Steel Surface Defect Recognition in Smart Manufacturing Using Deep Ensemble Transfer Learning-Based Techniques

Smart manufacturing and Industry 4.0 are transforming traditional manufacturing processes by utilizing innovative technologies such as the artificial intelligence(AI)and internet of things(IoT)to enhance efficiency,reduce costs,and ensure product quality.In light of the recent advancement of Industry 4.0,identifying defects has become important for ensuring the quality of products during the manufacturing process.In this research,we present an ensemble methodology for accurately classifying hot rolled steel surface defects by combining the strengths of four pre-trained convolutional neural network(CNN)architectures:VGG16,VGG19,Xception,and Mobile-Net V2,compensating for their individual weaknesses.We evaluated our methodology on the Xsteel surface defect dataset(XSDD),which comprises seven different classes.The ensemble methodology integrated the predictions of individual models through two methods:model averaging and weighted averaging.Our evaluation showed that the model averaging ensemble achieved an accuracy of 98.89%,a recall of 98.92%,a precision of 99.05%,and an F1-score of 98.97%,while the weighted averaging ensemble reached an accuracy of 99.72%,a recall of 99.74%,a precision of 99.67%,and an F1-score of 99.70%.The proposed weighted averaging ensemble model outperformed the model averaging method and the individual models in detecting defects in terms of accuracy,recall,precision,and F1-score.Comparative analysis with recent studies also showed the superior performance of our methodology.

Optimizing electronic structure through point defect engineering for enhanced electrocatalytic energy conversion

Point defect engineering endows catalysts with novel physical and chemical properties,elevating their electrocatalytic efficiency.The introduction of defects emerges as a promising strategy,effectively modifying the electronic structure of active sites.This optimization influences the adsorption energy of intermediates,thereby mitigating reaction energy barriers,altering paths,enhancing selectivity,and ultimately improving the catalytic efficiency of electrocatalysts.To elucidate the impact of defects on the electrocatalytic process,we comprehensively outline the roles of various point defects,their synthetic methodologies,and characterization techniques.Importantly,we consolidate insights into the relationship between point defects and catalytic activity for hydrogen/oxygen evolution and CO_(2)/O_(2)/N_(2) reduction reactions by integrating mechanisms from diverse reactions.This underscores the pivotal role of point defects in enhancing catalytic performance.At last,the principal challenges and prospects associated with point defects in current electrocatalysts are proposed,emphasizing their role in advancing the efficiency of electrochemical energy storage and conversion materials.

Defect Engineering with Rational Dopants Modulation for High‑Temperature Energy Harvesting in Lead‑Free Piezoceramics

High temperature piezoelectric energy harvester(HTPEH)is an important solution to replace chemical battery to achieve independent power supply of HT wireless sensors.However,simultaneously excellent performances,including high figure of merit(FOM),insulation resistivity(ρ)and depolarization temperature(Td)are indispensable but hard to achieve in lead-free piezoceramics,especially operating at 250°C has not been reported before.Herein,well-balanced performances are achieved in BiFeO3–BaTiO3 ceramics via innovative defect engineering with respect to delicate manganese doping.Due to the synergistic effect of enhancing electrostrictive coefficient by polarization configuration optimization,regulating iron ion oxidation state by high valence manganese ion and stabilizing domain orientation by defect dipole,comprehensive excellent electrical performances(Td=340°C,ρ250°C>10^(7)Ωcm and FOM_(250°C)=4905×10^(–15)m^(2)N^(−1))are realized at the solid solubility limit of manganese ions.The HT-PEHs assembled using the rationally designed piezoceramic can allow for fast charging of commercial electrolytic capacitor at 250°C with high energy conversion efficiency(η=11.43%).These characteristics demonstrate that defect engineering tailored BF-BT can satisfy high-end HT-PEHs requirements,paving a new way in developing selfpowered wireless sensors working in HT environments.

Defect Engineering:Can it Mitigate Strong Coulomb Effect of Mg^(2+)in Cathode Materials for Rechargeable Magnesium Batteries?

Rechargeable magnesium batteries(RMBs)have been considered a promising“post lithium-ion battery”system to meet the rapidly increasing demand of the emerging electric vehicle and grid energy storage market.However,the sluggish diffusion kinetics of bivalent Mg^(2+)in the host material,related to the strong Coulomb effect between Mg^(2+)and host anion lattices,hinders their further development toward practical applications.Defect engineering,regarded as an effective strategy to break through the slow migration puzzle,has been validated in various cathode materials for RMBs.In this review,we first thoroughly understand the intrinsic mechanism of Mg^(2+)diffusion in cathode materials,from which the key factors affecting ion diffusion are further presented.Then,the positive effects of purposely introduced defects,including vacancy and doping,and the corresponding strategies for introducing various defects are discussed.The applications of defect engineering in cathode materials for RMBs with advanced electrochemical properties are also summarized.Finally,the existing challenges and future perspectives of defect engineering in cathode materials for the overall high-performance RMBs are described.

Decade Milestone Advancement of Defect-Engineered g-C_(3)N_(4) for Solar Catalytic Applications

Over the past decade, graphitic carbon nitride(g-C_(3)N_(4)) has emerged as a universal photocatalyst toward various sustainable carbo-neutral technologies. Despite solar applications discrepancy, g-C_(3)N_(4) is still confronted with a general fatal issue of insufficient supply of thermodynamically active photocarriers due to its inferior solar harvesting ability and sluggish charge transfer dynamics. Fortunately, this could be significantly alleviated by the “all-in-one” defect engineering strategy, which enables a simultaneous amelioration of both textural uniqueness and intrinsic electronic band structures. To this end, we have summarized an unprecedently comprehensive discussion on defect controls including the vacancy/non-metallic dopant creation with optimized electronic band structure and electronic density, metallic doping with ultraactive coordinated environment(M–N_(x), M–C_(2)N_(2), M–O bonding), functional group grafting with optimized band structure, and promoted crystallinity with extended conjugation π system with weakened interlayered van der Waals interaction. Among them, the defect states induced by various defect types such as N vacancy, P/S/halogen dopants, and cyano group in boosting solar harvesting and accelerating photocarrier transfer have also been emphasized. More importantly, the shallow defect traps identified by femtosecond transient absorption spectra(fs-TAS) have also been highlighted. It is believed that this review would pave the way for future readers with a unique insight into a more precise defective g-C_(3)N_(4) “customization”, motivating more profound thinking and flourishing research outputs on g-C_(3)N_(4)-based photocatalysis.

Heterointerface Engineering-Induced Oxygen Defects for the Manganese Dissolution Inhibition in Aqueous Zinc Ion Batteries

Manganese-based material is a prospective cathode material for aqueous zinc ion batteries(ZIBs)by virtue of its high theoretical capacity,high operating voltage,and low price.However,the manganese dissolution during the electrochemical reaction causes its electrochemical cycling stability to be undesirable.In this work,heterointerface engineering-induced oxygen defects are introduced into heterostructure MnO_(2)(δa-MnO_(2))by in situ electrochemical activation to inhibit manganese dissolution for aqueous zinc ion batteries.Meanwhile,the heterointerface between the disordered amorphous and the crystalline MnO_(2)ofδa-MnO_(2)is decisive for the formation of oxygen defects.And the experimental results indicate that the manganese dissolution ofδa-MnO_(2)is considerably inhibited during the charge/discharge cycle.Theoretical analysis indicates that the oxygen defect regulates the electronic and band structure and the Mn-O bonding state of the electrode material,thereby promoting electron transport kinetics as well as inhibiting Mn dissolution.Consequently,the capacity ofδa-MnO_(2)does not degrade after 100 cycles at a current density of 0.5 Ag^(-1)and also 91%capacity retention after 500cycles at 1 Ag^(-1).This study provides a promising insight into the development of high-performance manganese-based cathode materials through a facile and low-cost strategy.

Impact Analysis of Microscopic Defect Types on the Macroscopic Crack Propagation in Sintered Silver Nanoparticles

Sintered silver nanoparticles(AgNPs)arewidely used in high-power electronics due to their exceptional properties.However,the material reliability is significantly affected by various microscopic defects.In this work,the three primary micro-defect types at potential stress concentrations in sintered AgNPs are identified,categorized,and quantified.Molecular dynamics(MD)simulations are employed to observe the failure evolution of different microscopic defects.The dominant mechanisms responsible for this evolution are dislocation nucleation and dislocation motion.At the same time,this paper clarifies the quantitative relationship between the tensile strain amount and the failure mechanism transitions of the three defect types by defining key strain points.The impact of defect types on the failure process is also discussed.Furthermore,traction-separation curves extracted from microscopic defect evolutions serve as a bridge to connect the macro-scale model.The validity of the crack propagation model is confirmed through tensile tests.Finally,we thoroughly analyze how micro-defect types influence macro-crack propagation and attempt to find supporting evidence from the MD model.Our findings provide a multi-perspective reference for the reliability analysis of sintered AgNPs.

Trace Cobalt Doping and Defect Engineering of High Surface Area α-Ni(OH)_(2) for Electrocatalytic Urea Oxidation

Owing to the intrinsically sluggish kinetics of urea oxidation reaction(UOR)involving a six-electron transfer process,developing efficient UOR electrocatalyst is a great challenge remained to be overwhelmed.Herein,by taking advantage of 2-Methylimidazole,of which is a kind of alkali in water and owns strong coordination ability to Co^(2+)in methanol,trace Co(1.0 mol%)addition was found to induce defect engineering onα-Ni(OH)_(2)in a dual-solvent system of water and methanol.Physical characterization results revealed that the synthesized electrocatalyst(WM-Ni_(0.99)Co_(0.01)(OH)_(2))was a kind of defective nanosheet with thickness around 5-6 nm,attributing to the synergistic effect of Co doping and defect engineering,its electron structure was finely altered,and its specific surface a rea was tremendously enlarged from 68 to 172.3 m^(2)g^(-1).With all these merits,its overpotential to drive 10 mA cm^(-2)was reduced by 110 mV.Besides,the interfacial behavior of UOR was also well deciphered by operando electrochemical impedance spectroscopy.

YOLO-DD:Improved YOLOv5 for Defect Detection

As computer technology continues to advance,factories have increasingly higher demands for detecting defects.However,detecting defects in a plant environment remains a challenging task due to the presence of complex backgrounds and defects of varying shapes and sizes.To address this issue,this paper proposes YOLO-DD,a defect detectionmodel based on YOLOv5 that is effective and robust.To improve the feature extraction process and better capture global information,the vanilla YOLOv5 is augmented with a new module called Relative-Distance-Aware Transformer(RDAT).Additionally,an Information Gap Filling Strategy(IGFS)is proposed to improve the fusion of features at different scales.The classic lightweight attention mechanism Squeeze-and-Excitation(SE)module is also incorporated into the neck section to enhance feature expression and improve the model’s performance.Experimental results on the NEU-DET dataset demonstrate that YOLO-DDachieves competitive results compared to state-of-the-art methods,with a 2.0% increase in accuracy compared to the original YOLOv5,achieving 82.41% accuracy and38.25FPS(framesper second).Themodel is also testedon a self-constructed fabric defect dataset,and the results show that YOLO-DD is more stable and has higher accuracy than the original YOLOv5,demonstrating its stability and generalization ability.The high efficiency of YOLO-DD enables it to meet the requirements of industrial high accuracy and real-time detection.

A Hybrid Deep Learning and Machine Learning-Based Approach to Classify Defects in Hot Rolled Steel Strips for Smart Manufacturing

Smart manufacturing is a process that optimizes factory performance and production quality by utilizing various technologies including the Internet of Things(IoT)and artificial intelligence(AI).Quality control is an important part of today’s smart manufacturing process,effectively reducing costs and enhancing operational efficiency.As technology in the industry becomes more advanced,identifying and classifying defects has become an essential element in ensuring the quality of products during the manufacturing process.In this study,we introduce a CNN model for classifying defects on hot-rolled steel strip surfaces using hybrid deep learning techniques,incorporating a global average pooling(GAP)layer and a machine learning-based SVM classifier,with the aim of enhancing accuracy.Initially,features are extracted by the VGG19 convolutional block.Then,after processing through the GAP layer,the extracted features are fed to the SVM classifier for classification.For this purpose,we collected images from publicly available datasets,including the Xsteel surface defect dataset(XSDD)and the NEU surface defect(NEU-CLS)datasets,and we employed offline data augmentation techniques to balance and increase the size of the datasets.The outcome of experiments shows that the proposed methodology achieves the highest metrics score,with 99.79%accuracy,99.80%precision,99.79%recall,and a 99.79%F1-score for the NEU-CLS dataset.Similarly,it achieves 99.64%accuracy,99.65%precision,99.63%recall,and a 99.64%F1-score for the XSDD dataset.A comparison of the proposed methodology to the most recent study showed that it achieved superior results as compared to the other studies.

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.

Defect engineering in transition-metal(Fe,Co,andNi)-based electrocatalysts for water splitting

Electrocatalytic water splitting seems to be an efficient strategy to deal with increasingly serious environmental problems and energy crises but still suffers from the lack of stable and efficient electrocatalysts.Designing practical electrocatalysts by introducing defect engineering,such as hybrid structure,surface vacancies,functional modification,and structural distortions,is proven to be a dependable solution for fabricating electrocatalysts with high catalytic activities,robust stability,and good practicability.This review is an overview of some relevant reports about the effects of defect engineering on the electrocatalytic water splitting performance of electrocatalysts.In detail,the types of defects,the preparation and characterization methods,and catalytic performances of electrocatalysts are presented,emphasizing the effects of the introduced defects on the electronic structures of electrocatalysts and the optimization of the intermediates'adsorption energy throughout the review.Finally,the existing challenges and personal perspectives of possible strategies for enhancing the catalytic performances of electrocatalysts are proposed.An in-depth understanding of the effects of defect engineering on the catalytic performance of electrocatalysts will light the way to design high-efficiency electrocatalysts for water splitting and other possible applications.

3D reconstruction and defect pattern recognition of bonding wire based on stereo vision

Non-destructive detection of wire bonding defects in integrated circuits(IC)is critical for ensuring product quality after packaging.Image-processing-based methods do not provide a detailed evaluation of the three-dimensional defects of the bonding wire.Therefore,a method of 3D reconstruction and pattern recognition of wire defects based on stereo vision,which can achieve non-destructive detection of bonding wire defects is proposed.The contour features of bonding wires and other electronic components in the depth image is analysed to complete the 3D reconstruction of the bonding wires.Especially to filter the noisy point cloud and obtain an accurate point cloud of the bonding wire surface,a point cloud segmentation method based on spatial surface feature detection(SFD)was proposed.SFD can extract more distinct features from the bonding wire surface during the point cloud segmentation process.Furthermore,in the defect detection process,a directional discretisation descriptor with multiple local normal vectors is designed for defect pattern recognition of bonding wires.The descriptor combines local and global features of wire and can describe the spatial variation trends and structural features of wires.The experimental results show that the method can complete the 3D reconstruction and defect pattern recognition of bonding wires,and the average accuracy of defect recognition is 96.47%,which meets the production requirements of bonding wire defect detection.

Improvement of High-Speed Detection Algorithm for Nonwoven Material Defects Based on Machine Vision

Defect detection is vital in the nonwoven material industry,ensuring surface quality before producing finished products.Recently,deep learning and computer vision advancements have revolutionized defect detection,making it a widely adopted approach in various industrial fields.This paper mainly studied the defect detection method for nonwoven materials based on the improved Nano Det-Plus model.Using the constructed samples of defects in nonwoven materials as the research objects,transfer learning experiments were conducted based on the Nano DetPlus object detection framework.Within this framework,the Backbone,path aggregation feature pyramid network(PAFPN)and Head network models were compared and trained through a process of freezing,with the ultimate aim of bolstering the model's feature extraction abilities and elevating detection accuracy.The half-precision quantization method was used to optimize the model after transfer learning experiments,reducing model weights and computational complexity to improve the detection speed.Performance comparisons were conducted between the improved model and the original Nano Det-Plus model,YOLO,SSD and other common industrial defect detection algorithms,validating that the improved methods based on transfer learning and semi-precision quantization enabled the model to meet the practical requirements of industrial production.

Defect Detection Model Using Time Series Data Augmentation and Transformation

Time-series data provide important information in many fields,and their processing and analysis have been the focus of much research.However,detecting anomalies is very difficult due to data imbalance,temporal dependence,and noise.Therefore,methodologies for data augmentation and conversion of time series data into images for analysis have been studied.This paper proposes a fault detection model that uses time series data augmentation and transformation to address the problems of data imbalance,temporal dependence,and robustness to noise.The method of data augmentation is set as the addition of noise.It involves adding Gaussian noise,with the noise level set to 0.002,to maximize the generalization performance of the model.In addition,we use the Markov Transition Field(MTF)method to effectively visualize the dynamic transitions of the data while converting the time series data into images.It enables the identification of patterns in time series data and assists in capturing the sequential dependencies of the data.For anomaly detection,the PatchCore model is applied to show excellent performance,and the detected anomaly areas are represented as heat maps.It allows for the detection of anomalies,and by applying an anomaly map to the original image,it is possible to capture the areas where anomalies occur.The performance evaluation shows that both F1-score and Accuracy are high when time series data is converted to images.Additionally,when processed as images rather than as time series data,there was a significant reduction in both the size of the data and the training time.The proposed method can provide an important springboard for research in the field of anomaly detection using time series data.Besides,it helps solve problems such as analyzing complex patterns in data lightweight.

Enhancing the Performance of Perovskite Light-Emitting Diodes via Synergistic Effect of Defect Passivation and Dielectric Screening

Metal halide perovskites,particularly the quasi-two-dimensional perovskite subclass,have exhibited considerable potential for next-generation electroluminescent materials for lighting and display.Nevertheless,the presence of defects within these perovskites has a substantial influence on the emission efficiency and durability of the devices.In this study,we revealed a synergistic passivation mechanism on perovskite films by using a dual-functional compound of potassium bromide.The dual functional potassium bromide on the one hand can passivate the defects of halide vacancies with bromine anions and,on the other hand,can screen the charged defects at the grain boundaries with potassium cations.This approach effectively reduces the probability of carriers quenching resulting from charged defects capture and consequently enhances the radiative recombination efficiency of perovskite thin films,leading to a significant enhancement of photoluminescence quantum yield to near-unity values(95%).Meanwhile,the potassium bromide treatment promoted the growth of homogeneous and smooth film,facilitating the charge carrier injection in the devices.Consequently,the perovskite light-emitting diodes based on this strategy achieve a maximum external quantum efficiency of~21%and maximum luminance of~60,000 cd m^(-2).This work provides a deeper insight into the passivation mechanism of ionic compound additives in perovskite with the solution method.

Software Defect Prediction Method Based on Stable Learning

The purpose of software defect prediction is to identify defect-prone code modules to assist software quality assurance teams with the appropriate allocation of resources and labor.In previous software defect prediction studies,transfer learning was effective in solving the problem of inconsistent project data distribution.However,target projects often lack sufficient data,which affects the performance of the transfer learning model.In addition,the presence of uncorrelated features between projects can decrease the prediction accuracy of the transfer learning model.To address these problems,this article propose a software defect prediction method based on stable learning(SDP-SL)that combines code visualization techniques and residual networks.This method first transforms code files into code images using code visualization techniques and then constructs a defect prediction model based on these code images.During the model training process,target project data are not required as prior knowledge.Following the principles of stable learning,this paper dynamically adjusted the weights of source project samples to eliminate dependencies between features,thereby capturing the“invariance mechanism”within the data.This approach explores the genuine relationship between code defect features and labels,thereby enhancing defect prediction performance.To evaluate the performance of SDP-SL,this article conducted comparative experiments on 10 open-source projects in the PROMISE dataset.The experimental results demonstrated that in terms of the F-measure,the proposed SDP-SL method outperformed other within-project defect prediction methods by 2.11%-44.03%.In cross-project defect prediction,the SDP-SL method provided an improvement of 5.89%-25.46% in prediction performance compared to other cross-project defect prediction methods.Therefore,SDP-SL can effectively enhance within-and cross-project defect predictions.

Attention-relation network for mobile phone screen defect classification via a few samples

How to use a few defect samples to complete the defect classification is a key challenge in the production of mobile phone screens.An attention-relation network for the mobile phone screen defect classification is proposed in this paper.The architecture of the attention-relation network contains two modules:a feature extract module and a feature metric module.Different from other few-shot models,an attention mechanism is applied to metric learning in our model to measure the distance between features,so as to pay attention to the correlation between features and suppress unwanted information.Besides,we combine dilated convolution and skip connection to extract more feature information for follow-up processing.We validate attention-relation network on the mobile phone screen defect dataset.The experimental results show that the classification accuracy of the attentionrelation network is 0.9486 under the 5-way 1-shot training strategy and 0.9039 under the 5-way 5-shot setting.It achieves the excellent effect of classification for mobile phone screen defects and outperforms with dominant advantages.

PdCu alloy anchored defective titania for photocatalytic conversion of carbon dioxide into methane with 100% selectivity

The photoreduction of CO_(2)into CH_(4)with simultaneous high activity and selectivity is a promising strategy to increase energy supply and alleviate global warming.However,the absence of the active sites that is responsible for the adsorption and activation of CO_(2)and the generation of CO and H2via side reactions often lead to poor efficiency and low selectivity of the catalyst.Herein,Cu,Pd,and PdCu metal clusters cocatalyst-anchored defective TiO_(2)nanotubes(Cu/TiO_(2)-SBO,Pd/TiO_(2)-SBO,and Pd1Cu1/TiO_(2)-SBO)were designed via a simple solution impregnation reduction and applied for photocatalytic conversion of CO_(2)to CH_(4).The Pd1Cu1/TiO_(2)-SBO photocatalyst exhibits excellent catalytic performance among the other catalysts for photoreduction of CO_(2)into CH_(4).More interestingly,the product selectivity of CH_(4)reaches up to 100%with a rate of 25μmol g^(-1)h^(-1).In-situ diffuse reflectance infrared Fourier transform spectroscopy(DRIFTS)and density functional theory(DFT)simulations indicate that the main reasons for the high selectivity of CH_(4)are attributed to the PdCu alloy and oxygen vacancies,which jointly enhance the photoinduced carrier separation and lower energy barriers of key intermediates.Moreover,due to the tunable d-band center of the Cu site in the PdCu alloy,the generated intermediates can be well prevented from poisoning and promoted to participate in further reactions.Hopefully,the current study will provide insight into the development of new,highly selective photocatalysts for the visible light-catalytic reduction of CO_(2)into CH_(4).

Strip steel surface defect detection algorithm based on improved Faster R-CNN

To solve the problems of the low accuracy and poor real-time performance of traditional strip steel surface defect detection meth-ods,which are caused by the characteristics of many kinds,complex shapes,and different scales of strip surface defects,a strip steel surface defect detection algorithm based on improved Faster R-CNN is proposed.Firstly,the residual convolution module is inserted into the Swin Transformer network module to form the RC-Swin Transformer network module,and the RC-Swin Transformer module is introduced into the backbone network of the traditional Faster R-CNN to enhance the ability of the network to extract the global feature information of the image and adapt to the complex shape of the strip steel surface defect.To improve the attention of the network to defects in the image,a CBAM-BiFPN network module is designed,and then the backbone network is combined with the CBAM-BiFPN network to realize the de-tection and fusion of multi-scale features.The RoI align layer is used instead of the RoI pooling layer to improve the accuracy of defect loca-tion.Finally,Soft NMS is used to achieve non-maximum suppression and remove redundant boxes.In the comparative experiment on the NEU-DET dataset,the improved algorithm improves the mean average precision by 4.2%compared with the Faster R-CNN algorithm,and also improves the average precision by 6.1%and 6.7%for crazing defect and rolled-in scale defect,which are difficult to detect with the Faster R-CNN algorithm.The experiments show that the improvements proposed in the paper effectively improve the detection accuracy of the algorithm and have certain practical value.