Microwave reflectometry is a powerful diagnostic that can measure the density profile and localized turbulence with high spatial and temporal resolution and will be used in ITER,so understanding the influence of plasm...Microwave reflectometry is a powerful diagnostic that can measure the density profile and localized turbulence with high spatial and temporal resolution and will be used in ITER,so understanding the influence of plasma perturbations on the reflect signal is important.The characteristics of the reflect signal from profile reflectometry,the time-of-flight(TOF)signal associated with the MHD instabilities,are investigated in EAST.Using a 1D full-wave simulation code by the Finite-DifferenceTime-Domain(FDTD)method,it is well validated that the local density flattening could induce the discontinuity of the simulated TOF signal and an obvious change of reflect amplitude.Experimental TOF signals under different types of MHD instabilities(sawtooth,sawtooth precursors and tearing mode)are studied in detail and show agreement with the simulation.Two new improved algorithms for detecting and localizing the radial positions of the low-order rational surface,the cross-correlation and gradient threshold(CGT)method and the 2D convolutional neural network approach(CNN)are presented for the first time.It is concluded that TOF signal analysis from profile reflectometry can provide a straightforward and localized measurement of the plasma perturbation from the edge to the core simultaneously and may be a complement or correction to the q-profile control,which will be beneficial for the advanced tokamak operation.展开更多
Within today's product development process, various FE-simulations (finite element) for the functional validation of the desired characteristics are made to avoid expensive testing with real components. Those simul...Within today's product development process, various FE-simulations (finite element) for the functional validation of the desired characteristics are made to avoid expensive testing with real components. Those simulations are performed with great effort for discretization, use of simulations conditions, like taking different non-linearities (i.e., material behavior, etc.) into account, to create meaningful results. Despite knowing the effects of deformations occurring during the production processes, always the non-deformed design model of a CAD-system (computer aided design) is used for the FE-simulations. It seems rather doubtful that further refinement of simulation methods makes sense, if the real manufactured geometry of the component is not considered for in the simulation. For an efficient exploit of the potential of simulation methods, an approach has been developed which offers a geometry model for simulation based on the existing CAD-model but with integrated production deviations as soon as a first prototype is at hand by adapting the FE-mesh to the real, 3D surface detected geometry.展开更多
To address the challenges of missed detections in water surface target detection using solely visual algorithms in unmanned surface vehicle(USV)perception,this paper proposes a method based on the fusion of visual and...To address the challenges of missed detections in water surface target detection using solely visual algorithms in unmanned surface vehicle(USV)perception,this paper proposes a method based on the fusion of visual and LiDAR point-cloud projection for water surface target detection.Firstly,the visual recognition component employs an improved YOLOv7 algorithmbased on a self-built dataset for the detection of water surface targets.This algorithm modifies the original YOLOv7 architecture to a Slim-Neck structure,addressing the problemof excessive redundant information during feature extraction in the original YOLOv7 network model.Simultaneously,this modification simplifies the computational burden of the detector,reduces inference time,and maintains accuracy.Secondly,to tackle the issue of sample imbalance in the self-built dataset,slide loss function is introduced.Finally,this paper replaces the original Complete Intersection over Union(CIoU)loss function with the Minimum Point Distance Intersection over Union(MPDIoU)loss function in the YOLOv7 algorithm,which accelerates model learning and enhances robustness.To mitigate the problem of missed recognitions caused by complex water surface conditions in purely visual algorithms,this paper further adopts the fusion of LiDAR and camera data,projecting the threedimensional point-cloud data from LiDAR onto a two-dimensional pixel plane.This significantly reduces the rate of missed detections for water surface targets.展开更多
Printed Circuit Board(PCB)surface tiny defect detection is a difficult task in the integrated circuit industry,especially since the detection of tiny defects on PCB boards with large-size complex circuits has become o...Printed Circuit Board(PCB)surface tiny defect detection is a difficult task in the integrated circuit industry,especially since the detection of tiny defects on PCB boards with large-size complex circuits has become one of the bottlenecks.To improve the performance of PCB surface tiny defects detection,a PCB tiny defects detection model based on an improved attention residual network(YOLOX-AttResNet)is proposed.First,the unsupervised clustering performance of the K-means algorithm is exploited to optimize the channel weights for subsequent operations by feeding the feature mapping into the SENet(Squeeze and Excitation Network)attention network;then the improved K-means-SENet network is fused with the directly mapped edges of the traditional ResNet network to form an augmented residual network(AttResNet);and finally,the AttResNet module is substituted for the traditional ResNet structure in the backbone feature extraction network of mainstream excellent detection models,thus improving the ability to extract small features from the backbone of the target detection network.The results of ablation experiments on a PCB surface defect dataset show that AttResNet is a reliable and efficient module.In Torify the performance of AttResNet for detecting small defects in large-size complex circuit images,a series of comparison experiments are further performed.The results show that the AttResNet module combines well with the five best existing target detection frameworks(YOLOv3,YOLOX,Faster R-CNN,TDD-Net,Cascade R-CNN),and all the combined new models have improved detection accuracy compared to the original model,which suggests that the AttResNet module proposed in this paper can help the detection model to extract target features.Among them,the YOLOX-AttResNet model proposed in this paper performs the best,with the highest accuracy of 98.45% and the detection speed of 36 FPS(Frames Per Second),which meets the accuracy and real-time requirements for the detection of tiny defects on PCB surfaces.This study can provide some new ideas for other real-time online detection tasks of tiny targets with high-resolution images.展开更多
The accumulation of defects on wind turbine blade surfaces can lead to irreversible damage,impacting the aero-dynamic performance of the blades.To address the challenge of detecting and quantifying surface defects on ...The accumulation of defects on wind turbine blade surfaces can lead to irreversible damage,impacting the aero-dynamic performance of the blades.To address the challenge of detecting and quantifying surface defects on wind turbine blades,a blade surface defect detection and quantification method based on an improved Deeplabv3+deep learning model is proposed.Firstly,an improved method for wind turbine blade surface defect detection,utilizing Mobilenetv2 as the backbone feature extraction network,is proposed based on an original Deeplabv3+deep learning model to address the issue of limited robustness.Secondly,through integrating the concept of pre-trained weights from transfer learning and implementing a freeze training strategy,significant improvements have been made to enhance both the training speed and model training accuracy of this deep learning model.Finally,based on segmented blade surface defect images,a method for quantifying blade defects is proposed.This method combines image stitching algorithms to achieve overall quantification and risk assessment of the entire blade.Test results show that the improved Deeplabv3+deep learning model reduces training time by approximately 43.03%compared to the original model,while achieving mAP and MIoU values of 96.87%and 96.93%,respectively.Moreover,it demonstrates robustness in detecting different surface defects on blades across different back-grounds.The application of a blade surface defect quantification method enables the precise quantification of dif-ferent defects and facilitates the assessment of risk levels associated with defect measurements across the entire blade.This method enables non-contact,long-distance,high-precision detection and quantification of surface defects on the blades,providing a reference for assessing surface defects on wind turbine blades.展开更多
In response to the problem of the high cost and low efficiency of traditional water surface litter cleanup through manpower,a lightweight water surface litter detection algorithm based on improved YOLOv5s is proposed ...In response to the problem of the high cost and low efficiency of traditional water surface litter cleanup through manpower,a lightweight water surface litter detection algorithm based on improved YOLOv5s is proposed to provide core technical support for real-time water surface litter detection by water surface litter cleanup vessels.The method reduces network parameters by introducing the deep separable convolution GhostConv in the lightweight network GhostNet to substitute the ordinary convolution in the original YOLOv5s feature extraction and fusion network;introducing the C3Ghost module to substitute the C3 module in the original backbone and neck networks to further reduce computational effort.Using a Convolutional Block Attention Mechanism(CBAM)module in the backbone network to strengthen the network’s ability to extract significant target features from images.Finally,the loss function is optimized using the Focal-EIoU loss func-tion to improve the convergence speed and model accuracy.The experimental results illustrate that the improved algorithm outperforms the original Yolov5s in all aspects of the homemade water surface litter dataset and has certain advantages over some current mainstream algorithms in terms of model size,detection accuracy,and speed,which can deal with the problems of real-time detection of water surface litter in real life.展开更多
Ensuring high product quality is of paramount importance in pharmaceutical drug manufacturing,as it is subject to rigorous regulatory practices.This study presents a research focused on the development of an on-line d...Ensuring high product quality is of paramount importance in pharmaceutical drug manufacturing,as it is subject to rigorous regulatory practices.This study presents a research focused on the development of an on-line detection method and system for identifying surface defects in pharmaceutical products packaged in aluminum-plastic blisters.Firstly,the aluminum-plastic blister packages exhibit multi-scale features and inter-class indistinction.To address this,the deep semantic network with boundary refinement(DSN-BR)model is proposed,which leverages semantic segmentation domain knowledge,to accurately segment the defects in pixel level.Additionally,a specialized image acquisition module that minimizes the impact of ambient light is established,ensuring high-quality image capture.Finally,the image acquisition module,image detection module,and data management module are designed to construct a comprehensive online surface defect detection system.To validate the effectiveness of our approach,we employ a real dataset for instance verification on the implemented system.The experimental results substantiate the outstanding performance of the DSN-BR,achieving the mean intersection over union(MIoU)of 90.5%.Furthermore,the proposed system achieves an inference speed of up to 14.12 f/s,while attaining an F1-Score of 98.25%.These results demonstrate that the system meets the actual needs of the enterprise and provides theoretical and methodological support for intelligent inspection of product surface quality.By standardizing the control process of pharmaceutical manufacturing and improving the management capability of the manufacturing process,our approach holds significant market application prospects.展开更多
Segment Anything Model(SAM)is a cutting-edge model that has shown impressive performance in general object segmentation.The birth of the segment anything is a groundbreaking step towards creating a universal intellige...Segment Anything Model(SAM)is a cutting-edge model that has shown impressive performance in general object segmentation.The birth of the segment anything is a groundbreaking step towards creating a universal intelligent model.Due to its superior performance in general object segmentation,it quickly gained attention and interest.This makes SAM particularly attractive in industrial surface defect segmentation,especially for complex industrial scenes with limited training data.However,its segmentation ability for specific industrial scenes remains unknown.Therefore,in this work,we select three representative and complex industrial surface defect detection scenarios,namely strip steel surface defects,tile surface defects,and rail surface defects,to evaluate the segmentation performance of SAM.Our results show that although SAM has great potential in general object segmentation,it cannot achieve satisfactory performance in complex industrial scenes.Our test results are available at:https://github.com/VDT-2048/SAM-IS.展开更多
Longitudinal cracks are common defects of continuous casting slabs and may lead to serious quality accidents. Image capturing and recognition of hot slabs is an effective way for on-line detection of cracks, and recog...Longitudinal cracks are common defects of continuous casting slabs and may lead to serious quality accidents. Image capturing and recognition of hot slabs is an effective way for on-line detection of cracks, and recognition of cracks is essential because the surface of hot slabs is very complicated. In order to detect the surface longitudinal cracks of the slabs, a new feature extraction method based on Curvelet transform and kernel locality preserving projections (KLPP) is proposed. First, sample images are decomposed into three levels by Curvelet transform. Second, Fourier transform is applied to all sub-band images and the Fourier amplitude spectrum of each sub-band is computed to get features with translational invariance. Third, five kinds of statistical features of the Fourier amplitude spectrum are computed and combined in different forms. Then, KLPP is employed for dimensionality reduction of the obtained 62 types of high-dimensional combined features. Finally, a support vector machine (SVM) is used for sample set classification. Experiments with samples from a real production line of continuous casting slabs show that the algorithm is effective to detect longitudinal cracks, and the classification rate is 91.89%.展开更多
In the surface imaging of underwater structures, long working distance will reduce image quality due to the turbidity of water. To acquire high definition and large field of view(FOV) images for surface detection, a s...In the surface imaging of underwater structures, long working distance will reduce image quality due to the turbidity of water. To acquire high definition and large field of view(FOV) images for surface detection, a short-working-distance underwater imaging system is proposed based on camera array. A multi-view calibration and rectification method is developed. A look-up table(LUT) method and a multi-resolution spline(MRS) method are applied to stitch array images real-time and seamlessly.Experiments both in the air and in the water are conducted. Strength and weakness of the LUT and MRS methods are discussed.Based on the results, the effectiveness in surface detection of underwater structures is verified.展开更多
In the industrial production of expanded thermoplastic polyurethane (E-TPU) midsoles, the surface defects still rely on manual inspection at present, and the eligibility criteria are uneven. Therefore, this paper prop...In the industrial production of expanded thermoplastic polyurethane (E-TPU) midsoles, the surface defects still rely on manual inspection at present, and the eligibility criteria are uneven. Therefore, this paper proposes an E-TPU midsole surface defect detection method based on machine vision to achieve automatic detection and defect classification. The proposed method is divided into three parts: image preprocessing, block defect detection, and linear defect detection. Image preprocessing uses RGB three channel self-inspection to identify scorch and color pollution. Block defect detection uses superpixel segmentation and background prior mining to determine holes, impurities, and dirt. Linear defect detection uses Gabor filter and Hough transform to detect indentation and convex marks. After image preprocessing, block defect detection and linear defect detection are simultaneously performed by parallel computing. The false positive rate (FPR) of the proposed method in this paper is 8.3%, the false negatives rate (FNR) of the hole is 4.7%, the FNR of indentation is 2.1%, and the running time does not exceed 1.6 s. The test results show that this method can quickly and accurately detect various defects in the E-TPU midsole.展开更多
A simple technique for sensitive detection of heroine based on surface- plasmonresonance has been theoretically and experimentally investigated. The experiment was realized by using an anti-MO monoclonal antibody and ...A simple technique for sensitive detection of heroine based on surface- plasmonresonance has been theoretically and experimentally investigated. The experiment was realized by using an anti-MO monoclonal antibody and a morphine (MO)-bovine serum albumin (MOBSA) conjugate (antigen). The reason for using MO-BSA in the detection of heroine was also discussed. MO-BSA was immobilized on a gold thin film of SPR sensor chip by physical adsorption. The configuration of the device is allowed to be further miniaturized, which is required for the construction of a portable SPR device in the application of in-situ analysis.展开更多
For surface defects in electronic water pump shells,the manual detection efficiency is low,prone to misdetection and leak detection,and encounters problems,such as uncertainty.To improve the speed and accuracy of surf...For surface defects in electronic water pump shells,the manual detection efficiency is low,prone to misdetection and leak detection,and encounters problems,such as uncertainty.To improve the speed and accuracy of surface defect detection,a lightweight detection method based on an improved YOLOv5s method is proposed to replace the traditional manual detection methods.In this method,the MobileNetV3 module replaces the backbone network of YOLOv5s,depth-separable convolution is introduced,the parameters and calculations are reduced,and CIoU_Loss is used as the loss function of the boundary box regression to improve its detection accuracy.A dataset of electronic pump shell defects is established,and the performance of the improved method is evaluated by comparing it with that of the original method.The results show that the parameters and FLOPs are reduced by 49.83%and 61.59%,respectively,compared with the original YOLOv5s model,and the detection accuracy is improved by 1.74%,which is an indication of the superiority of the improved method.To further verify the universality of the improved method,it is compared with the results using the original method on the PASCALVOC2007 dataset,which verifies that it yields better performance.In summary,the improved lightweight method can be used for the real-time detection of electronic water pump shell defects.展开更多
The study area is located between the cities of Comitan (16°10'43"N and 92°04'20''W) a city with 150,000 inhabitants and La Esperanza (16°9'15''N and 91°...The study area is located between the cities of Comitan (16°10'43"N and 92°04'20''W) a city with 150,000 inhabitants and La Esperanza (16°9'15''N and 91°52'5''W) a town with 3000 inhabitants. Both weather stations are 30 km from each other in the Chiapas State, México. 54 years of daily records of the series of maximum (<em>t</em><sub>max</sub>) and minimum temperatures (<em>t</em><sub>min</sub>) of the weather station 07205 Comitan that is on top of a house and 30 years of daily records of the weather station 07374 La Esperanza were analyzed. The objective is to analyze the evidence of climate change in the Comitan valley. 2.07% and 19.04% of missing data were filled, respectively, with the WS method. In order to verify homogeneity three methods were used: Standard Normal Homogeneity Test (SNHT), the Von Neumann method and the Buishand method. The heterogeneous series were homogenized using climatol. The trends of <em>t</em><sub>max</sub> and <em>t</em><sub>min</sub> for both weather stations were analyzed by simple linear regression, Sperman’s rho and Mann-Kendall tests. The Mann-Kendal test method confirmed the warming trend at the Comitan station for both variables with <em>Z<sub>MK</sub></em> statistic values equal to 1.57 (statistically not significant) and 4.64 (statistically significant). However, for the Esperanza station, it determined a cooling trend for tmin and a slight non-significant warming for <em>t</em><sub>max</sub> with a <em>Z</em><sub><em>MK</em></sub> statistic of -2.27 (statistically significant) and 1.16 (statistically not significant), for a significance level <em>α</em> = 0.05.展开更多
Surface defects can affect the quality of steel plate.Many methods based on computer vision are currently applied to surface defect detection of steel plate.However,their real-time performance and object detection of ...Surface defects can affect the quality of steel plate.Many methods based on computer vision are currently applied to surface defect detection of steel plate.However,their real-time performance and object detection of small defect are still unsatisfactory.An improved object detection network based on You Only Look One-level Feature(YOLOF)is proposed to show excellent performance in surface defect detection of steel plate,called DLF-YOLOF.First,the anchor-free detector is used to reduce the network hyperparameters.Secondly,deformable convolution network and local spatial attention module are introduced into the feature extraction network to increase the contextual information in the feature maps.Also,the soft non-maximum suppression is used to improve detection accuracy significantly.Finally,data augmentation is performed for small defect objects during training to improve detection accuracy.Experiments show the average precision and average precision for small objects are 42.7%and 33.5%at a detection speed of 62 frames per second on a single GPU,respectively.This shows that DLF-YOLOF has excellent performance to meet the needs of industrial real-time detection.展开更多
Wind turbine blades are prone to failure due to high tip speed,rain,dust and so on.A surface condition detecting approach based on wind turbine blade aerodynamic noise is proposed.On the experimental measurement data,...Wind turbine blades are prone to failure due to high tip speed,rain,dust and so on.A surface condition detecting approach based on wind turbine blade aerodynamic noise is proposed.On the experimental measurement data,variational mode decomposition filtering and Mel spectrogram drawing are conducted first.The Mel spectrogram is divided into two halves based on frequency characteristics and then sent into the convolutional neural network.Gaussian white noise is superimposed on the original signal and the output results are assessed based on score coefficients,considering the complexity of the real environment.The surfaces of Wind turbine blades are classified into four types:standard,attachments,polishing,and serrated trailing edge.The proposed method is evaluated and the detection accuracy in complicated background conditions is found to be 99.59%.In addition to support the differentiation of trained models,utilizing proper score coefficients also permit the screening of unknown types.展开更多
Defect detection assurance on production lines machine-vision-based surface is important in quality This paper presents a fast defect detection method using the weighted least-squares model. We assume that an inspecti...Defect detection assurance on production lines machine-vision-based surface is important in quality This paper presents a fast defect detection method using the weighted least-squares model. We assume that an inspection image can be regarded as a combination of a defect-free template image and a residual image. The defect-free template image is generated from training samples adaptively, and the residual image is the result of the subtraction between each inspection image and corresponding defect-free template image. In the weighted least-squares model, the residual error near the edge is suppressed to reduce the false alarms caused by spatial misalignment. Experiment results on different types of buttons show that the proposed method is robust to illumination vibration and rotation deviation and produces results that are better than those of two other methods.展开更多
An ultra-sensitive and highly selective parathion methyl (PM) detection method by surface plasmon resonance (SPR) combined with molecularly imprinted films (MIF) was developed. The PM-imprinted film was prepared...An ultra-sensitive and highly selective parathion methyl (PM) detection method by surface plasmon resonance (SPR) combined with molecularly imprinted films (MIF) was developed. The PM-imprinted film was prepared by thermo initiated polymerization on the bare Au surface of an SPR sensor chip, Template PM molecules were quickly removed by an organic solution of acetonitrilelacetic acid (9:1, v/v), causing a shift of 0.5° in SPR angle. In the concentrations range of 10^-13-10^-10 mol/L, the refractive index showed a gradual increase with higher concentrations of template PM and the changes of SPR angles were linear with the negative logarithm of PM concentrations. In the experiment, the minimum detectable concentration was 10^-13 mol/L. The selectivity of the thin PM-imprinted film against diuron, tetrachlorvinphose and fenitrothion was examined, but no observable binding was detected. The results in the experiment suggested that the MIF had the advantages of high sensitivity and selectivity.展开更多
A method of detecting dry, icy and wet road surface conditions based on scanniag detection of single wavelength backward power is proposed in this letter. The detector is used to receive the backward scattered power w...A method of detecting dry, icy and wet road surface conditions based on scanniag detection of single wavelength backward power is proposed in this letter. The detector is used to receive the backward scattered power which changes with the incidence angle. The relationship between backward power and incidence angle is used to find out the effective angle range and distinguish method. Experiment and simulation show that it is feasible to classifv these three conditions within incidence angle of 5.3 degree.展开更多
In recent years, modern optical processing technologies, such as single point diamond turning, ion beam etching, and magneto-theological finishing, arc getting break- throughs. Machining precisions of super-smooth opt...In recent years, modern optical processing technologies, such as single point diamond turning, ion beam etching, and magneto-theological finishing, arc getting break- throughs. Machining precisions of super-smooth optics have also been significantly improved. However, with increasing demands for the optical surface quality,展开更多
基金supported by the Open Fund of Magnetic Confinement Laboratory of Anhui Province(No.2023 AMF03005)the China Postdoctoral Science Foundation(No.2021M703256)+4 种基金the Director Funding of Hefei Institutes of Physical Science,Chinese Academy of Sciences(No.YZJJ2022QN16)the National Key R&D Program of China(Nos.2022YFE03050003,2019YFE03080200,2019Y FE03040002,and 2022YFE03070004)National Natural Science Foundation of China(Nos.12075284,12175277,12275315 and 12275311)the National Magnetic Confinement Fusion Science Program of China(No.2022YFE03040001)the Science Foundation of the Institute of Plasma Physics,Chinese Academy of Sciences(No.DSJJ-2021-08)。
文摘Microwave reflectometry is a powerful diagnostic that can measure the density profile and localized turbulence with high spatial and temporal resolution and will be used in ITER,so understanding the influence of plasma perturbations on the reflect signal is important.The characteristics of the reflect signal from profile reflectometry,the time-of-flight(TOF)signal associated with the MHD instabilities,are investigated in EAST.Using a 1D full-wave simulation code by the Finite-DifferenceTime-Domain(FDTD)method,it is well validated that the local density flattening could induce the discontinuity of the simulated TOF signal and an obvious change of reflect amplitude.Experimental TOF signals under different types of MHD instabilities(sawtooth,sawtooth precursors and tearing mode)are studied in detail and show agreement with the simulation.Two new improved algorithms for detecting and localizing the radial positions of the low-order rational surface,the cross-correlation and gradient threshold(CGT)method and the 2D convolutional neural network approach(CNN)are presented for the first time.It is concluded that TOF signal analysis from profile reflectometry can provide a straightforward and localized measurement of the plasma perturbation from the edge to the core simultaneously and may be a complement or correction to the q-profile control,which will be beneficial for the advanced tokamak operation.
文摘Within today's product development process, various FE-simulations (finite element) for the functional validation of the desired characteristics are made to avoid expensive testing with real components. Those simulations are performed with great effort for discretization, use of simulations conditions, like taking different non-linearities (i.e., material behavior, etc.) into account, to create meaningful results. Despite knowing the effects of deformations occurring during the production processes, always the non-deformed design model of a CAD-system (computer aided design) is used for the FE-simulations. It seems rather doubtful that further refinement of simulation methods makes sense, if the real manufactured geometry of the component is not considered for in the simulation. For an efficient exploit of the potential of simulation methods, an approach has been developed which offers a geometry model for simulation based on the existing CAD-model but with integrated production deviations as soon as a first prototype is at hand by adapting the FE-mesh to the real, 3D surface detected geometry.
基金supported by the National Natural Science Foundation of China(No.51876114)the Shanghai Engineering Research Center of Marine Renewable Energy(Grant No.19DZ2254800).
文摘To address the challenges of missed detections in water surface target detection using solely visual algorithms in unmanned surface vehicle(USV)perception,this paper proposes a method based on the fusion of visual and LiDAR point-cloud projection for water surface target detection.Firstly,the visual recognition component employs an improved YOLOv7 algorithmbased on a self-built dataset for the detection of water surface targets.This algorithm modifies the original YOLOv7 architecture to a Slim-Neck structure,addressing the problemof excessive redundant information during feature extraction in the original YOLOv7 network model.Simultaneously,this modification simplifies the computational burden of the detector,reduces inference time,and maintains accuracy.Secondly,to tackle the issue of sample imbalance in the self-built dataset,slide loss function is introduced.Finally,this paper replaces the original Complete Intersection over Union(CIoU)loss function with the Minimum Point Distance Intersection over Union(MPDIoU)loss function in the YOLOv7 algorithm,which accelerates model learning and enhances robustness.To mitigate the problem of missed recognitions caused by complex water surface conditions in purely visual algorithms,this paper further adopts the fusion of LiDAR and camera data,projecting the threedimensional point-cloud data from LiDAR onto a two-dimensional pixel plane.This significantly reduces the rate of missed detections for water surface targets.
基金supported by the National Natural Science Foundation of China(No.61976083)Hubei Province Key R&D Program of China(No.2022BBA0016).
文摘Printed Circuit Board(PCB)surface tiny defect detection is a difficult task in the integrated circuit industry,especially since the detection of tiny defects on PCB boards with large-size complex circuits has become one of the bottlenecks.To improve the performance of PCB surface tiny defects detection,a PCB tiny defects detection model based on an improved attention residual network(YOLOX-AttResNet)is proposed.First,the unsupervised clustering performance of the K-means algorithm is exploited to optimize the channel weights for subsequent operations by feeding the feature mapping into the SENet(Squeeze and Excitation Network)attention network;then the improved K-means-SENet network is fused with the directly mapped edges of the traditional ResNet network to form an augmented residual network(AttResNet);and finally,the AttResNet module is substituted for the traditional ResNet structure in the backbone feature extraction network of mainstream excellent detection models,thus improving the ability to extract small features from the backbone of the target detection network.The results of ablation experiments on a PCB surface defect dataset show that AttResNet is a reliable and efficient module.In Torify the performance of AttResNet for detecting small defects in large-size complex circuit images,a series of comparison experiments are further performed.The results show that the AttResNet module combines well with the five best existing target detection frameworks(YOLOv3,YOLOX,Faster R-CNN,TDD-Net,Cascade R-CNN),and all the combined new models have improved detection accuracy compared to the original model,which suggests that the AttResNet module proposed in this paper can help the detection model to extract target features.Among them,the YOLOX-AttResNet model proposed in this paper performs the best,with the highest accuracy of 98.45% and the detection speed of 36 FPS(Frames Per Second),which meets the accuracy and real-time requirements for the detection of tiny defects on PCB surfaces.This study can provide some new ideas for other real-time online detection tasks of tiny targets with high-resolution images.
基金supported by the National Science Foundation of China(Grant Nos.52068049 and 51908266)the Science Fund for Distinguished Young Scholars of Gansu Province(No.21JR7RA267)Hongliu Outstanding Young Talents Program of Lanzhou University of Technology.
文摘The accumulation of defects on wind turbine blade surfaces can lead to irreversible damage,impacting the aero-dynamic performance of the blades.To address the challenge of detecting and quantifying surface defects on wind turbine blades,a blade surface defect detection and quantification method based on an improved Deeplabv3+deep learning model is proposed.Firstly,an improved method for wind turbine blade surface defect detection,utilizing Mobilenetv2 as the backbone feature extraction network,is proposed based on an original Deeplabv3+deep learning model to address the issue of limited robustness.Secondly,through integrating the concept of pre-trained weights from transfer learning and implementing a freeze training strategy,significant improvements have been made to enhance both the training speed and model training accuracy of this deep learning model.Finally,based on segmented blade surface defect images,a method for quantifying blade defects is proposed.This method combines image stitching algorithms to achieve overall quantification and risk assessment of the entire blade.Test results show that the improved Deeplabv3+deep learning model reduces training time by approximately 43.03%compared to the original model,while achieving mAP and MIoU values of 96.87%and 96.93%,respectively.Moreover,it demonstrates robustness in detecting different surface defects on blades across different back-grounds.The application of a blade surface defect quantification method enables the precise quantification of dif-ferent defects and facilitates the assessment of risk levels associated with defect measurements across the entire blade.This method enables non-contact,long-distance,high-precision detection and quantification of surface defects on the blades,providing a reference for assessing surface defects on wind turbine blades.
基金Support for this work was in part from the China University Industry-University Research Innovation Fund Project(No.2022BL052),author B.T,https://www.cutech.edu.cnin part by the Science and Technology InnovationR&DProject of the State GeneralAdministration of Sports of China(No.22KJCX024),author B.T,https://www.sport.gov.cn+1 种基金in part by the Major Project of Philosophy and Social Science Research in Higher Education Institutions in Hubei Province(No.21ZD054),author B.T,https://jyt.hubei.gov.cnKey Project of Hubei Provincial Key Laboratory of Intelligent Transportation Technology and Equipment Open Fund(No.2022XZ106),author B.T,https://hbpu.edu.cn.
文摘In response to the problem of the high cost and low efficiency of traditional water surface litter cleanup through manpower,a lightweight water surface litter detection algorithm based on improved YOLOv5s is proposed to provide core technical support for real-time water surface litter detection by water surface litter cleanup vessels.The method reduces network parameters by introducing the deep separable convolution GhostConv in the lightweight network GhostNet to substitute the ordinary convolution in the original YOLOv5s feature extraction and fusion network;introducing the C3Ghost module to substitute the C3 module in the original backbone and neck networks to further reduce computational effort.Using a Convolutional Block Attention Mechanism(CBAM)module in the backbone network to strengthen the network’s ability to extract significant target features from images.Finally,the loss function is optimized using the Focal-EIoU loss func-tion to improve the convergence speed and model accuracy.The experimental results illustrate that the improved algorithm outperforms the original Yolov5s in all aspects of the homemade water surface litter dataset and has certain advantages over some current mainstream algorithms in terms of model size,detection accuracy,and speed,which can deal with the problems of real-time detection of water surface litter in real life.
文摘Ensuring high product quality is of paramount importance in pharmaceutical drug manufacturing,as it is subject to rigorous regulatory practices.This study presents a research focused on the development of an on-line detection method and system for identifying surface defects in pharmaceutical products packaged in aluminum-plastic blisters.Firstly,the aluminum-plastic blister packages exhibit multi-scale features and inter-class indistinction.To address this,the deep semantic network with boundary refinement(DSN-BR)model is proposed,which leverages semantic segmentation domain knowledge,to accurately segment the defects in pixel level.Additionally,a specialized image acquisition module that minimizes the impact of ambient light is established,ensuring high-quality image capture.Finally,the image acquisition module,image detection module,and data management module are designed to construct a comprehensive online surface defect detection system.To validate the effectiveness of our approach,we employ a real dataset for instance verification on the implemented system.The experimental results substantiate the outstanding performance of the DSN-BR,achieving the mean intersection over union(MIoU)of 90.5%.Furthermore,the proposed system achieves an inference speed of up to 14.12 f/s,while attaining an F1-Score of 98.25%.These results demonstrate that the system meets the actual needs of the enterprise and provides theoretical and methodological support for intelligent inspection of product surface quality.By standardizing the control process of pharmaceutical manufacturing and improving the management capability of the manufacturing process,our approach holds significant market application prospects.
基金supported by the National Natural Science Foundation of China(51805078)Project of National Key Laboratory of Advanced Casting Technologies(CAT2023-002)the 111 Project(B16009).
文摘Segment Anything Model(SAM)is a cutting-edge model that has shown impressive performance in general object segmentation.The birth of the segment anything is a groundbreaking step towards creating a universal intelligent model.Due to its superior performance in general object segmentation,it quickly gained attention and interest.This makes SAM particularly attractive in industrial surface defect segmentation,especially for complex industrial scenes with limited training data.However,its segmentation ability for specific industrial scenes remains unknown.Therefore,in this work,we select three representative and complex industrial surface defect detection scenarios,namely strip steel surface defects,tile surface defects,and rail surface defects,to evaluate the segmentation performance of SAM.Our results show that although SAM has great potential in general object segmentation,it cannot achieve satisfactory performance in complex industrial scenes.Our test results are available at:https://github.com/VDT-2048/SAM-IS.
基金Sponsored by Program for New Century Excellent Talents in University of China(NCET-08-0726)Beijing Nova Program of China(2007B027)
文摘Longitudinal cracks are common defects of continuous casting slabs and may lead to serious quality accidents. Image capturing and recognition of hot slabs is an effective way for on-line detection of cracks, and recognition of cracks is essential because the surface of hot slabs is very complicated. In order to detect the surface longitudinal cracks of the slabs, a new feature extraction method based on Curvelet transform and kernel locality preserving projections (KLPP) is proposed. First, sample images are decomposed into three levels by Curvelet transform. Second, Fourier transform is applied to all sub-band images and the Fourier amplitude spectrum of each sub-band is computed to get features with translational invariance. Third, five kinds of statistical features of the Fourier amplitude spectrum are computed and combined in different forms. Then, KLPP is employed for dimensionality reduction of the obtained 62 types of high-dimensional combined features. Finally, a support vector machine (SVM) is used for sample set classification. Experiments with samples from a real production line of continuous casting slabs show that the algorithm is effective to detect longitudinal cracks, and the classification rate is 91.89%.
基金supported by the National Key Technology R&D Program(Grant No.2014BAK11B04)the National Natural Science Foundation of China(Grant Nos.11272089,11327201,11532005&11602056)
文摘In the surface imaging of underwater structures, long working distance will reduce image quality due to the turbidity of water. To acquire high definition and large field of view(FOV) images for surface detection, a short-working-distance underwater imaging system is proposed based on camera array. A multi-view calibration and rectification method is developed. A look-up table(LUT) method and a multi-resolution spline(MRS) method are applied to stitch array images real-time and seamlessly.Experiments both in the air and in the water are conducted. Strength and weakness of the LUT and MRS methods are discussed.Based on the results, the effectiveness in surface detection of underwater structures is verified.
文摘In the industrial production of expanded thermoplastic polyurethane (E-TPU) midsoles, the surface defects still rely on manual inspection at present, and the eligibility criteria are uneven. Therefore, this paper proposes an E-TPU midsole surface defect detection method based on machine vision to achieve automatic detection and defect classification. The proposed method is divided into three parts: image preprocessing, block defect detection, and linear defect detection. Image preprocessing uses RGB three channel self-inspection to identify scorch and color pollution. Block defect detection uses superpixel segmentation and background prior mining to determine holes, impurities, and dirt. Linear defect detection uses Gabor filter and Hough transform to detect indentation and convex marks. After image preprocessing, block defect detection and linear defect detection are simultaneously performed by parallel computing. The false positive rate (FPR) of the proposed method in this paper is 8.3%, the false negatives rate (FNR) of the hole is 4.7%, the FNR of indentation is 2.1%, and the running time does not exceed 1.6 s. The test results show that this method can quickly and accurately detect various defects in the E-TPU midsole.
文摘A simple technique for sensitive detection of heroine based on surface- plasmonresonance has been theoretically and experimentally investigated. The experiment was realized by using an anti-MO monoclonal antibody and a morphine (MO)-bovine serum albumin (MOBSA) conjugate (antigen). The reason for using MO-BSA in the detection of heroine was also discussed. MO-BSA was immobilized on a gold thin film of SPR sensor chip by physical adsorption. The configuration of the device is allowed to be further miniaturized, which is required for the construction of a portable SPR device in the application of in-situ analysis.
基金This work is supported by the Qing Lan Project of the Higher Education Institutions of Jiangsu Province,the 2022 Jiangsu Science and Technology Plan Special Fund(International Science and Technology Cooperation)(BZ2022029).
文摘For surface defects in electronic water pump shells,the manual detection efficiency is low,prone to misdetection and leak detection,and encounters problems,such as uncertainty.To improve the speed and accuracy of surface defect detection,a lightweight detection method based on an improved YOLOv5s method is proposed to replace the traditional manual detection methods.In this method,the MobileNetV3 module replaces the backbone network of YOLOv5s,depth-separable convolution is introduced,the parameters and calculations are reduced,and CIoU_Loss is used as the loss function of the boundary box regression to improve its detection accuracy.A dataset of electronic pump shell defects is established,and the performance of the improved method is evaluated by comparing it with that of the original method.The results show that the parameters and FLOPs are reduced by 49.83%and 61.59%,respectively,compared with the original YOLOv5s model,and the detection accuracy is improved by 1.74%,which is an indication of the superiority of the improved method.To further verify the universality of the improved method,it is compared with the results using the original method on the PASCALVOC2007 dataset,which verifies that it yields better performance.In summary,the improved lightweight method can be used for the real-time detection of electronic water pump shell defects.
文摘The study area is located between the cities of Comitan (16°10'43"N and 92°04'20''W) a city with 150,000 inhabitants and La Esperanza (16°9'15''N and 91°52'5''W) a town with 3000 inhabitants. Both weather stations are 30 km from each other in the Chiapas State, México. 54 years of daily records of the series of maximum (<em>t</em><sub>max</sub>) and minimum temperatures (<em>t</em><sub>min</sub>) of the weather station 07205 Comitan that is on top of a house and 30 years of daily records of the weather station 07374 La Esperanza were analyzed. The objective is to analyze the evidence of climate change in the Comitan valley. 2.07% and 19.04% of missing data were filled, respectively, with the WS method. In order to verify homogeneity three methods were used: Standard Normal Homogeneity Test (SNHT), the Von Neumann method and the Buishand method. The heterogeneous series were homogenized using climatol. The trends of <em>t</em><sub>max</sub> and <em>t</em><sub>min</sub> for both weather stations were analyzed by simple linear regression, Sperman’s rho and Mann-Kendall tests. The Mann-Kendal test method confirmed the warming trend at the Comitan station for both variables with <em>Z<sub>MK</sub></em> statistic values equal to 1.57 (statistically not significant) and 4.64 (statistically significant). However, for the Esperanza station, it determined a cooling trend for tmin and a slight non-significant warming for <em>t</em><sub>max</sub> with a <em>Z</em><sub><em>MK</em></sub> statistic of -2.27 (statistically significant) and 1.16 (statistically not significant), for a significance level <em>α</em> = 0.05.
基金supported by the Natural Science Foundation of Liaoning Province(No.2022-MS-353)Basic Scientific Research Project of Education Department of Liaoning Province(Nos.2020LNZD06 and LJKMZ20220640)。
文摘Surface defects can affect the quality of steel plate.Many methods based on computer vision are currently applied to surface defect detection of steel plate.However,their real-time performance and object detection of small defect are still unsatisfactory.An improved object detection network based on You Only Look One-level Feature(YOLOF)is proposed to show excellent performance in surface defect detection of steel plate,called DLF-YOLOF.First,the anchor-free detector is used to reduce the network hyperparameters.Secondly,deformable convolution network and local spatial attention module are introduced into the feature extraction network to increase the contextual information in the feature maps.Also,the soft non-maximum suppression is used to improve detection accuracy significantly.Finally,data augmentation is performed for small defect objects during training to improve detection accuracy.Experiments show the average precision and average precision for small objects are 42.7%and 33.5%at a detection speed of 62 frames per second on a single GPU,respectively.This shows that DLF-YOLOF has excellent performance to meet the needs of industrial real-time detection.
基金funded by the National Nature Science Founda-tion of China(Grant Nos.51905469 and 11672261)the National key research and development program of China under grant number(Grant No.2019YFE0192600)。
文摘Wind turbine blades are prone to failure due to high tip speed,rain,dust and so on.A surface condition detecting approach based on wind turbine blade aerodynamic noise is proposed.On the experimental measurement data,variational mode decomposition filtering and Mel spectrogram drawing are conducted first.The Mel spectrogram is divided into two halves based on frequency characteristics and then sent into the convolutional neural network.Gaussian white noise is superimposed on the original signal and the output results are assessed based on score coefficients,considering the complexity of the real environment.The surfaces of Wind turbine blades are classified into four types:standard,attachments,polishing,and serrated trailing edge.The proposed method is evaluated and the detection accuracy in complicated background conditions is found to be 99.59%.In addition to support the differentiation of trained models,utilizing proper score coefficients also permit the screening of unknown types.
文摘Defect detection assurance on production lines machine-vision-based surface is important in quality This paper presents a fast defect detection method using the weighted least-squares model. We assume that an inspection image can be regarded as a combination of a defect-free template image and a residual image. The defect-free template image is generated from training samples adaptively, and the residual image is the result of the subtraction between each inspection image and corresponding defect-free template image. In the weighted least-squares model, the residual error near the edge is suppressed to reduce the false alarms caused by spatial misalignment. Experiment results on different types of buttons show that the proposed method is robust to illumination vibration and rotation deviation and produces results that are better than those of two other methods.
基金supported by the National Natural Science Foundation of China (No.20771015)the National ‘‘111’’ Project of China’s Higher Education (No.B07012)
文摘An ultra-sensitive and highly selective parathion methyl (PM) detection method by surface plasmon resonance (SPR) combined with molecularly imprinted films (MIF) was developed. The PM-imprinted film was prepared by thermo initiated polymerization on the bare Au surface of an SPR sensor chip, Template PM molecules were quickly removed by an organic solution of acetonitrilelacetic acid (9:1, v/v), causing a shift of 0.5° in SPR angle. In the concentrations range of 10^-13-10^-10 mol/L, the refractive index showed a gradual increase with higher concentrations of template PM and the changes of SPR angles were linear with the negative logarithm of PM concentrations. In the experiment, the minimum detectable concentration was 10^-13 mol/L. The selectivity of the thin PM-imprinted film against diuron, tetrachlorvinphose and fenitrothion was examined, but no observable binding was detected. The results in the experiment suggested that the MIF had the advantages of high sensitivity and selectivity.
文摘A method of detecting dry, icy and wet road surface conditions based on scanniag detection of single wavelength backward power is proposed in this letter. The detector is used to receive the backward scattered power which changes with the incidence angle. The relationship between backward power and incidence angle is used to find out the effective angle range and distinguish method. Experiment and simulation show that it is feasible to classifv these three conditions within incidence angle of 5.3 degree.
基金supported by the National Natural Science Foundation of China(Nos.61627825 and 11275172)the State Key Laboratory of Modern Optical Instrumentation Innovation Program(MOI)(No.MOI2015 B06)
文摘In recent years, modern optical processing technologies, such as single point diamond turning, ion beam etching, and magneto-theological finishing, arc getting break- throughs. Machining precisions of super-smooth optics have also been significantly improved. However, with increasing demands for the optical surface quality,