SAM Era:Can It Segment Any Industrial Surface Defects?

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.

Analytical Modeling and Mechanism Analysis of Time-Varying Excitation for Surface Defects in Rolling Element Bearings

Surface defects,including dents,spalls,and cracks,for rolling element bearings are the most common faults in rotating machinery.The accurate model for the time-varying excitation is the basis for the vibration mechanism analysis and fault feature extraction.However,in conventional investigations,this issue is not well and fully addressed from the perspective of theoretical analysis and physical derivation.In this study,an improved analytical model for time-varying displacement excitations(TVDEs)caused by surface defects is theoretically formulated.First and foremost,the physical mechanism for the effect of defect sizes on the physical process of rolling element-defect interaction is revealed.According to the physical interaction mechanism between the rolling element and different types of defects,the relationship between time-varying displacement pulse and defect sizes is further analytically derived.With the obtained time-varying displacement pulse,the dynamic model for the deep groove bearings considering the internal excitation caused by the surface defect is established.The nonlinear vibration responses and fault features induced by surface defects are analyzed using the proposed TVDE model.The results suggest that the presence of surface defects may result in the occurrence of the dual-impulse phenomenon,which can serve as indexes for surface-defect fault diagnosis.

Formation and control of the surface defect in hypo-peritectic steel during continuous casting:A review

Hypo-peritectic steels are widely used in various industrial fields because of their high strength,high toughness,high processability,high weldability,and low material cost.However,surface defects are liable to occur during continuous casting,which includes depression,longitudinal cracks,deep oscillation marks,and severe level fluctuation with slag entrapment.The high-efficiency production of hypo-peritectic steels by continuous casting is still a great challenge due to the limited understanding of the mechanism of peritectic solidification.This work reviews the definition and classification of hypo-peritectic steels and introduces the formation tendency of common surface defects related to peritectic solidification.New achievements in the mechanism of peritectic reaction and transformation have been listed.Finally,countermeasures to avoiding surface defects of hypo-peritectic steels duiring continuous casting are summarized.Enlightening certain points in the continuous casting of hypo-peritectic steels and the development of new techniques to overcome the present problems will be a great aid to researchers.

Rail Surface Defect Detection Based on Improved UPerNet and Connected Component Analysis

To guarantee the safety of railway operations,the swift detection of rail surface defects becomes imperative.Traditional methods of manual inspection and conventional nondestructive testing prove inefficient,especially when scaling to extensive railway networks.Moreover,the unpredictable and intricate nature of defect edge shapes further complicates detection efforts.Addressing these challenges,this paper introduces an enhanced Unified Perceptual Parsing for Scene Understanding Network(UPerNet)tailored for rail surface defect detection.Notably,the Swin Transformer Tiny version(Swin-T)network,underpinned by the Transformer architecture,is employed for adept feature extraction.This approach capitalizes on the global information present in the image and sidesteps the issue of inductive preference.The model’s efficiency is further amplified by the windowbased self-attention,which minimizes the model’s parameter count.We implement the cross-GPU synchronized batch normalization(SyncBN)for gradient optimization and integrate the Lovász-hinge loss function to leverage pixel dependency relationships.Experimental evaluations underscore the efficacy of our improved UPerNet,with results demonstrating Pixel Accuracy(PA)scores of 91.39%and 93.35%,Intersection over Union(IoU)values of 83.69%and 87.58%,Dice Coefficients of 91.12%and 93.38%,and Precision metrics of 90.85%and 93.41%across two distinct datasets.An increment in detection accuracy was discernible.For further practical applicability,we deploy semantic segmentation of rail surface defects,leveraging connected component processing techniques to distinguish varied defects within the same frame.By computing the actual defect length and area,our deep learning methodology presents results that offer intuitive insights for railway maintenance professionals.

Tuning the crystallite size of monoclinic ZrO_(2) to reveal critical roles of surface defects on m–ZrO_(2) catalyst for direct synthesis of isobutene from syngas

The effects of crystallite size on the physicochemical properties and surface defects of pure monoclinic ZrO_(2) catalysts for isobutene synthesis were studied.We prepared a series of monoclinic ZrO_(2) catalysts with different crystallite size by changing calcination temperature and evaluated their catalytic performance for isobutene synthesis from syngas.ZrO_(2) with small crystalline size showed higher CO conversion and isobutene selectivity,while samples with large crystalline size preferred to form dimethyl ether(DME)instead of hydrocarbons,much less to isobutene.Oxygen defects(ODefects)analyzed by X-ray photoelectron spectroscopy(XPS)provided evidence that more ODefectsoccupied on the surface of ZrO_(2) catalysts with smaller crystalline size.Electron paramagnetic resonance(EPR)and ultraviolet–visible diffuse reflectance(UV–vis DRS)confirmed the presence of high concentration of surface defects and Zr3+on mZrO_(2)-5.9 sample,respectively.In situ diffuse reflectance infrared Fourier transform spectroscopy(in situ DRIFTS)analysis indicated that the adsorption strength of formed formate species on catalyst reduced as the crystalline size decreased.These results suggested that surface defects were responsible for CO activation and further influenced the adsorption strength of surface species,and thus the products distribution changed.This study provides an in-depth insight for active sites regulation of ZrO_(2) catalyst in CO hydrogenation reaction.

Surface defect-rich ceria quantum dots anchored on sulfur-doped carbon nitride nanotubes with enhanced charge separation for solar hydrogen production

Designing defect-engineered semiconductor heterojunctions can effectively promote the charge carrier separation.Herein,novel ceria(CeO2) quantum dots(QDs) decorated sulfur-doped carbon nitride nanotubes(SCN NTs) were synthesized via a thermal polycondensation coupled in situ depositionprecipitation method without use of template or surfactant.The structure and morphology studies indicate that ultrafine CeO2 QDs are well distributed inside and outside of SCN NTs offering highly dispersed active sites and a large contact interface between two components.This leads to the promoted formation of rich Ce^(3+) ion and oxygen vacancies as confirmed by XPS.The photocatalytic performance can be facilely modulated by the content of CeO2 QDs introduced in SCN matrix while bare CeO2 does not show activity of hydrogen production.The optimal catalyst with 10% of CeO2 loading yields a hydrogen evolution rate of 2923.8 μmol h-1 g-1 under visible light,remarkably higher than that of bare SCN and their physical mixtures.Further studies reveal that the abundant surface defects and the created 0 D/1 D junctions play a critical role in improving the separation and transfer of charge carriers,leading to superior solar hydrogen production and good stability.

Research on Surface Defect Detection Method of E-TPU Midsole Based on Machine Vision

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.

Impact of Methanol Photomediated Surface Defects on Photocatalytic H2 Production Over Pt/TiO2

Co-catalysts play a critical role in enhancing the efficiency of inorganic semiconductor photocatalysts;however,synthetic approaches to tailoring cocatalyst properties are rarely the focus of research efforts.A photomediated route to control the dispersion and oxidation state of a platinum(Pt)cocatalyst through defect generation in the P25 titania photocatalyst substrate is reported.Titania photoirradiation in the presence of methanol induces longlived surface defects which subsequently promote the photodeposition of highly dispersed(2.2±0.8 nm)and heavily reduced Pt nanoparticles on exposure to H2 PtCl6.The optimal methanol concentration of 20 vol%produces the highest density of metallic Pt nanoparticles.Photocatalytic activity for water splitting and associated hydrogen(H2)production under UV irradiation mirrors the methanol concentration employed during the P25 photoirradiation pretreatment and resulting Pt loading resulting in a common mass-normalized H2 productivity of 3800±130 mmol gpt-1 h-1.Photomediated surface defects(arising in the presence of a methanol hole scavenger)provide electron traps that regulate subsequent photodeposition of a Pt co-catalyst over P25,offering a facile route to tune photocatalytic efficiency.

Surface defects in 4H-SiC homoepitaxial layers

Although a high-quality homoepitaxial layer of 4H‑silicon carbide(4H-SiC)can be obtained on a 4°off-axis substrate using chemical vapor deposition,the reduction of defects is still a focus of research.In this study,several kinds of surface defects in the 4H-SiC homoepitaxial layer are systemically investigated,including triangles,carrots,surface pits,basal plane dislocations,and step bunching.Themorphologies and structures of surface defects are further discussed via optical microscopy and potassium hydroxide-based defect selective etching analysis.Through research and analysis,we found that the origin of surface defects in the 4H-SiC homoepitaxial layer can be attributed to two aspects:the propagation of substrate defects,such as scratches,dislocation,and inclusion,and improper process parameters during epitaxial growth,such as in-situ etch,C/Si ratio,and growth temperature.It is believed that the surface defects in the 4H-SiC homoepitaxial layer can be significantly decreased by precisely controlling the chemistry on the deposition surface during the growth process.

Grading Method of Kiwifruit Based on Surface Defect Recognition

Aiming at the problems of single classification method and high classification cost of kiwifruit in China,we proposed a grading method based on kiwifruit surface defects.A set of kiwifruit image acquisition system was built.The K-means clustering segmentation algorithm was used to segment the surface defects,and then color contrast was performed to determine whether it was a piece of defective fruit.Then,the shape features of normal fruit were extracted and an SVM classifier was designed to further determine its grade.This method has the advantages of low cost,simple algorithm and high efficiency,which opens a new way for fruit classification,and is of great significance to promoting the development of fruit classification industry in China and enhancing international competitiveness.

Surface defects incorporated diamond machining of silicon

This paper reports the performance enhancement benefits in diamond turning of the silicon wafer by incorporation of the surface defect machining(SDM)method.The hybrid micromachining methods usually require additional hardware to leverage the added advantage of hybrid technologies such as laser heating,cryogenic cooling,electric pulse or ultrasonic elliptical vibration.The SDM method tested in this paper does not require any such additional baggage and is easy to implement in a sequential micro-machining mode.This paper made use of Raman spectroscopy data,average surface roughness data and imaging data of the cutting chips of silicon for drawing a comparison between conventional single-point diamond turning(SPDT)and SDM while incorporating surface defects in the(i)circumferential and(ii)radial directions.Complementary 3D finite element analysis(FEA)was performed to analyse the cutting forces and the evolution of residual stress on the machined wafer.It was found that the surface defects generated in the circumferential direction with an interspacing of 1 mm revealed the lowest average surface roughness(Ra)of 3.2 nm as opposed to 8 nm Ra obtained through conventional SPDT using the same cutting parameters.The observation of the Raman spectroscopy performed on the cutting chips showed remnants of phase transformation during the micromachining process in all cases.FEA was used to extract quantifiable information about the residual stress as well as the sub-surface integrity and it was discovered that the grooves made in the circumferential direction gave the best machining performance.The information being reported here is expected to provide an avalanche of opportunities in the SPDT area for low-cost machining solution for a range of other nominal hard,brittle materials such as SiC,ZnSe and GaAs as well as hard steels.

DLF-YOLOF:an improved YOLOF-based surface defect detection for steel plate

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.

Printed Circuit Board (PCB) Surface Micro Defect Detection Model Based on Residual Network with Novel Attention Mechanism

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.

Surface defect engineered-Mg-based implants enable the dual functions of superhydrophobic and synergetic photothermal/chemodynamic therapy

Promoting metallic magnesium(Mg)-based implants to treat bone diseases in clinics,such as osteosarcoma and bacterial infection,remains a challenging topic.Herein,an iron hydroxide-based composite coating with a twostage nanosheet-like structure was fabricated on Mg alloy,and this was followed by a thermal reduction treatment to break some of the surface Fe–OH bonds.The coating demonstrated three positive changes in properties due to the defects.First,the removal of–OH made the coating superhydrophobic,and it had self-cleaning and antifouling properties.This is beneficial for keeping the implants clean and for anti-corrosion before implantation into the human body.Furthermore,the superhydrophobicity could be removed by immersing the implant in a 75%ethanol solution,to further facilitate biological action during service.Second,the color of the coating changed from yellow to brown-black,leading to an increase in the light absorption,which resulted in an excellent photothermal effect.Third,the defects increased the Fe2+content in the coating and highly improved peroxidase activity.Thus,the defect coating exhibited synergistic photothermal/chemodynamic therapeutic effects for bacteria and tumors.Moreover,the coating substantially enhanced the anti-corrosion and biocompatibility of the Mg alloys.Therefore,this study offers a novel multi-functional Mg-based implant for osteosarcoma therapy.

Neutral and metallic vs.charged and semiconducting surface layer in acceptor doped CeO_(2)

The monomolecular surface layer of acceptor doped CeO_(2) may become neutral and metallic or charged and semiconducting.This is revealed in the theoretical analysis of the oxygen pressure dependence of the surface defects concentration in acceptor doped ceria with two different dopant types and operated under different oxygen pressures.Recently published experimental data for highly reduced Sm0.2Ce0.8O1.9-x(SDC)containing a fixed valence dopant Sm3+are very different from those published for Pr0.1Ce0.9O_(2)-x(PCO) with the variable valence dopant Pr4+/Pr3+being reduced under milder conditions.The theoretical analysis of these experimental results fits very well the experimental results of SDC and PCO.It leads to the following predictions:the highly reduced surface of SDC is metallic and neutral,the metallic surface electron density of state is gs=0.9×10^(38)J-1·m^(-2)(1.4×1015eV^(-1)·cm^(-2)),the electron effective mass is meff,s=3.3me,and the phase diagram of the reduced surface has theα(fcc)structure as in the bulk.In PCO a double layer is predicted to be formed between the surface and the bulk with the surface being negatively charged and semiconducting.The surface of PCO maintains high Pr^(3+) defect concentration as well as relative high oxygen vacancy concentration at oxygen pressures higher than in the bulk.The reasons for the difference between a metallic and semiconducting surface layer of acceptor doped CeO_(2) are reviewed,as well as the key theoretical considerations applied in coping with this problem.For that we make use of the experimental data and theoretical analysis available for acceptor doped ceria.

Facile Surface Engineering of NiCo_(2)O_(4) to Boost Propane Oxidation Activity

Spinel oxide(NiCo_(2)O_(4))has demonstrated great potential to replace noble metal catalysts for the oxidation reaction of air pollutants.To further boost the oxidation ability of such catalysts,in this study,a facile surface-engineering strategy wherein NiCo_(2)O_(4) was treated with different alkali solvents was developed.The obtained catalyst(NiCo_(2)O_(4)-OH)showed a higher surface alkalinity and more surface defects compared to the pristine spinel oxide,including enhanced structural distortion as well as promoted oxygen vacancies.The propane oxidation ability of NiCo_(2)O_(4)-OH was greatly enhanced,with a propane conversion rate that was approximately 6.4 times higher than that of pristine NiCo_(2)O_(4) at a reaction temperature 193℃.This work sets a valuable paradigm for the surface modulation of spinel oxide via alkali treatment to ensure a high-performance oxidation catalyst.

Improved Sobel algorithm for defect detection of rail surfaces with enhanced efficiency and accuracy

A more effective and accurate improved Sobel algorithm has been developed to detect surface defects on heavy rails. The proposed method can make up for the mere sensitivity to X and Y directions of the Sobel algorithm by adding six templates at different directions. Meanwhile, an experimental platform for detecting surface defects consisting of the bed-jig, image-forming system with CCD cameras and light sources, parallel computer system and cable system has been constructed. The detection results of the backfin defects show that the improved Sobel algorithm can achieve an accurate and efficient positioning with decreasing interference noises to the defect edge. It can also extract more precise features and characteristic parameters of the backfin defect. Furthermore, the BP neural network adopted for defects classification with the inputting characteristic parameters of improved Sobel algorithm can obtain the optimal training precision of 0.0095827 with 106 iterative steps and time of 3 s less than Sobel algorithm with 146 steps and 5 s. Finally, an enhanced identification rate of 10% for the defects is also confirmed after the Sobel algorithm is improved.

Wavy PtCu alloy nanowire networks with abundant surface defects enhanced oxygen reduction reaction

Bimetalic platinum-copper(Pt-Cu)alloy nanowires have emerged as a novel class of fuel cell electrocatalysts for oxygen reduction reaction(ORR)due to their intrinsic high catalytic activity and durability,but preparing such electrocatalysts with clean surface via facile method is still a challenge.Herein,PtCu alloy with nanowire networks(NWNs)structure is obtained by a simple modified polyol method accompanied with a salt-mediated self-assembly process in a water/ethylene glycol(EG)mixing media.The formation mechanism of PtCu NWNs including the morphological evolution and the relevant experimental parameters has been investigated systematically.We propose that a micro-interface in H2O-EG media formed with the assistance of disodium dihydrogen pyrophosphate(Na2H2P2O7)and its unique nature of coordinating with Pt^2+ or Cu^2+ play critical roles in the formation of NWNs.When tested as ORR catalyst,the PtCuNWNs/C exhibits much higher activity and durability than that of PtNWNs/C and commercial PtC,even exceeding the target of DOE in 2020.The excellent performance of PtCuNWNs/C could be attributed to the unique structure of NWNs with 2.4 nm ultrathin wavy nanowires and plentiful surface defects and the modified electronic effect caused by alloying with Cu atoms.

Surface-defective FeS2 for electrochemical NH3 production under ambient conditions

In the viewpoint of ammonia economy,electrochemical N2 reduction reaction(NRR)under mild condition is a very promising approach for sustainable development.By virtue of robust activity and low cost,transition-metalbased materials become one kind of the most attractive electrocatalysts in realizing ammonia synthesis to the industrial level.However,the investigation related to NRR electrocatalysts still mainly rely on costly substance or fabrication process,which greatly restrict their large-scale applications.In this work,a simple fabricated FeS2 electrode is adopted as NRR catalysts.The abundant surface defects due to the existence of Cr element,as well as the synergistic effect between FeS2 crystal planes provided excellent electrocatalytic performance with a high NH3 yield rate(11.5μg h^-1mg^-1 Fe)and Faradaic efficiency(14.6%)at-0.2 V vs.reversible hydrogen electrode(RHE)toward NRR under ambient conditions.The superior catalytic performance of such non-precious metal catalysts would strongly promote the application of NRR process industrially.

Unbalanced classification method using least squares support vector machine with sparse strategy for steel surface defects with label noise

Least squares support vector machine (LS-SVM) plays an important role in steel surface defects classification because of its high speed. However, the defect samples obtained from the real production line may be noise. LS-SVM suffers from the poor classification performance in the classification stage when there are noise samples. Thus, in the classification stage, it is necessary to design an effective algorithm to process the defects dataset obtained from the real production line. To this end, an adaptive weight function was employed to reduce the adverse effect of noise samples. Moreover, although LSSVM offers fast speed, it still suffers from a high computational complexity if the number of training samples is large. The time for steel surface defects classification should be as short as possible. Therefore, a sparse strategy was adopted to prune the training samples. Finally, since the steel surface defects classification belongs to unbalanced data classification, LSSVM algorithm is not applicable. Hence, the unbalanced data information was introduced to improve the classification performance. Comprehensively considering above-mentioned factors, an improved LS-SVM classification model was proposed, termed as ILS-SVM. Experimental results show that the new algorithm has the advantages of high speed and great anti-noise ability.