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.

Application of multi-scale feature extraction to surface defect classification of hot-rolled steels

Feature extraction is essential to the classification of surface defect images. The defects of hot-rolled steels distribute in different directions. Therefore, the methods of multi-scale geometric analysis （MGA） were employed to decompose the image into several directional subba^ds at several scales. Then, the statistical features of each subband were calculated to produce a high-dimensional feature vector, which was reduced to a lower-dimensional vector by graph embedding algorithms. Finally, support vector machine （SVM） was used for defect classification. The multi-scale feature extraction method was implemented via curvelet transform and kernel locality preserving projections （KLPP）. Experiment results show that the proposed method is effective for classifying the surface defects of hot-rolled steels and the total classification rate is up to 97.33%.

Application of a new feature extraction and optimization method to surface defect recognition of cold rolled strips

Considering that the surface defects of cold rolled strips are hard to be recognized by human eyes under high-speed circumstances, an automatic recognition technique was discussed. Spectrum images of defects can be got by fast Fourier transform （FFF） and sum of valid pixels （SVP）, and its optimized center region, which concentrates nearly all energies, are extracted as an original feature set. Using genetic algorithm to optimize the feature set, an optimized feature set with 51 features can be achieved. Using the optimized feature set as an input vector of neural networks, the recognition effects of LVQ neural networks have been studied. Experiment results show that the new method can get a higher classification rate and can settle the automatic recognition problem of surface defects on cold rolled strips ideally.

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.

Creation of surface defects on carbon nanofibers by steam treatment

A direct strategy for the creation of defects on carbon nanofibers (CNFs) has been developed by steam treatment.Nitrogen physisorption,XRD,Raman spectra,SEM and TEM analyses proved the existence of the new defects on CNFs.BET surface area of CNFs after steam treatment was enhanced from 20 to 378 m2/g.Pd catalysts supported on CNFs were also prepared by colloidal deposition method.The different activity of Pd/CNFs catalysts in the partial hydrogenation of phenylacetylene further demonstrated the diverse surfaces of CNFs could be formed by steam treatment.

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.

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.

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.

Contribution of Surface Defects to the Interface Conductivity of SrTiO_3/LaAlO_3

Based on the first-principles method, the structural stability and the contribution of point defects such as O, Sr or Ti vacancies on two-dimensional electron gas of n- and p-type LaAlO3/SrTiO3 interfaces are investigated. The results show that O vacancies at p-type interfaces have much lower formation energies, and Sr or Ti vacancies at n-type interfaces are more stable than the ones at p-type interfaces under O-rich conditions. The calculated densities of states indicate that O vacancies act as donors and give a significant compensation to hole carriers, resulting in insulating behavior at p-type interfaces. In contrast, Sr or Ti vacancies tend to trap electrons and behave as acceptors. Sr vacancies are the most stable defects at high oxygen partial pressures, and the Sr vacancies rather than Ti vacancies are responsible for the insulator-metal transition of n-type interface. The calculated results can be helpful to understand the tuned electronic properties of LaAlO3 /SrTiO3 heterointerfaces.

AN EFFICIENT LABELLING ALGORITHM FOR WOODPANELS SURFACE DEFECTS

This paper describes an efficient approach for labeling images using a combination of pipeline (Datacube) and (general purpose computer) processing. The output of the algorithm is coordinate list of labeled object pixels that facilitates further high level operations. It is an efficient labeling algorithm for a automatic classification of surface defects on wood boards.

Surface defect gap solitons in two-dimensional optical lattices

We investigate the existence and stability of surface defect gap solitons at an interface between a defect in a two-dimensional optical lattice and a uniform saturable Kerr nonlinear medium. The surface defect embedded in the two-dimensional optical lattice gives rise to some unique properties. It is interestingly found that for the negative defect, stable surface defect gap solitons can exist both in the semi-infinite gap and in the first gap. The deeper the negative defect, the narrower the stable region in the semi-infinite gap will be. For a positive defect, the surface defect gap solitons exist only in the semi-infinite gap and the stable region localizes in a low power region.

Constructing a data platform for surface defect management using a multidimensional database

Surface quality has been one of the key factors influencing the ongoing improvement of the quality of steel. Therefore,it is urgent to provide methods for efficient supervision of surface defects. This paper first expressed the main problems existing in defect management and then focused on constructing a data platform of surface defect management using a multidimensional database. Finally, some onqine applications of the platform at Baosteel were demonstrated. Results show that the constructed multidimensional database provides more structured defect data, and thus it is suitable for swift and multi-angle analysis of the defect data.

Surface defect gap solitons in one-dimensional dual-frequency lattices

We study the surface defect gap solitons in an interface between a defect of one-dimensional dual-frequency lattices and the uniform media. Some unique properties are revealed that such lattices can broaden the region of semi-finite gap, and the semi-finite gap exists not only in the positive and zero defects but also in the negative defect; unlike in the regular lattices, the semi-finite gap exists in the positive and zero defects but does not exist in the negative defect. In particular, stable solitons exist almost in the whole semi-finite gap for the positive and zero defects. These properties are different from other lattices with defects. In addition, it is found that the existence of surface dual-frequency lattice solitons does not need a threshold power.

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.