These adverse conditions contribute to varyi...The main cable is the primary load-bearing component of a suspension bridge,continuously exposed to harsh environmental conditions,such as wind and rain,throughout the year.These adverse conditions contribute to varying degrees of degradation and damage to the main cable,necessitating regular inspections to prevent catastrophic failures.Traditional manual inspection methods not only suffer from low efficiency but also pose significant safety risks to personnel.To address these challenges and ensure the safe and effective inspection of suspension bridge main cables,this study introduces a novel cooperative climbing robot,designated as Main Cable Robot Version II(CCRobot-M-II),inspired by the locomotion of the inchworm.The robot employs an alternating opening and closing mechanism of four gripper sets,mimicking the inchworm's movement to achieve efficient crawling along the suspension bridge handrails.This paper provides a comprehensive analysis of the structural design,key components,and motion mechanisms of CCRobot-M-II.A detailed force analysis of the robot's crawling process is also presented,followed by the design of the control system and the development of an efficient motion control algorithm.Laboratory experiments demonstrate that the robot achieves a positional error of 00.64%during crawling,with a maximum average crawling speed of 7.6 m/min.Furthermore,the biomimetic design enables the robot to overcome obstacles up to 30 mm in height and possess the capability to handle suspension bridge cables with spans ranging from 740 to 1100 mm.Finally,CCRobot-M-II successfully conducted an inspection of the main cable on a suspension bridge,marking the world's first successful deployment of a climbing robot for main cable inspection on a suspension bridge.展开更多
The spatial offset of bridge has a significant impact on the safety,comfort,and durability of high-speed railway(HSR)operations,so it is crucial to rapidly and effectively detect the spatial offset of operational HSR ...The spatial offset of bridge has a significant impact on the safety,comfort,and durability of high-speed railway(HSR)operations,so it is crucial to rapidly and effectively detect the spatial offset of operational HSR bridges.Drive-by monitoring of bridge uneven settlement demonstrates significant potential due to its practicality,cost-effectiveness,and efficiency.However,existing drive-by methods for detecting bridge offset have limitations such as reliance on a single data source,low detection accuracy,and the inability to identify lateral deformations of bridges.This paper proposes a novel drive-by inspection method for spatial offset of HSR bridge based on multi-source data fusion of comprehensive inspection train.Firstly,dung beetle optimizer-variational mode decomposition was employed to achieve adaptive decomposition of non-stationary dynamic signals,and explore the hidden temporal relationships in the data.Subsequently,a long short-term memory neural network was developed to achieve feature fusion of multi-source signal and accurate prediction of spatial settlement of HSR bridge.A dataset of track irregularities and CRH380A high-speed train responses was generated using a 3D train-track-bridge interaction model,and the accuracy and effectiveness of the proposed hybrid deep learning model were numerically validated.Finally,the reliability of the proposed drive-by inspection method was further validated by analyzing the actual measurement data obtained from comprehensive inspection train.The research findings indicate that the proposed approach enables rapid and accurate detection of spatial offset in HSR bridge,ensuring the long-term operational safety of HSR bridges.展开更多
Semantic segmentation for mixed scenes of aerial remote sensing and road traffic is one of the key technologies for visual perception of flying cars.The State-of-the-Art(SOTA)semantic segmentation methods have made re...Semantic segmentation for mixed scenes of aerial remote sensing and road traffic is one of the key technologies for visual perception of flying cars.The State-of-the-Art(SOTA)semantic segmentation methods have made remarkable achievements in both fine-grained segmentation and real-time performance.However,when faced with the huge differences in scale and semantic categories brought about by the mixed scenes of aerial remote sensing and road traffic,they still face great challenges and there is little related research.Addressing the above issue,this paper proposes a semantic segmentation model specifically for mixed datasets of aerial remote sensing and road traffic scenes.First,a novel decoding-recoding multi-scale feature iterative refinement structure is proposed,which utilizes the re-integration and continuous enhancement of multi-scale information to effectively deal with the huge scale differences between cross-domain scenes,while using a fully convolutional structure to ensure the lightweight and real-time requirements.Second,a welldesigned cross-window attention mechanism combined with a global information integration decoding block forms an enhanced global context perception,which can effectively capture the long-range dependencies and multi-scale global context information of different scenes,thereby achieving fine-grained semantic segmentation.The proposed method is tested on a large-scale mixed dataset of aerial remote sensing and road traffic scenes.The results confirm that it can effectively deal with the problem of large-scale differences in cross-domain scenes.Its segmentation accuracy surpasses that of the SOTA methods,which meets the real-time requirements.展开更多
The Qingtongxia Irrigation District in Ningxia is an important hydrological and ecological region.To assess its ecological environment quality from 2001 to 2021 across multiple scales and identify driving factors,a mo...The Qingtongxia Irrigation District in Ningxia is an important hydrological and ecological region.To assess its ecological environment quality from 2001 to 2021 across multiple scales and identify driving factors,a modified remote sensing ecological index(MRSEI)was developed by incorporating evapotranspiration.Spatial and temporal patterns were analyzed using the coefficient of variation,spatial autocorrelation,and semi-variogram methods,while influencing factors were explored via the optimal parameter geographical detector model.The MRSEI’s first principal component loadings and rankings aligned with those of RSEI(average contribution:81.31%),effectively reflecting spatiotemporal variations.At sub-irrigation district and landscape scales,ecological quality was slightly lower than at the district level but remained stable.Moderate and good ecological grades accounted for 36.28%and 33.38%of the area,respectively,at the district scale,and the moderate grade reached 70.48%on smaller scales.Spatial heterogeneity intensified with decreasing scale,and human activity lost explanatory power below a 5 km range.Human factors mainly drove ecological differentiation at the district scale,while natural factors dominated at finer scales.The MRSEI offers a novel tool for ecological assessment in arid/semi-arid areas and supports scale-adapted ecological protection strategies.展开更多
Distributed Denial of Service(DDoS)attacks are one of the severe threats to network infrastructure,sometimes bypassing traditional diagnosis algorithms because of their evolving complexity.PresentMachine Learning(ML)t...Distributed Denial of Service(DDoS)attacks are one of the severe threats to network infrastructure,sometimes bypassing traditional diagnosis algorithms because of their evolving complexity.PresentMachine Learning(ML)techniques for DDoS attack diagnosis normally apply network traffic statistical features such as packet sizes and inter-arrival times.However,such techniques sometimes fail to capture complicated relations among various traffic flows.In this paper,we present a new multi-scale ensemble strategy given the Graph Neural Networks(GNNs)for improving DDoS detection.Our technique divides traffic into macro-and micro-level elements,letting various GNN models to get the two corase-scale anomalies and subtle,stealthy attack models.Through modeling network traffic as graph-structured data,GNNs efficiently learn intricate relations among network entities.The proposed ensemble learning algorithm combines the results of several GNNs to improve generalization,robustness,and scalability.Extensive experiments on three benchmark datasets—UNSW-NB15,CICIDS2017,and CICDDoS2019—show that our approach outperforms traditional machine learning and deep learning models in detecting both high-rate and low-rate(stealthy)DDoS attacks,with significant improvements in accuracy and recall.These findings demonstrate the suggested method’s applicability and robustness for real-world implementation in contexts where several DDoS patterns coexist.展开更多
Advanced healthcare monitors for air pollution applications pose a significant challenge in achieving a balance between high-performance filtration and multifunctional smart integration.Electrospinning triboelectric n...Advanced healthcare monitors for air pollution applications pose a significant challenge in achieving a balance between high-performance filtration and multifunctional smart integration.Electrospinning triboelectric nanogenerators(TENG)provide a significant potential for use under such difficult circumstances.We have successfully constructed a high-performance TENG utilizing a novel multi-scale nanofiber architecture.Nylon 66(PA66)and chitosan quaternary ammonium salt(HACC)composites were prepared by electrospinning,and PA66/H multiscale nanofiber membranes composed of nanofibers(≈73 nm)and submicron-fibers(≈123 nm)were formed.PA66/H multi-scale nanofiber membrane as the positive electrode and negative electrode-spun PVDF-HFP nanofiber membrane composed of respiration-driven PVDF-HFP@PA66/H TENG.The resulting PVDF-HFP@PA66/H TENG based air filter utilizes electrostatic adsorption and physical interception mechanisms,achieving PM_(0.3)filtration efficiency over 99%with a pressure drop of only 48 Pa.Besides,PVDF-HFP@PA66/H TENG exhibits excellent stability in high-humidity environments,with filtration efficiency reduced by less than 1%.At the same time,the TENG achieves periodic contact separation through breathing drive to achieve self-power,which can ensure the long-term stability of the filtration efficiency.In addition to the air filtration function,TENG can also monitor health in real time by capturing human breathing signals without external power supply.This integrated system combines high-efficiency air filtration,self-powered operation,and health monitoring,presenting an innovative solution for air purification,smart protective equipment,and portable health monitoring.These findings highlight the potential of this technology for diverse applications,offering a promising direction for advancing multifunctional air filtration systems.展开更多
Defect detection in printed circuit boards(PCB)remains challenging due to the difficulty of identifying small-scale defects,the inefficiency of conventional approaches,and the interference from complex backgrounds.To ...Defect detection in printed circuit boards(PCB)remains challenging due to the difficulty of identifying small-scale defects,the inefficiency of conventional approaches,and the interference from complex backgrounds.To address these issues,this paper proposes SIM-Net,an enhanced detection framework derived from YOLOv11.The model integrates SPDConv to preserve fine-grained features for small object detection,introduces a novel convolutional partial attention module(C2PAM)to suppress redundant background information and highlight salient regions,and employs a multi-scale fusion network(MFN)with a multi-grain contextual module(MGCT)to strengthen contextual representation and accelerate inference.Experimental evaluations demonstrate that SIM-Net achieves 92.4%mAP,92%accuracy,and 89.4%recall with an inference speed of 75.1 FPS,outperforming existing state-of-the-art methods.These results confirm the robustness and real-time applicability of SIM-Net for PCB defect inspection.展开更多
The pore structure of shale oil reservoir significantly affects the occurrence and mobility of hydrocarbons.The potential of a new type of alkaline lake shale oil has been demonstrated,but there are few reports on the...The pore structure of shale oil reservoir significantly affects the occurrence and mobility of hydrocarbons.The potential of a new type of alkaline lake shale oil has been demonstrated,but there are few reports on the pore system of alkaline lake shale,which restricts the efficient exploration and development of shale oil.This study investigates the Fengcheng Formation shale in the Mahu sag of the Junggar Basin,employing methods such as low-temperature nitrogecn adsorption(LTNA),mercury intrusion capillary pressure(MICP),and nuclear magnetic resonance(NMR)to quantitatively characterize the multi-scale pore structure and fractal characteristics of shale,while evaluating the applicability of these methods.Based on a comprehensive analysis of material composition,different pore types,and fractal dimensions,the controlling factors for the development of different pore types and their seepage capacity are discussed.The results indicate that inorganic mineral pores are the main development in alkaline lake shale,with the pore morphology being characterized by slit-like and ink-bottle shapes.The multi-scale pore size distribution(PSD)shows that Ⅱ-micropores(10-100 nm)and mesopores(100–1000 nm)are the main contributors to the pore system.The development of Ⅱ-micropores is associated with feldspar and calcareous minerals,the development of Ⅰ-micropores(<10 nm)and mesopores is related to quartz content,while large pores are mainly found in interlayer fissures of clay minerals.The development of Ⅰ-micropores increases the roughness of pore surface and enhances the adsorption capacity of the pores,while the development of Ⅱ-micropores associated with calcareous minerals hinders pore seepage capacity.Mesopores and macropores(>1000 nm)exhibit good flowability.The high content of siliceous minerals plays a positive role in the pore system of alkaline lake shale.The shale with higher fractal dimension Dmin exhibits greater adsorption capacity,which hinders the accumulation of free-state shale oil.Different types of pore space play different roles in the occurrence of shale oil,with free-state shale oil primarily occurring in micro-fractures and inorganic mineral pores,and the pore size is exceeding 10 nm.展开更多
This paper proposes an approach to determing the optimal cluster spacing for volume fracturing in shale oil reservoirs based on three scales,i.e.microscopic capillary displacement,large-scale core imbibition,and macro...This paper proposes an approach to determing the optimal cluster spacing for volume fracturing in shale oil reservoirs based on three scales,i.e.microscopic capillary displacement,large-scale core imbibition,and macroscopic reservoir nuclear magnetic resonance(NMR)logging.Through flow experiments using capillary with different diameters and lengths,and large-scale core counter-current and dynamic imbibition tests,and combing with the NMR logging data of single wells,a graded optimization criterion for cluster spacing is established.The proposed approach was tested in the shale oil reservoir in the seventh member of the Triassic Yanchang Formation(Change 7 Member),the Ordos Basin.The following findings are obtained.First,in the Chang 7 reservoir,oil in pores smaller than 8μm requires a threshold pressure,and for 2-8μm pores,the movable drainage distance ranges from 0.7 m to 4.6 m under a pressure difference of 27 mPa.Second,the large-scale core imbibition tests show a counter-current imbibition distance of only 10 cm,but a dynamic imbibition distance up to 30 cm.Third,in-situ NMR logging results verified that the post-fracturing matrix drainage radius around fractures is 0-4 m,which is consistent with those of capillary flow experiments and large-scale core imbibition tests.The main pore-size range(2-8μm)of the Chang 7 reservoir corresponds to a permeability interval of(0.1-0.4)×10^(-3)μm^(2).Accordingly,a graded optimization criterion for cluster spacing is proposed as follows:for reservoirs with permeability less than 0.20×10^(-3)μm^(2),the cluster spacing should be reduced to smaller than 4.2 m;for reservoirs with permeability of(0.2-0.4)×10^(-3)μm^(2),the cluster spacing should be designed as 4.2-9.2 m.Field application on a pilot platform,where the cluster spacing was reduced to 4.0-6.0 m,yielded an increased initial oil production by approximately 36.6%over a 100-m horizontal reservoir section as compared with untested similar platforms.展开更多
This study proposes a multi-scale simplified residual convolutional neural network(MS-SRCNN)for the precise prediction of Mg-Nd binary alloy compositions from scanning electron microscope(SEM)images.A multi-scale data...This study proposes a multi-scale simplified residual convolutional neural network(MS-SRCNN)for the precise prediction of Mg-Nd binary alloy compositions from scanning electron microscope(SEM)images.A multi-scale data structure is established by spatially aligning and stacking SEM images at different magnifications.The MS-SRCNN significantly reduces computational runtime by over 90%compared to traditional architectures like ResNet50,VGG16,and VGG19,without compromising prediction accuracy.The model demonstrates more excellent predictive performance,achieving a>5%increase in R^(2) compared to single-scale models.Furthermore,the MS-SRCNN exhibits robust composition prediction capability across other Mg-based binary alloys,including Mg-La,Mg-Sn,Mg-Ce,Mg-Sm,Mg-Ag,and Mg-Y,thereby emphasizing its generalization and extrapolation potential.This research establishes a non-destructive,microstructure-informed composition analysis framework,reduces characterization time compared to traditional experiment methods and provides insights into the composition-microstructure relationship in diverse material systems.展开更多
With the increasing complexity of substation inspection tasks,achieving efficient and safe path planning for Unmanned Aerial Vehicles in densely populated and structurally complex three-dimensional(3D)environments rem...With the increasing complexity of substation inspection tasks,achieving efficient and safe path planning for Unmanned Aerial Vehicles in densely populated and structurally complex three-dimensional(3D)environments remains a critical challenge.To address this problem,this paper proposes an improved path planning algorithm—Random Geometric Graph(RGG)-guided Rapidly-exploring Random Tree(R-RRT)—based on the classical Rapidly-exploring Random Tree(RRT)framework.First,a refined 3D occupancy grid map is constructed from Light Detection and Ranging point cloud data through ground filtering,noise removal,coordinate transformation,and obstacle inflation using spherical structuring elements.During the planning stage,a dynamic goal-biasing strategy is introduced to adaptively adjust the sampling direction,the sampling distribution is optimized using a pre-generated RGG,and collision detection is accelerated via a K-Dimensional Tree structure.After initial trajectory generation,redundant nodes are eliminated via greedy pruning,and a curvature-minimizing gradient-based optimizationmethod is applied to smooth the trajectory.Experimental results conducted in a simulated substation environment demonstrate that,compared with mainstream path planning algorithms,the proposed R-RRT achieves superior performance in terms of path length,planning time,and trajectory smoothness.Comprehensive analysis shows that the proposed method significantly enhances trajectory quality,planning efficiency,and operational safety,validating its applicability and advantages for high-precision 3D path planning in complex substation inspection scenarios.展开更多
With the rapid expansion of drone applications,accurate detection of objects in aerial imagery has become crucial for intelligent transportation,urban management,and emergency rescue missions.However,existing methods ...With the rapid expansion of drone applications,accurate detection of objects in aerial imagery has become crucial for intelligent transportation,urban management,and emergency rescue missions.However,existing methods face numerous challenges in practical deployment,including scale variation handling,feature degradation,and complex backgrounds.To address these issues,we propose Edge-enhanced and Detail-Capturing You Only Look Once(EHDC-YOLO),a novel framework for object detection in Unmanned Aerial Vehicle(UAV)imagery.Based on the You Only Look Once version 11 nano(YOLOv11n)baseline,EHDC-YOLO systematically introduces several architectural enhancements:(1)a Multi-Scale Edge Enhancement(MSEE)module that leverages multi-scale pooling and edge information to enhance boundary feature extraction;(2)an Enhanced Feature Pyramid Network(EFPN)that integrates P2-level features with Cross Stage Partial(CSP)structures and OmniKernel convolutions for better fine-grained representation;and(3)Dynamic Head(DyHead)with multi-dimensional attention mechanisms for enhanced cross-scale modeling and perspective adaptability.Comprehensive experiments on the Vision meets Drones for Detection(VisDrone-DET)2019 dataset demonstrate that EHDC-YOLO achieves significant improvements,increasing mean Average Precision(mAP)@0.5 from 33.2%to 46.1%(an absolute improvement of 12.9 percentage points)and mAP@0.5:0.95 from 19.5%to 28.0%(an absolute improvement of 8.5 percentage points)compared with the YOLOv11n baseline,while maintaining a reasonable parameter count(2.81 M vs the baseline’s 2.58 M).Further ablation studies confirm the effectiveness of each proposed component,while visualization results highlight EHDC-YOLO’s superior performance in detecting objects and handling occlusions in complex drone scenarios.展开更多
基金financially supported by theNatural Research Project of College in Anhui Province under grant 2024AH051365,2025AHGXZK30826Research Platform of New Energy and Energy-Saving Technology Research Center under grant KYJG002.
文摘Intelligent inspection of transmission lines enables efficient automated fault detection by integrating artificial intelligence,robotics,and other related technologies.It plays a key role in ensuring power grid safety,reducing operation and maintenance costs,driving the digital transformation of the power industry,and facilitating the achievement of the dual-carbon goals.This review focuses on vision-based power line inspection,with deep learning as the core perspective to systematically analyze the latest research advancements in this field.Firstly,at the technical foundation level,it elaborates on deep learning algorithms for intelligent transmission line inspection based on image perception,covering object detection algorithms,semantic segmentation algorithms,and other relevant methodologies.Secondly,in application practice,it summarizes deep learning-based intelligent inspection applications across six dimensions—including detection of power insulators and their defects,transmission tower detection,power line feature extraction,metal fitting and defect detection,thermal fault diagnosis of power components,and safety hazard detection in power scenarios,and further lists relevant public datasets.Finally,in response to current challenges,it identifies five key future research directions,such as the deep integration of multiple learning paradigms,multi-modal data fusion,collaborative application of large and small models,cloud-edge-end collaborative integration,and multi-agent cluster control.This paper reviews and analyzes numerous deep learning-based intelligent detectionmethods for aerial images,comprehensively explores the application of deep learning in Unmanned Aerial Vehicle(UAV)inspection scenarios,and thus provides valuable theoretical and practical references for scholars engaged in smart grid automated inspection research.
基金funded by the National Natural Science Foundation of China,grant numbers 52374156 and 62476005。
文摘Images taken in dim environments frequently exhibit issues like insufficient brightness,noise,color shifts,and loss of detail.These problems pose significant challenges to dark image enhancement tasks.Current approaches,while effective in global illumination modeling,often struggle to simultaneously suppress noise and preserve structural details,especially under heterogeneous lighting.Furthermore,misalignment between luminance and color channels introduces additional challenges to accurate enhancement.In response to the aforementioned difficulties,we introduce a single-stage framework,M2ATNet,using the multi-scale multi-attention and Transformer architecture.First,to address the problems of texture blurring and residual noise,we design a multi-scale multi-attention denoising module(MMAD),which is applied separately to the luminance and color channels to enhance the structural and texture modeling capabilities.Secondly,to solve the non-alignment problem of the luminance and color channels,we introduce the multi-channel feature fusion Transformer(CFFT)module,which effectively recovers the dark details and corrects the color shifts through cross-channel alignment and deep feature interaction.To guide the model to learn more stably and efficiently,we also fuse multiple types of loss functions to form a hybrid loss term.We extensively evaluate the proposed method on various standard datasets,including LOL-v1,LOL-v2,DICM,LIME,and NPE.Evaluation in terms of numerical metrics and visual quality demonstrate that M2ATNet consistently outperforms existing advanced approaches.Ablation studies further confirm the critical roles played by the MMAD and CFFT modules to detail preservation and visual fidelity under challenging illumination-deficient environments.
基金supported,in part,by the National Nature Science Foundation of China under Grant 62272236,62376128in part,by the Natural Science Foundation of Jiangsu Province under Grant BK20201136,BK20191401.
文摘Video emotion recognition is widely used due to its alignment with the temporal characteristics of human emotional expression,but existingmodels have significant shortcomings.On the one hand,Transformermultihead self-attention modeling of global temporal dependency has problems of high computational overhead and feature similarity.On the other hand,fixed-size convolution kernels are often used,which have weak perception ability for emotional regions of different scales.Therefore,this paper proposes a video emotion recognition model that combines multi-scale region-aware convolution with temporal interactive sampling.In terms of space,multi-branch large-kernel stripe convolution is used to perceive emotional region features at different scales,and attention weights are generated for each scale feature.In terms of time,multi-layer odd-even down-sampling is performed on the time series,and oddeven sub-sequence interaction is performed to solve the problem of feature similarity,while reducing computational costs due to the linear relationship between sampling and convolution overhead.This paper was tested on CMU-MOSI,CMU-MOSEI,and Hume Reaction.The Acc-2 reached 83.4%,85.2%,and 81.2%,respectively.The experimental results show that the model can significantly improve the accuracy of emotion recognition.
基金supported by the Science and Technology Project of State Grid Corporation of China(5400-202199281A-0-0-00).
文摘In a multiple voltage source converter(VSC)system,the nonlinear characteristics of phase-locked loops(PLLs)and their interactions have a significant influence on the synchronization stability of converters.In this paper,these influences are investigated from the perspective of the time domain.First,a novel time-domain model of the multi-VSC system is obtained by using a multi-scale method.On this basis,a stability criterion is proposed to assess the synchronization stability of the system.Then,the accuracy of the time-domain model and its stability criterion in various conditions are discussed.Moreover,the negative impact of the interaction on the system is quantified.Finally,the above theoretical analysis is also verified in the controller hardware-in-the-loop(CHIL)experiments.
基金financially supported byChongqingUniversity of Technology Graduate Innovation Foundation(Grant No.gzlcx20253267).
文摘Camouflaged Object Detection(COD)aims to identify objects that share highly similar patterns—such as texture,intensity,and color—with their surrounding environment.Due to their intrinsic resemblance to the background,camouflaged objects often exhibit vague boundaries and varying scales,making it challenging to accurately locate targets and delineate their indistinct edges.To address this,we propose a novel camouflaged object detection network called Edge-Guided and Multi-scale Fusion Network(EGMFNet),which leverages edge-guided multi-scale integration for enhanced performance.The model incorporates two innovative components:a Multi-scale Fusion Module(MSFM)and an Edge-Guided Attention Module(EGA).These designs exploit multi-scale features to uncover subtle cues between candidate objects and the background while emphasizing camouflaged object boundaries.Moreover,recognizing the rich contextual information in fused features,we introduce a Dual-Branch Global Context Module(DGCM)to refine features using extensive global context,thereby generatingmore informative representations.Experimental results on four benchmark datasets demonstrate that EGMFNet outperforms state-of-the-art methods across five evaluation metrics.Specifically,on COD10K,our EGMFNet-P improves F_(β)by 4.8 points and reduces mean absolute error(MAE)by 0.006 compared with ZoomNeXt;on NC4K,it achieves a 3.6-point increase in F_(β).OnCAMO and CHAMELEON,it obtains 4.5-point increases in F_(β),respectively.These consistent gains substantiate the superiority and robustness of EGMFNet.
基金supported by the Henan Province Key R&D Project under Grant 241111210400the Henan Provincial Science and Technology Research Project under Grants 252102211047,252102211062,252102211055 and 232102210069+2 种基金the Jiangsu Provincial Scheme Double Initiative Plan JSS-CBS20230474,the XJTLU RDF-21-02-008the Science and Technology Innovation Project of Zhengzhou University of Light Industry under Grant 23XNKJTD0205the Higher Education Teaching Reform Research and Practice Project of Henan Province under Grant 2024SJGLX0126。
文摘Accurate and efficient detection of building changes in remote sensing imagery is crucial for urban planning,disaster emergency response,and resource management.However,existing methods face challenges such as spectral similarity between buildings and backgrounds,sensor variations,and insufficient computational efficiency.To address these challenges,this paper proposes a novel Multi-scale Efficient Wavelet-based Change Detection Network(MewCDNet),which integrates the advantages of Convolutional Neural Networks and Transformers,balances computational costs,and achieves high-performance building change detection.The network employs EfficientNet-B4 as the backbone for hierarchical feature extraction,integrates multi-level feature maps through a multi-scale fusion strategy,and incorporates two key modules:Cross-temporal Difference Detection(CTDD)and Cross-scale Wavelet Refinement(CSWR).CTDD adopts a dual-branch architecture that combines pixel-wise differencing with semanticaware Euclidean distance weighting to enhance the distinction between true changes and background noise.CSWR integrates Haar-based Discrete Wavelet Transform with multi-head cross-attention mechanisms,enabling cross-scale feature fusion while significantly improving edge localization and suppressing spurious changes.Extensive experiments on four benchmark datasets demonstrate MewCDNet’s superiority over comparison methods:achieving F1 scores of 91.54%on LEVIR,93.70%on WHUCD,and 64.96%on S2Looking for building change detection.Furthermore,MewCDNet exhibits optimal performance on the multi-class⋅SYSU dataset(F1:82.71%),highlighting its exceptional generalization capability.
基金Tianmin Tianyuan Boutique Vegetable Industry Technology Service Station(Grant No.2024120011003081)Development of Environmental Monitoring and Traceability System for Wuqing Agricultural Production Areas(Grant No.2024120011001866)。
文摘Tomato is a major economic crop worldwide,and diseases on tomato leaves can significantly reduce both yield and quality.Traditional manual inspection is inefficient and highly subjective,making it difficult to meet the requirements of early disease identification in complex natural environments.To address this issue,this study proposes an improved YOLO11-based model,YOLO-SPDNet(Scale Sequence Fusion,Position-Channel Attention,and Dual Enhancement Network).The model integrates the SEAM(Self-Ensembling Attention Mechanism)semantic enhancement module,the MLCA(Mixed Local Channel Attention)lightweight attention mechanism,and the SPA(Scale-Position-Detail Awareness)module composed of SSFF(Scale Sequence Feature Fusion),TFE(Triple Feature Encoding),and CPAM(Channel and Position Attention Mechanism).These enhancements strengthen fine-grained lesion detection while maintaining model lightweightness.Experimental results show that YOLO-SPDNet achieves an accuracy of 91.8%,a recall of 86.5%,and an mAP@0.5 of 90.6%on the test set,with a computational complexity of 12.5 GFLOPs.Furthermore,the model reaches a real-time inference speed of 987 FPS,making it suitable for deployment on mobile agricultural terminals and online monitoring systems.Comparative analysis and ablation studies further validate the reliability and practical applicability of the proposed model in complex natural scenes.
文摘Driven by rapid advances in deep learning,object detection has been widely adopted across diverse application scenarios.However,in low-light conditions,critical visual cues of target objects are severely degraded,posing a significant challenge for accurate low-light object detection.Existing methods struggle to preserve discriminative features while maintaining semantic consistency between low-light and normal-light images.For this purpose,this study proposes a DL-YOLO model specially tailored for low-light detection.To mitigate target feature attenuation introduced by repeated downsampling,we design aMulti-Scale FeatureConvolution(MSF-Conv)module that captures rich,multi-level details via multi-scale feature learning,thereby reducing model complexity and computational cost.For feature fusion,we integrated the C3k2-DWRmodule by embedding the Dilation-wise Residual(DWR)mechanism into the 2-core optimized Cross Stage Partial(C3)framework,achieving efficient feature integration.In addition,we replace conventional localization losses with WIoU(Weighted Intersection over Union),which dynamically adjusts gradient gain according to sample quality,thereby improving localization robustness and precision.Experiments on the ExDark dataset demonstrate that DL-YOLO delivers strong low-light detection performance.The relevant code is published at https://github.com/cym0997/DL-YOLO.
基金Shenzhen Science and Technology Program(Grant No.20220817171811004)(Grant No.RCBS20231211090816033)+4 种基金the Major Key Project of PCL,China under Grant PCL2025A13Longgang District,Shenzhen's"Ten-Action Plan"for Supporting Innovation Projects(Grant No.LGKCSDPT2024002,LGKCSDPT2024003,LGKCSDPT2024004)the"Zhiguo"Action of Guangxi Science and Technology Program(Grant No.ZG2503980003)Guangdong S&T Program under(Grant No.2025B0909040003)Guangdong Provincial Leading Talent Program(Grant No.2024TX08Z319).
文摘The main cable is the primary load-bearing component of a suspension bridge,continuously exposed to harsh environmental conditions,such as wind and rain,throughout the year.These adverse conditions contribute to varying degrees of degradation and damage to the main cable,necessitating regular inspections to prevent catastrophic failures.Traditional manual inspection methods not only suffer from low efficiency but also pose significant safety risks to personnel.To address these challenges and ensure the safe and effective inspection of suspension bridge main cables,this study introduces a novel cooperative climbing robot,designated as Main Cable Robot Version II(CCRobot-M-II),inspired by the locomotion of the inchworm.The robot employs an alternating opening and closing mechanism of four gripper sets,mimicking the inchworm's movement to achieve efficient crawling along the suspension bridge handrails.This paper provides a comprehensive analysis of the structural design,key components,and motion mechanisms of CCRobot-M-II.A detailed force analysis of the robot's crawling process is also presented,followed by the design of the control system and the development of an efficient motion control algorithm.Laboratory experiments demonstrate that the robot achieves a positional error of 00.64%during crawling,with a maximum average crawling speed of 7.6 m/min.Furthermore,the biomimetic design enables the robot to overcome obstacles up to 30 mm in height and possess the capability to handle suspension bridge cables with spans ranging from 740 to 1100 mm.Finally,CCRobot-M-II successfully conducted an inspection of the main cable on a suspension bridge,marking the world's first successful deployment of a climbing robot for main cable inspection on a suspension bridge.
基金sponsored by the National Natural Science Foundation of China(Grant No.52178100).
文摘The spatial offset of bridge has a significant impact on the safety,comfort,and durability of high-speed railway(HSR)operations,so it is crucial to rapidly and effectively detect the spatial offset of operational HSR bridges.Drive-by monitoring of bridge uneven settlement demonstrates significant potential due to its practicality,cost-effectiveness,and efficiency.However,existing drive-by methods for detecting bridge offset have limitations such as reliance on a single data source,low detection accuracy,and the inability to identify lateral deformations of bridges.This paper proposes a novel drive-by inspection method for spatial offset of HSR bridge based on multi-source data fusion of comprehensive inspection train.Firstly,dung beetle optimizer-variational mode decomposition was employed to achieve adaptive decomposition of non-stationary dynamic signals,and explore the hidden temporal relationships in the data.Subsequently,a long short-term memory neural network was developed to achieve feature fusion of multi-source signal and accurate prediction of spatial settlement of HSR bridge.A dataset of track irregularities and CRH380A high-speed train responses was generated using a 3D train-track-bridge interaction model,and the accuracy and effectiveness of the proposed hybrid deep learning model were numerically validated.Finally,the reliability of the proposed drive-by inspection method was further validated by analyzing the actual measurement data obtained from comprehensive inspection train.The research findings indicate that the proposed approach enables rapid and accurate detection of spatial offset in HSR bridge,ensuring the long-term operational safety of HSR bridges.
基金supported by the National Key Research and Development of China(No.2022YFB2503400).
文摘Semantic segmentation for mixed scenes of aerial remote sensing and road traffic is one of the key technologies for visual perception of flying cars.The State-of-the-Art(SOTA)semantic segmentation methods have made remarkable achievements in both fine-grained segmentation and real-time performance.However,when faced with the huge differences in scale and semantic categories brought about by the mixed scenes of aerial remote sensing and road traffic,they still face great challenges and there is little related research.Addressing the above issue,this paper proposes a semantic segmentation model specifically for mixed datasets of aerial remote sensing and road traffic scenes.First,a novel decoding-recoding multi-scale feature iterative refinement structure is proposed,which utilizes the re-integration and continuous enhancement of multi-scale information to effectively deal with the huge scale differences between cross-domain scenes,while using a fully convolutional structure to ensure the lightweight and real-time requirements.Second,a welldesigned cross-window attention mechanism combined with a global information integration decoding block forms an enhanced global context perception,which can effectively capture the long-range dependencies and multi-scale global context information of different scenes,thereby achieving fine-grained semantic segmentation.The proposed method is tested on a large-scale mixed dataset of aerial remote sensing and road traffic scenes.The results confirm that it can effectively deal with the problem of large-scale differences in cross-domain scenes.Its segmentation accuracy surpasses that of the SOTA methods,which meets the real-time requirements.
基金National Key Research&Development Program of China,No.2021YFC3201201Ningxia Key Research and Development Program(Special Talents),No.2023BSB03021+1 种基金Natural Science Foundation of Ningxia,No.2023AAC05014University First-Class Discipline Construction Project of Ningxia,No.NXYLXK2021A03。
文摘The Qingtongxia Irrigation District in Ningxia is an important hydrological and ecological region.To assess its ecological environment quality from 2001 to 2021 across multiple scales and identify driving factors,a modified remote sensing ecological index(MRSEI)was developed by incorporating evapotranspiration.Spatial and temporal patterns were analyzed using the coefficient of variation,spatial autocorrelation,and semi-variogram methods,while influencing factors were explored via the optimal parameter geographical detector model.The MRSEI’s first principal component loadings and rankings aligned with those of RSEI(average contribution:81.31%),effectively reflecting spatiotemporal variations.At sub-irrigation district and landscape scales,ecological quality was slightly lower than at the district level but remained stable.Moderate and good ecological grades accounted for 36.28%and 33.38%of the area,respectively,at the district scale,and the moderate grade reached 70.48%on smaller scales.Spatial heterogeneity intensified with decreasing scale,and human activity lost explanatory power below a 5 km range.Human factors mainly drove ecological differentiation at the district scale,while natural factors dominated at finer scales.The MRSEI offers a novel tool for ecological assessment in arid/semi-arid areas and supports scale-adapted ecological protection strategies.
文摘Distributed Denial of Service(DDoS)attacks are one of the severe threats to network infrastructure,sometimes bypassing traditional diagnosis algorithms because of their evolving complexity.PresentMachine Learning(ML)techniques for DDoS attack diagnosis normally apply network traffic statistical features such as packet sizes and inter-arrival times.However,such techniques sometimes fail to capture complicated relations among various traffic flows.In this paper,we present a new multi-scale ensemble strategy given the Graph Neural Networks(GNNs)for improving DDoS detection.Our technique divides traffic into macro-and micro-level elements,letting various GNN models to get the two corase-scale anomalies and subtle,stealthy attack models.Through modeling network traffic as graph-structured data,GNNs efficiently learn intricate relations among network entities.The proposed ensemble learning algorithm combines the results of several GNNs to improve generalization,robustness,and scalability.Extensive experiments on three benchmark datasets—UNSW-NB15,CICIDS2017,and CICDDoS2019—show that our approach outperforms traditional machine learning and deep learning models in detecting both high-rate and low-rate(stealthy)DDoS attacks,with significant improvements in accuracy and recall.These findings demonstrate the suggested method’s applicability and robustness for real-world implementation in contexts where several DDoS patterns coexist.
基金financial support from the National Key Research and Development Program of China(2022YFB3804905)National Natural Science Foundation of China(22375047,22378068,and 22378071)+1 种基金Natural Science Foundation of Fujian Province(2022J01568)111 Project(No.D17005).
文摘Advanced healthcare monitors for air pollution applications pose a significant challenge in achieving a balance between high-performance filtration and multifunctional smart integration.Electrospinning triboelectric nanogenerators(TENG)provide a significant potential for use under such difficult circumstances.We have successfully constructed a high-performance TENG utilizing a novel multi-scale nanofiber architecture.Nylon 66(PA66)and chitosan quaternary ammonium salt(HACC)composites were prepared by electrospinning,and PA66/H multiscale nanofiber membranes composed of nanofibers(≈73 nm)and submicron-fibers(≈123 nm)were formed.PA66/H multi-scale nanofiber membrane as the positive electrode and negative electrode-spun PVDF-HFP nanofiber membrane composed of respiration-driven PVDF-HFP@PA66/H TENG.The resulting PVDF-HFP@PA66/H TENG based air filter utilizes electrostatic adsorption and physical interception mechanisms,achieving PM_(0.3)filtration efficiency over 99%with a pressure drop of only 48 Pa.Besides,PVDF-HFP@PA66/H TENG exhibits excellent stability in high-humidity environments,with filtration efficiency reduced by less than 1%.At the same time,the TENG achieves periodic contact separation through breathing drive to achieve self-power,which can ensure the long-term stability of the filtration efficiency.In addition to the air filtration function,TENG can also monitor health in real time by capturing human breathing signals without external power supply.This integrated system combines high-efficiency air filtration,self-powered operation,and health monitoring,presenting an innovative solution for air purification,smart protective equipment,and portable health monitoring.These findings highlight the potential of this technology for diverse applications,offering a promising direction for advancing multifunctional air filtration systems.
文摘Defect detection in printed circuit boards(PCB)remains challenging due to the difficulty of identifying small-scale defects,the inefficiency of conventional approaches,and the interference from complex backgrounds.To address these issues,this paper proposes SIM-Net,an enhanced detection framework derived from YOLOv11.The model integrates SPDConv to preserve fine-grained features for small object detection,introduces a novel convolutional partial attention module(C2PAM)to suppress redundant background information and highlight salient regions,and employs a multi-scale fusion network(MFN)with a multi-grain contextual module(MGCT)to strengthen contextual representation and accelerate inference.Experimental evaluations demonstrate that SIM-Net achieves 92.4%mAP,92%accuracy,and 89.4%recall with an inference speed of 75.1 FPS,outperforming existing state-of-the-art methods.These results confirm the robustness and real-time applicability of SIM-Net for PCB defect inspection.
基金financially supported by the National Natural Science Foundation of China(Nos.42272137,42202160)AAPG Foundation Grants-in-Aid and the Strategic Cooperation Technology Projecti of CNPC and CUPB(No.ZLZX2020-01-05)。
文摘The pore structure of shale oil reservoir significantly affects the occurrence and mobility of hydrocarbons.The potential of a new type of alkaline lake shale oil has been demonstrated,but there are few reports on the pore system of alkaline lake shale,which restricts the efficient exploration and development of shale oil.This study investigates the Fengcheng Formation shale in the Mahu sag of the Junggar Basin,employing methods such as low-temperature nitrogecn adsorption(LTNA),mercury intrusion capillary pressure(MICP),and nuclear magnetic resonance(NMR)to quantitatively characterize the multi-scale pore structure and fractal characteristics of shale,while evaluating the applicability of these methods.Based on a comprehensive analysis of material composition,different pore types,and fractal dimensions,the controlling factors for the development of different pore types and their seepage capacity are discussed.The results indicate that inorganic mineral pores are the main development in alkaline lake shale,with the pore morphology being characterized by slit-like and ink-bottle shapes.The multi-scale pore size distribution(PSD)shows that Ⅱ-micropores(10-100 nm)and mesopores(100–1000 nm)are the main contributors to the pore system.The development of Ⅱ-micropores is associated with feldspar and calcareous minerals,the development of Ⅰ-micropores(<10 nm)and mesopores is related to quartz content,while large pores are mainly found in interlayer fissures of clay minerals.The development of Ⅰ-micropores increases the roughness of pore surface and enhances the adsorption capacity of the pores,while the development of Ⅱ-micropores associated with calcareous minerals hinders pore seepage capacity.Mesopores and macropores(>1000 nm)exhibit good flowability.The high content of siliceous minerals plays a positive role in the pore system of alkaline lake shale.The shale with higher fractal dimension Dmin exhibits greater adsorption capacity,which hinders the accumulation of free-state shale oil.Different types of pore space play different roles in the occurrence of shale oil,with free-state shale oil primarily occurring in micro-fractures and inorganic mineral pores,and the pore size is exceeding 10 nm.
基金Supported by the China National Oil and Gas Major Project(2025ZD1404800)PetroChina Science and Technology Major Project(2023ZZ15YJ03)CNPC Changqing Oilfield Company Major Special Project(2023DZZ04)。
文摘This paper proposes an approach to determing the optimal cluster spacing for volume fracturing in shale oil reservoirs based on three scales,i.e.microscopic capillary displacement,large-scale core imbibition,and macroscopic reservoir nuclear magnetic resonance(NMR)logging.Through flow experiments using capillary with different diameters and lengths,and large-scale core counter-current and dynamic imbibition tests,and combing with the NMR logging data of single wells,a graded optimization criterion for cluster spacing is established.The proposed approach was tested in the shale oil reservoir in the seventh member of the Triassic Yanchang Formation(Change 7 Member),the Ordos Basin.The following findings are obtained.First,in the Chang 7 reservoir,oil in pores smaller than 8μm requires a threshold pressure,and for 2-8μm pores,the movable drainage distance ranges from 0.7 m to 4.6 m under a pressure difference of 27 mPa.Second,the large-scale core imbibition tests show a counter-current imbibition distance of only 10 cm,but a dynamic imbibition distance up to 30 cm.Third,in-situ NMR logging results verified that the post-fracturing matrix drainage radius around fractures is 0-4 m,which is consistent with those of capillary flow experiments and large-scale core imbibition tests.The main pore-size range(2-8μm)of the Chang 7 reservoir corresponds to a permeability interval of(0.1-0.4)×10^(-3)μm^(2).Accordingly,a graded optimization criterion for cluster spacing is proposed as follows:for reservoirs with permeability less than 0.20×10^(-3)μm^(2),the cluster spacing should be reduced to smaller than 4.2 m;for reservoirs with permeability of(0.2-0.4)×10^(-3)μm^(2),the cluster spacing should be designed as 4.2-9.2 m.Field application on a pilot platform,where the cluster spacing was reduced to 4.0-6.0 m,yielded an increased initial oil production by approximately 36.6%over a 100-m horizontal reservoir section as compared with untested similar platforms.
基金funded by the National Natural Science Foundation of China(No.52204407)the Natural Science Foundation of Jiangsu Province(No.BK20220595)the China Postdoctoral Science Foundation(No.2022M723689).
文摘This study proposes a multi-scale simplified residual convolutional neural network(MS-SRCNN)for the precise prediction of Mg-Nd binary alloy compositions from scanning electron microscope(SEM)images.A multi-scale data structure is established by spatially aligning and stacking SEM images at different magnifications.The MS-SRCNN significantly reduces computational runtime by over 90%compared to traditional architectures like ResNet50,VGG16,and VGG19,without compromising prediction accuracy.The model demonstrates more excellent predictive performance,achieving a>5%increase in R^(2) compared to single-scale models.Furthermore,the MS-SRCNN exhibits robust composition prediction capability across other Mg-based binary alloys,including Mg-La,Mg-Sn,Mg-Ce,Mg-Sm,Mg-Ag,and Mg-Y,thereby emphasizing its generalization and extrapolation potential.This research establishes a non-destructive,microstructure-informed composition analysis framework,reduces characterization time compared to traditional experiment methods and provides insights into the composition-microstructure relationship in diverse material systems.
基金Funding for this research was provided by the Program for Scientific Research Innovation Team in Colleges and Universities of Anhui Province(No.2022AH010095)the Hefei Key Technology R&D“Champion-Based Selection”Project(No.2023SGJ011).
文摘With the increasing complexity of substation inspection tasks,achieving efficient and safe path planning for Unmanned Aerial Vehicles in densely populated and structurally complex three-dimensional(3D)environments remains a critical challenge.To address this problem,this paper proposes an improved path planning algorithm—Random Geometric Graph(RGG)-guided Rapidly-exploring Random Tree(R-RRT)—based on the classical Rapidly-exploring Random Tree(RRT)framework.First,a refined 3D occupancy grid map is constructed from Light Detection and Ranging point cloud data through ground filtering,noise removal,coordinate transformation,and obstacle inflation using spherical structuring elements.During the planning stage,a dynamic goal-biasing strategy is introduced to adaptively adjust the sampling direction,the sampling distribution is optimized using a pre-generated RGG,and collision detection is accelerated via a K-Dimensional Tree structure.After initial trajectory generation,redundant nodes are eliminated via greedy pruning,and a curvature-minimizing gradient-based optimizationmethod is applied to smooth the trajectory.Experimental results conducted in a simulated substation environment demonstrate that,compared with mainstream path planning algorithms,the proposed R-RRT achieves superior performance in terms of path length,planning time,and trajectory smoothness.Comprehensive analysis shows that the proposed method significantly enhances trajectory quality,planning efficiency,and operational safety,validating its applicability and advantages for high-precision 3D path planning in complex substation inspection scenarios.
文摘With the rapid expansion of drone applications,accurate detection of objects in aerial imagery has become crucial for intelligent transportation,urban management,and emergency rescue missions.However,existing methods face numerous challenges in practical deployment,including scale variation handling,feature degradation,and complex backgrounds.To address these issues,we propose Edge-enhanced and Detail-Capturing You Only Look Once(EHDC-YOLO),a novel framework for object detection in Unmanned Aerial Vehicle(UAV)imagery.Based on the You Only Look Once version 11 nano(YOLOv11n)baseline,EHDC-YOLO systematically introduces several architectural enhancements:(1)a Multi-Scale Edge Enhancement(MSEE)module that leverages multi-scale pooling and edge information to enhance boundary feature extraction;(2)an Enhanced Feature Pyramid Network(EFPN)that integrates P2-level features with Cross Stage Partial(CSP)structures and OmniKernel convolutions for better fine-grained representation;and(3)Dynamic Head(DyHead)with multi-dimensional attention mechanisms for enhanced cross-scale modeling and perspective adaptability.Comprehensive experiments on the Vision meets Drones for Detection(VisDrone-DET)2019 dataset demonstrate that EHDC-YOLO achieves significant improvements,increasing mean Average Precision(mAP)@0.5 from 33.2%to 46.1%(an absolute improvement of 12.9 percentage points)and mAP@0.5:0.95 from 19.5%to 28.0%(an absolute improvement of 8.5 percentage points)compared with the YOLOv11n baseline,while maintaining a reasonable parameter count(2.81 M vs the baseline’s 2.58 M).Further ablation studies confirm the effectiveness of each proposed component,while visualization results highlight EHDC-YOLO’s superior performance in detecting objects and handling occlusions in complex drone scenarios.
