Search

In mechanical engineering, monitoring steel surface defects is crucial for ensuring the quality of industrial products, as these defects account for over 90% of flaws in steel items. Traditional manual inspection methods are time-consuming and may overlook some defects. To address these challenges, this study introduces an automated deep learning (DL) model for continuous monitoring of steel surface defects using real-world images from the Industrial Machine Tool Component Surface Defect (IMTCSD) dataset, which includes 1,104 three-channel images, 394 of which are categorized as exhibiting "pitting" damage. This study evaluated several Convolutional Neural Network (CNN) classifiers: EfficientNetB3, ResNet-50, and MobileNetV2, to determine the most effective model for defect detection. EfficientNetB3 is distinguished by its scalable architecture that adapts efficiently across various image dimensions, making it ideal for high-accuracy applications on limited computational resources. ResNet-50 uses residual connections to maintain performance in deeper networks by facilitating smooth gradient flow, yet it requires more computational power. MobileNetV2, designed for real-time applications on devices with limited resources, uses lightweight depthwise separable convolutions. The performance of these models was assessed using accuracy, recall, precision, specificity, F1-score, and AUC metrics. EfficientNetB3 emerged as the best performing model, achieving an accuracy of 0.981, specificity of 0.975, recall of 0.987, precision of 0.975, and an F1-score of 0.982. This model proved effective in detecting defects even on dirty surfaces, demonstrating its potential to significantly enhance quality control in industrial settings. [ABSTRACT FROM AUTHOR]

Copyright of Materiały Budowlane is the property of Wydawnictwo SIGMA-NOT and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The main objective of this research is to create and improve three different object identification techniques for identifying surface flaws and categorising dimensions in steel that has been fabricated. RetinaNet, YOLOv3, and Faster R-CNN are the selected modalities in the experiment. The main goal is to evaluate these modalities' ability to detect and classify defects on steel surfaces in terms of accuracy, precision, recall, and F1 score. This assessment makes use of a varied collection of steel surface photos that show different kinds and sizes of faults. Training, validation, and testing sets make up the dataset's partitioning. The training set is used to train and optimise the three modalities, while the testing and validation sets are used to evaluate their performance. According to the study's findings, all three methods provide excellent of 0.92. RetinaNet comes in second with an F1 score of 0.89, followed by YOLOv3 with an F1 score of 0.87, while the Faster R-CNN modality obtains the greatest overall performance with an F1 score. [ABSTRACT FROM AUTHOR]

The success of machine learning (ML) models in object or pattern recognition naturally leads to ML being employed in the classification of the microstructure of steel surfaces. Light optical microscopy (LOM) is the traditional imaging process in this field. However, the increasing use of ML to extract or relate more aspects of the aforementioned materials and the limitations of LOM motivated us to provide an improvement to the established image acquisition process. In essence, we perform style transfer from LOM to scanning electron microscopy (SEM) combined with “intelligent” upscaling. This is achieved by employing an ML model trained on a multimodal dataset to generate an SEM-like image from the corresponding LOM image. This transformation, in our opinion, which is corroborated by a detailed analysis of the source, target and prediction, successfully pushes the limits of LOM in the case of steel surfaces. The expected consequence is the improvement of the precise characterization of advanced multiphase steels’ structure based on these transformed LOM images.

The success of machine learning (ML) models in object or pattern recognition naturally leads to ML being employed in the classification of the microstructure of steel surfaces. Light optical microscopy (LOM) is the traditional imaging process in this field. However, the increasing use of ML to extract or relate more aspects of the aforementioned materials and the limitations of LOM motivated us to provide an improvement to the established image acquisition process. In essence, we perform style transfer from LOM to scanning electron microscopy (SEM) combined with "intelligent" upscaling. This is achieved by employing an ML model trained on a multimodal dataset to generate an SEM-like image from the corresponding LOM image. This transformation, in our opinion, which is corroborated by a detailed analysis of the source, target and prediction, successfully pushes the limits of LOM in the case of steel surfaces. The expected consequence is the improvement of the precise characterization of advanced multiphase steels' structure based on these transformed LOM images. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Ground Improvement is the property of Journal of Ground Improvement Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In steel production, defect detection is crucial for preventing safety risks, and improving the accuracy of steel defect detection in industrial environments remains challenging due to the variable types of defects, cluttered backgrounds, low contrast, and noise interference. Therefore, this paper introduces a steel surface defect detection model, DBCW-YOLO, based on YOLOv5. Firstly, a new feature fusion strategy is proposed to optimize the feature map fusion pair model using the BiFPN method to fuse information at multiple scales, and CARAFE up-sampling is introduced to expand the sensory field of the network and make more effective use of the surrounding information. Secondly, the WIoU uses a dynamic non-monotonic focusing mechanism introduced in the loss function part to optimize the loss function and solve the problem of accuracy degradation due to sample inhomogeneity. This approach improves the learning ability of small target steel defects and accelerates network convergence. Finally, we use the dynamic heads in the network prediction phase. This improves the scale-aware, spatial-aware, and task-aware performance of the algorithm. Experimental results on the NEU-DET dataset show that the average detection accuracy is 81.1, which is about (YOLOv5) 6% higher than the original model and satisfies real-time detection. Therefore, DBCW-YOLO has good overall performance in the steel surface defect detection task. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

An enhanced steel surface defect detection algorithm based on YOLOv8 was introduced to enhance the accuracy of small target detection. This algorithm incorporates an attention-free mechanism to calculate attention-weight, aiding in the extraction of specific feature regions. Additionally, improvements were made to the SPPF module to expand the receptive field and enhance target detection optimization. Experimental evaluations on the NEU-DET dataset demonstrated significant enhancements over the original YOLOv8 algorithm. The improved algorithm exhibited a 9.3 percentage point increase in precision, a 10 percentage point increase in recall, a 4.6 percentage point increase in mAP@0.5, and a remarkable 21.2 percentage point increase in mAP@0.5:0.95.Significant progress has also been made in analyzing the surface data of aluminum sheets. The enhanced algorithm has shown a 6% increase in precision compared to the original YOLOv8 algorithm. Additionally, recall has improved by 3.2%, mAP@0.5 has increased by 4.1%, and mAP@0.5:0.95 has seen a notable rise of 17.4%.

In order to improve the problem of insufficient measurement scale and accuracy in the process of fracture toughness testing by indentation method, a method for assessing the fracture toughness of steel based on Berkovich indentation strain energy density (SED) is proposed based on the critical indentation energy (CIE) method. The fracture toughness of nine steels is evaluated by considering both elastic and plastic energies and correcting the critical total pressure depth. The results show that the relative error of the toughness measured by considering only the plastic energy is found to be in the range of 5% to 20%, whereas the relative error of the toughness measured by considering both the elastic and plastic energies is found to be within 5%. At the same time, determining the fitting range for the critical total indentation depth requires avoiding the region where the elastic modulus of the material rises near the surface. These improve the accuracy of evaluating the fracture toughness of steel based on the CIE method using the Berkovich indenter. [ABSTRACT FROM AUTHOR]

Slagging and fouling of boilers are typical technological problems in the combustion of solid fuels (especially coal and biomass). This study proposes a novel approach based on laser texturing of the near-surface layer of steel used to make heating surfaces of coal-fired boilers. This approach is aimed at improving the resistance of metal surfaces to slagging. The formation of slag deposits on the surfaces of AISI 310 S steel modified by laser radiation has been experimentally studied. The formation of slag melt was analyzed on the surface of modified and polished steel plates during heating to 1400 °C. High-temperature heating and interaction with slag led to a change in the chemical composition of the steel. A significant increase in the chromium content (up to 47%) of the steel surface and the transformation of its texture with the formation of grains up to 2.5 µm in size were established. Laser surface treatment significantly increased the resistance of the steel to such changes and also reduced the grain size to 1.5 µm. As a result of laser modification of surfaces, the temperature of slag formation shifts to higher values (higher by 60–75 °C compared to the unmodified polished surface). The anisotropic texture (cauliflower type) contributed to a decrease in the size of the slag spreading front, and also had by self-cleaning properties from the mineral melt. The latter allows to increase the reliability and energy efficiency of boiler equipment. [Display omitted] [ABSTRACT FROM AUTHOR]

In steel production, defect detection is crucial for preventing safety risks, and improving the accuracy of steel defect detection in industrial environments remains challenging due to the variable types of defects, cluttered backgrounds, low contrast, and noise interference. Therefore, this paper introduces a steel surface defect detection model, DBCW-YOLO, based on YOLOv5. Firstly, a new feature fusion strategy is proposed to optimize the feature map fusion pair model using the BiFPN method to fuse information at multiple scales, and CARAFE up-sampling is introduced to expand the sensory field of the network and make more effective use of the surrounding information. Secondly, the WIoU uses a dynamic non-monotonic focusing mechanism introduced in the loss function part to optimize the loss function and solve the problem of accuracy degradation due to sample inhomogeneity. This approach improves the learning ability of small target steel defects and accelerates network convergence. Finally, we use the dynamic heads in the network prediction phase. This improves the scale-aware, spatial-aware, and task-aware performance of the algorithm. Experimental results on the NEU-DET dataset show that the average detection accuracy is 81.1, which is about (YOLOv5) 6% higher than the original model and satisfies real-time detection. Therefore, DBCW-YOLO has good overall performance in the steel surface defect detection task.

In order to improve the efficiency of small target detection of steel surface defects, an improved Yolov7- tiny steel surface defect detection algorithm is proposed. The activation function of the feature extraction network is changed to SiLU to improve the feature extraction capability. The tensor splicing operation of the feature fusion network is combined with the weighted bidirectional feature pyramid BiFPN, and the nearest interpolation of the upper sampling part is replaced with the lightweight operator CARAFE to improve the feature fusion ability. Finally, the multi-head self-attention mechanism MHSA and SPD convolution building blocks are introduced at the output end to improve the detection performance of the output end for small targets of steel surface defects. The ablation and contrast experiments are carried out on the NEU-DET dataset. Compared with the original Yolov7-tiny algorithm, the improved algorithm has increased the mAP by 11.7 percentage points, the precision by 3.3 percentage points, and the FPS value reaches 192. The results show that the improved algorithm can effectively improve the detection efficiency of small targets of steel surface defects. Comparative experiments on the VOC2012 dataset show that the improved algorithm is universal. [ABSTRACT FROM AUTHOR]

To enhance the precision of detecting defects on steel plate surfaces and diminish the incidences of false detection and leakage, the ESI-YOLOv8 algorithm is introduced. This algorithm introduces a novel EP module and integrates the large separation convolutional attention module and the spatial pyramid pooling module to propose the SPPF-LSKA module. Additionally, the original CIOU loss function is replaced with the INNER-CIOU loss function. The EP module minimizes redundant computations and model parameters to optimize efficiency and simultaneously increases the multi-scale fusion mechanism to expand the sensory field. The SPPF-LSKA module reduces computational complexity, accelerates model operation speed, and improves detection accuracy. Additionally, the INNER-CIOU loss function can improve detection speed and model accuracy by controlling the scale size of the auxiliary border.The results of the experiment indicate that, following the improvements made, the algorithm’s detection accuracy has increased to 78%, which is 3.7% higher than the original YOLOv8. Furthermore, the model parameters were reduced, and the verification was conducted using the CoCo dataset, resulting in an average accuracy of 77.8%. In conclusion, the algorithm has demonstrated its ability to perform steel plate surface defect detection with efficiency and accuracy.

Steel is an important raw material of fluid components. The technological level limitation leads to the surface faults of the steel, thus the key to improving fluid components quality is to diagnose the faults in steel production. The complex shape and small size of steel surface faults result in the low accuracy of the diagnosis, and the large size of the network leads to poor real-time performance. Therefore, aiming at the problems, an improved YOLOV5 is proposed. Firstly, to reduce the feature information loss, coordinate attention is used to improve YOLOV5, thus the diagnosis ability can be improved. Secondly, to further reduce the loss, a new connection is constructed in YOLOV5, and the detection ability can also be further improved. Thirdly, to improve the real-time performance of the fault diagnosis, YOLOV5 is improved by the lightweight method ShuffleNetV2, and its size can be reduced. Lastly, to further improve the accuracy, the cosine annealing with warm restarts algorithm is used to optimize YOLOV5. The dataset of NEU-DET is verified and testified. The results show that improved YOLOV5 can diagnose steel surface faults with high efficiency and accuracy. [ABSTRACT FROM AUTHOR]

Features of structure organization during pulsed laser melting of steel surface layers are studied. Based on analyzing crystallization process rate kinetics it is established that temperature gradients and thermal stresses developing in irradiated metal areas during melting contribute to convective mixing of liquid at a rate of 103 cm/sec, and also, despite an extremely short laser pulse time (10–3 sec) they contribute to partial or complete dissolution of the original structure carbides. As a result, the chemical composition of melted metal changes, martensitic transformation points are lowered and a significant amount of textured metastable residual austenite (40–60%) is fixed that has a very fine structure (dendrite cross-section 5–9 nm). This has a favorable effect on irradiated material surface layer quality and mechanical properties. It is established by experiment that with a change in laser processing regime it becomes possible to achieve a wide range of cooling rates during crystallization, i.e., to control the degree of carbide dissolution, structural characteristics, and melted metal area properties. It is demonstrated that in order to achieve the maximum possible degree of hardening for irradiated steels having different chemical composition, it is necessary to dissolve 30–60% of carbides in the initial metal. As a result of this after laser irradiation material heat resistance increases by 50–100°C, and wear resistance increases by a factor of 2–4. [ABSTRACT FROM AUTHOR]

Pipeline steels are among the most common engineering materials and are used extensively in various industries. Therefore, it is essential that these materials are hydrophobic and corrosion resistant. Herein, a simple method to prepare a superhydrophobic coating on X65 steel is proposed. Firstly, the black oxide coating (BO) was grown in situ on X65 steel surface, utilizing its morphology advantage to build the micro-nano structure, where they showed a water contact angle (WCA) of 158°. After fluorination, the WCA of the coating increased to 163°. The prepared superhydrophobic samples were exposed to air and salt spray test for a 30-day durability study, where the long-lasting superhydrophobicity of the coating demonstrated its wide applicability. In addition, the coating also exhibited excellent corrosion resistance and self-cleaning property. This work provides a simple and low-cost technique for designing superhydrophobic coatings on steels. [ABSTRACT FROM AUTHOR]

With the development of artificial intelligence technology and the popularity of intelligent production projects, intelligent inspection systems have gradually become a hot topic in the industrial field. As a fundamental problem in the field of computer vision, how to achieve object detection in the industry while taking into account the accuracy and real-time detection is an important challenge in the development of intelligent detection systems. The detection of defects on steel surfaces is an important application of object detection in the industry. Correct and fast detection of surface defects can greatly improve productivity and product quality. To this end, this paper introduces the MSFT-YOLO model, which is improved based on the one-stage detector. The MSFT-YOLO model is proposed for the industrial scenario in which the image background interference is great, the defect category is easily confused, the defect scale changes a great deal, and the detection results of small defects are poor. By adding the TRANS module, which is designed based on Transformer, to the backbone and detection headers, the features can be combined with global information. The fusion of features at different scales by combining multi-scale feature fusion structures enhances the dynamic adjustment of the detector to objects at different scales. To further improve the performance of MSFT-YOLO, we also introduce plenty of effective strategies, such as data augmentation and multi-step training methods. The test results on the NEU-DET dataset show that MSPF-YOLO can achieve real-time detection, and the average detection accuracy of MSFT-YOLO is 75.2, improving about 7% compared to the baseline model (YOLOv5) and 18% compared to Faster R-CNN, which is advantageous and inspiring. [ABSTRACT FROM AUTHOR]

Owing to the high hardness and hydrogen passivation of carbon bonds, hydrogenated diamond‐like carbon (a‐C:H) film has shown promising potential to achieve ultra‐low friction and wear on steel surfaces. Here, a‐C:H film was successfully deposited on 9Cr18Mo steel via programmable high power pulse magnetron sputtering and potential application for industrial was evaluated. The a‐C:H films against different mating materials of GCr15 steel balls, Al2O3, Si3N4, ZrO2, and a‐C:H‐coated GCr15 balls all showed ultra‐low friction under a normal load of 5 N in a dry ambient air environment. Among them, self‐mating tribo‐system a‐C:H films on steel surfaces and a‐C:H‐coated steel balls achieve best friction performance; the principal reason is that both contacting surfaces coated with a‐C:H film have the lower electron affinities compared with other tribo‐systems. However, the differences of coefficient of friction (COF) for uncoated‐GCr15, Al2O3, ZrO2, Si3N4, and a‐C:H(GCr15) balls can be attributed to different sizes of clustering in wear debris. This work provides new insights on synthesis and industry application of the a‐C:H films with ultra‐low friction properties. [ABSTRACT FROM AUTHOR]

With the advance in Industry 4.0, smart industrial monitoring has been proposed to timely discover faults and defects in industrial processes. Steel is widely used in manufacturing equipment, and steel surface defect inspection is of great significance to the normal operation of steel equipment in manufacturing workshops. In steel defect inspection systems, industrial inspection robots generate images via scanning steel surface, and processors perform surface defect inspection algorithms on images. We focus on applying advanced object detection techniques to surface defect inspection algorithm for sheet steel. In the proposed steel surface defect inspection model, a deformable convolution enhanced backbone network firstly extracts complex features from multi-shape steel surface defects. Then the feature fusion network with balanced feature pyramid generates high-quality multi-resolution feature maps for the inspection of multi-size defects. Finally, detector network achieves the localization and classification of steel surface defects. The proposed model is evaluated on a typical steel surface defect dataset. Our model achieves 0.805 mAP, 0.144 higher than baseline models, and our model shows high efficiency in inference. Experiments are performed to reveal the effect of employed approaches, and results also show our model achieves a balance between inspection performance and inference efficiency. [ABSTRACT FROM AUTHOR]

With the development of artificial intelligence technology and the popularity of intelligent production projects, intelligent inspection systems have gradually become a hot topic in the industrial field. As a fundamental problem in the field of computer vision, how to achieve object detection in the industry while taking into account the accuracy and real-time detection is an important challenge in the development of intelligent detection systems. The detection of defects on steel surfaces is an important application of object detection in the industry. Correct and fast detection of surface defects can greatly improve productivity and product quality. To this end, this paper introduces the MSFT-YOLO model, which is improved based on the one-stage detector. The MSFT-YOLO model is proposed for the industrial scenario in which the image background interference is great, the defect category is easily confused, the defect scale changes a great deal, and the detection results of small defects are poor. By adding the TRANS module, which is designed based on Transformer, to the backbone and detection headers, the features can be combined with global information. The fusion of features at different scales by combining multi-scale feature fusion structures enhances the dynamic adjustment of the detector to objects at different scales. To further improve the performance of MSFT-YOLO, we also introduce plenty of effective strategies, such as data augmentation and multi-step training methods. The test results on the NEU-DET dataset show that MSPF-YOLO can achieve real-time detection, and the average detection accuracy of MSFT-YOLO is 75.2, improving about 7% compared to the baseline model (YOLOv5) and 18% compared to Faster R-CNN, which is advantageous and inspiring.

The corrosion behavior of steel in 0.5 M H2SO4 solution in the presence of polyethylene glycol (PEG 6000) as a green corrosion inhibitor was investigated under well-defined hydrodynamic conditions simulated by a steel rotating disk electrode with the rotation speeds of 250–5000 rpm. The results obtained from electrochemical impedance spectroscopy and potentiodynamic polarization measurements demonstrated the better protection of steel at higher concentrations of the polymer. Additionally, the corrosion inhibition experienced a dramatic reduction in going from hydrostatic to hydrodynamic conditions. This was indicated by corrosion resistance (Rcorr), which reduced from 162 Ω cm2 at the stagnant condition to 65.7 Ω cm2 at the dynamic state with a flow rate of just 250 rpm in the presence of 5 g L−1 PEG. This observation was a consequence of the transportation of corrosion products from the metal surface toward the bulk in fluid flow conditions, leading to a restriction in the formation of an adhesive protection layer on the steel surface. [ABSTRACT FROM AUTHOR]

Inspecting steel surfaces is important to ensure steel quality. Numerous defect-detection methods have been developed for steel surfaces. However, they are primarily used for local defects, and their accuracy in detecting distributed defects is unsatisfactory because such defects are difficult to locate and have complex texture characteristics. To solve these issues, an improved random forest algorithm with optimal multi-feature-set fusion (OMFF-RF algorithm) is proposed for distributed defect recognition in this paper. The OMFF-RF algorithm includes the following three aspects. First, a histogram of oriented gradient (HOG) feature-set and a gray-level co-occurrence matrix (GLCM) feature-set are extracted and fused to describe local and global texture characteristics, respectively. Second, given the small number of samples of distributed defect images and the high dimensionality of the extracted feature-sets, a random forest algorithm is introduced to perform defect classification. Third, the feature-sets vary greatly in performance and dimensionality. To improve the fusion efficiency, OMFF-RF merges the HOG feature-set and the GLCM feature-set through a multi-feature-set fusion factor, which changes the number of decision trees that correspond to each feature-set in the RF algorithm. The OMFF factor is found by optimizing the fitting curve of the classification accuracy of the test set using a stepping multi-feature-set fusion factor. In experiments, the effectiveness of the proposed OMFF-RF was verified using 5 types of distributed defects collected from an actual steel production line. OMFF-RF achieved a recognition accuracy of 91%, a result superior to support vector machine (SVM) and conventional RF algorithms. [ABSTRACT FROM AUTHOR]

Sorption and phase distribution of 54Mn, 59Fe, 60Со, 106Ru, 125Sb, 137Cs, 144Се, 154,155Eu, and 235,238U radionuclides in contact of the Pb-Bi melt with the steel surface were studied. Radionuclides of the elements with the minimal oxygen affinity (Ru, Te, and Sb) remain mainly in the coolant melt and are weakly sorbed onto the solid phase. The other fission product radionuclides having higher oxygen affinity are sorbed onto the surface of steel structural materials. The sorption increases at 350-400°С. [ABSTRACT FROM AUTHOR]

For steel surface defect recognition, feature extraction and classification are very important steps. In this paper, multi-type statistical features and enhanced twin support vector machine classifier are formulated and applied. Firstly, four types of statistical features for different attributes of defect region are proposed. They are insensitive to affine transformation in scale and rotation. And those attributes include shape distance and local binary pattern operators with sign and magnitude. Then, dummy boundary samples and representative samples are extracted from steel surface defect dataset. Dummy boundary samples include the sparse boundary information of dataset. They can reduce the adverse impact of noise samples. Representative samples with local and global properties are used to replace samples with quadratic loss. They can exclude noise samples. Based on dummy boundary samples and representative samples, enhanced twin support vector machine is formulated. On one hand, it can solve multi-class classification problem. On the other hand, it has anti-noise ability and high classification efficiency. At last, enhanced twin support vector machine classifier and multi-type statistical features are applied to recognize five types of steel surface defects. The experimental results show that our proposed multi-class classifier has perfect performance in efficiency and accuracy. And multi-type statistical features are in favor of improving classification performance. [ABSTRACT FROM AUTHOR]

Solid polymer composite systems are widely being used for potential technological applications in secondary energy sources and electrochromic devices. In this study, we synthesized and characterized a composite material composed of polyaniline (PANI) and natural needle platy (NPG) vein graphite. Fourier transform infrared spectroscopy (FTIR), X-ray diffraction (XRD), cyclic voltammetry (CV), scanning electron microscopy (SEM), X-ray photoelectron spectroscopy (XPS), micro-Raman analysis, thermogravimetric and differential thermal analysis (TGA/DTA), transmission electron microscopy (TEM) were used to study the structural and electrochemical properties of the prepared PANI/NPG graphite composite. XPS, FTIR, and micro-Raman analysis confirmed the existence of relevant functional groups and bonding in the prepared PANI/NPG composite material. The composite shows a very low corrosion rate, approximately 29 μm per year, and high hydrophobicity on steel surfaces, which helps to prevent the corrosion due to O 2 penetration towards the metal surface. It indicates that the composite can be used as a high potential surface coating material to anticorrosion. The specific capacitance of PANI/NPG composite is 833.3 F g −1 , which is higher than that of PANI. This synergistic electrical performance result proves the prepared PANI/NPG graphite composite as a suitable protective coating material for steel surfaces. [ABSTRACT FROM AUTHOR]

The influence of steel surface finishing and pH of simulated concrete pore solutions (SCPS) on the chloride threshold value (CTV) was evaluated. Steel samples were analysed, with four different finishes: as received (T), diamond-polished (D), polished (P500) and pre-oxidized (DH). The studies were performed in SCPS with pH values of 11.6 and 13.5, and of different chloride concentrations. The electrochemical behaviour of the samples was assessed using open circuit potential, potentiodynamic polarization curves and scanning vibrating electrode techniques. The surface of the steel samples was observed by optical microscopy and SEM/EDS. The results showed that the samples were ranked D > DH > P500 > T for the CTV after which pitting corrosion occurs. The highest chloride threshold value was found in D samples. [ABSTRACT FROM AUTHOR]

There are several types of steel products, such as wire rods, cold-rolled coils, hot-rolled coils, thick plates, and electrical sheets. Surface stains on cold-rolled coils are considered defects. However, surface stains on thick plates are not considered defects. A conventional optical structure is composed of a camera and lighting module. A defect inspection system that uses a dual lighting structure to distinguish uneven defects and color changes by surface noise is proposed. In addition, an image processing algorithm that can be used to detect defects is presented in this paper. The algorithm consists of a Gabor filter that detects the switching pattern and employs the binarization method to extract the shape of the defect. The optics module and detection algorithm optimized using a simulator were installed at a real plant, and the experimental results conducted on thick steel plate images obtained from the steel production line show the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Computer vision is augmented in various manufacturing industries to perform automated inspection operations accurately and efficiently. It has been observed that the performance of vision-based inspection approaches degrades considerably upon utilizing images captured under shop-floor conditions. This work proposes utilizing Histogram Equalization and adversarial training through Neural Structure Learning (NSL) for developing a robust vision-based Surface Defect Classification framework. A novel deep neural network architecture obtains adversarial samples in the extracted feature space instead of obtaining the same in the original input image space. The architecture can be easily integrated and employed with various machine learning models. A commonly employed steel surface defect dataset (NEU) with practical relevance to industrial cases is selected for the model training and experimental studies. The robustness of the proposed approach is evaluated over the Extended Diversity Enhanced (ENEU) dataset derived by simulating image acquisition variations similar to shop floor conditions. The results reveal that the proposed approach enhances the recognition accuracy of the baseline method from 87.7% to 92.4% over ENEU. The prediction accuracy of the proposed approach is considerably better than the traditional methods and deep learning competitors over ENEU. The qualitative and quantitative comparison of results obtained using the present approach with methods reported in the literature demonstrates the effectiveness of adversarial training in improving the generalization abilities of machine learning models. [ABSTRACT FROM AUTHOR]

Contrasts of low-voltage secondary electron microscope images have been experimentally investigated using commercial instruments having an annular type in-lens (IL) detector. The topographic and material contrasts of oxide particles on steel surfaces in the secondary electron microscope images recorded by the IL and the Everhart-Thonley detectors systematically change as a function of working distance. It is found that these two contrasts are divided using the different concentric areas of the IL detector surface. These results are discussed in terms of the kinetic energy of the detected electrons. Two simple methods for the information selection using one IL-type detector are proposed. Copyright © 2015 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Surface analysis techniques using electron microscopy for steel products are reviewed. The recent progress in scanning electron microscopy (SEM), transmission electron microscopy (TEM), and focused ion beam (FIB) are presented with some applications to steel surfaces, coating layers, and corrosion products. [ABSTRACT FROM AUTHOR]

Chemical etching technique is widely used for restoration of obliterated engraved marks on steel surface in the field of public security. The consumed thickness of steel surface during restoration process is considered as a major criterion for evaluating the efficiency of the chemical etching reagent. The thinner the consumed thickness, the higher the restoration efficiency. According to chemical principles, maintaining the continuous oxidative capabilities of etching reagents and increasing the kinetic rate difference of the reaction between the engraved and non-engraved area with the chemical etching reagent can effectively reduce the consumed steel thickness. The study employed steel surface from the engine case of motorcycle and the car frame of automobile. The chemical etching reagents are composed of nitric acid as the oxidizer, hydrofluoric acid as the coordination agent and mixed with glacial acetic acid or acetone as the solvents. Based on the performance evaluation of three different etching reagents, the one composed of HNO3, HF and acetone gave the best result. [ABSTRACT FROM AUTHOR]

The adsorption and inhibition effect of two aminopyrimidine derivatives of 2-aminopyrimidine (AP) and 2,4-diaminopyrimdine (DAP) on steel surface in 0.5 M H2SO4 solution were studied by weight loss, open circuit potential (OCP), potentiodynamic polarization curves, electrochemical impedance spectroscopy (EIS) and scanning electron microscope (SEM) methods. Quantum chemical calculation of density function theory (DFT) and molecular dynamics (MD) simulations were applied to theoretically determine the relationship between molecular structure and inhibition efficiency. The results show that two aminopyrimidine derivatives act as good inhibitors, and inhibition efficiency follows the order: DAP > AP. The adsorption of each inhibitor on steel surface obeys Langmuir adsorption isotherm. Both AP and DAP are arranged as mixed-type inhibitors. EIS diagram appears a large capacitive loop at high frequencies (HF) followed by a small inductive loop at low frequencies (LF), and the addition of aminopyrimidine inhibitor increases the impedance of electrode. The electron densities of both HOMO and LUMO are localized principally on the pyrimidine ring, which could be both the acceptor of the electron and the donor of the electron. The donating electrons to metal follows the order: DAP > AP, which is in completely accordance with that of inhibitive performance. MD simulations reveal both aminopyrimidine molecules adsorb on the Fe(001) surface in the nearly flat manner, and the sequence of either adsorption energy (Eads) or binding energy (Ebin) agrees well with that of inhibition efficiency. [ABSTRACT FROM AUTHOR]

Synergism of Saccharum officinarum (sugarcane) and Ananas comosus (pineapple) extract additives on the quality of electroplated zinc on mild steel in acid chloride solution was investigated experimentally at ambient temperature (~28 °C). The experiments were performed at different plating times (15 and 18 min), additive concentrations (2, 2.5, 3 ml/50 ml of acid chloride solution), pH 5, temperature (27-30 °C), current (0.08 A), and voltage (13 V DC) conditions. Zinc electroplating on mild steel was performed using a DC-supply. The surface of the plated steel was examined with scanning electron microscopy, and energy dispersive spectroscopy for surface elemental composition analysis. Different surface characteristics were obtained depending upon the concentration of the additive and the plating time. The corrosion resistance of the plated surface was determined by a gravimetric method. Microstructural morphology of the plated surface indicated a good quality electroplating that was better than either the sugarcane or pineapple extracts alone. The electroplating process was sensitive to changes in additive concentration and plating time. Any variation in the plating parameter produced an entirely new and different surface crystal morphology. [ABSTRACT FROM AUTHOR]