Strip Defects Research Articles

Cross-domain fine grained strip steel defect detection method based on semi-supervised learning and Multi-head Self Attention coordination

The identification of steel strip defects plays a pivotal role in assessing steel quality and advancing production technology. However, the majority of intelligent defect recognition algorithms for steel strips, based on deep learning, primarily focus on supervised learning. These methods depend on a multitude of training samples, incurring additional manual labelling costs, and exhibit low recognition efficiency. In contrast to supervised learning, we integrate the fine-grained characteristics of strip defects. We propose a cross-domain, fine-grained strip defect detection method based on semi-supervised learning and Multi-head self-attention coordination, along with an improvement strategy, resulting in a novel network structure: Multi-head Self Attention and Semi-supervised collaborative detection network (MSD Net). This method initiates the cross-domain migration of defect samples through Cycle Generative Adversarial Networks (Cycle GAN), creating new semi-supervised training samples from source domain and target domain data to enhance data distribution diversity. The detection model is then constructed leveraging the advantages of Multi-head Self Attention (MSA) in augmenting the global receptive field of feature extraction. The proposed semi-supervised learning method employs a pseudo-label allocation strategy to guide the model in fully utilizing the distribution fitting of unlabeled samples. This allows the deep neural network to learn a more comprehensive multivariate data distribution within the training set, thereby enhancing the generalization ability of the semi-supervised model. Experimental results on the benchmark dataset for steel strip defect detection demonstrate that the cross-domain semi-supervised method achieves a test accuracy of 96.1 % on mAP@0.5, surpassing the supervised baseline model by 4.8 %. Our method also outperforms the baseline supervised model in the accuracy of small target recognition on PASCAL VOC 2007 datasets. Additionally, we have implemented a strip defect detection system based on edge computing for real-time deployment of the proposed algorithm. Testing in an actual industrial setting further validates the efficacy of our proposed method in practical applications. Our work encourages further exploration, the task of public datasets can be obtained at https://github.com/songzhiweiknight/NEU-DET-Datasets.git.

DCW-YOLO: An Improved Method for Surface Damage Detection of Wind Turbine Blades

Wind turbine blades (WTBs) are prone to damage from their working environment, including surface peeling and cracks. Early and effective detection of surface defects on WTBs can avoid complex and costly repairs and serious safety hazards. Traditional object detection methods have disadvantages of insufficient detection capabilities, extended model inference times, low recognition accuracy for small objects, and elongated strip defects within WTB datasets. In light of these challenges, a novel model named DCW-YOLO for surface damage detection of WTBs is proposed in this research, which leverages image data collected by unmanned aerial vehicles (UAVs) and the YOLOv8 algorithm for image analysis. Firstly, Dynamic Separable Convolution (DSConv) is introduced into the C2f module of YOLOv8, allowing the model to more effectively focus on the geometric structural details associated with damage on WTBs. Secondly, the upsampling method is replaced with the content-aware reassembly of features (CARAFE), which significantly minimizes the degradation of image characteristics throughout the upsampling process and boosts the network’s ability to extract features. Finally, the loss function is substituted with the WIoU (Wise-IoU) strategy. This strategy allows for a more accurate regression of the target bounding boxes and helps to improve the reliability in the localization of WTBs damages, especially for low-quality examples. This model demonstrates a notable superiority in surface damage detection of WTBs compared to the original YOLOv8n and has achieved a substantial improvement in the mAP@0.5 metric, rising from 91.4% to 93.8%. Furthermore, in the more rigorous mAP@0.5–0.95 metric, it has also seen an increase from 68.9% to 71.2%.

Multi-level joint distributed alignment-based domain adaptation for cross-scenario strip defect recognition

Multi-level joint distributed alignment-based domain adaptation for cross-scenario strip defect recognition

Sketch-guided spatial adaptive normalization and high-level feature constraints based GAN image synthesis for steel strip defect detection data augmentation

Deep learning methods have made remarkable strides in surface defect detection. But, they heavily rely on large amount of training data, which can be a costly endeavor, especially for specific applications like steel strip surface defect detection, where acquiring and labeling large-scale data is impractical due to the rarity of certain defective categories in production environment. Hence, realistic defect image synthesis can greatly alleviate this issue. However, training image generation networks also demand substantial data, making image data augmentation merely an auxiliary effort. In this work, we propose a Generative Adversarial Network (GAN)-based image synthesis framework. We selectively extract the defect edges of the original image as well as the background texture information, and use them as network input through the spatially-adaptive (de)normalization (SPADE) module. This enriches the input information, thus significantly reducing the amount of training data for GAN network in image generation, and enhancing the background details as well as the defect boundaries in the generated images. Additionally, we introduce a novel generator loss term that balances the similarity and perceptual fidelity between synthetic and real images by constraining high-level features at different feature levels. This provides more valuable information for data augmentation in training object detection models using synthetic images. Our experimental results demonstrate the sophistication of the proposed image synthesis method and its effectiveness in data augmentation for steel strip surface defect detection tasks.

Formation and Evolution Mechanism of the Inclusions of Al2O3·SiO2·CaO and Al2O3·SiO2·CaO·MgO in Seamless Steel Tube Steel

Herein, the formation and evolution mechanism of inclusions of Al2O3·SiO2·CaO and Al2O3·SiO2·CaO·MgO in seamless steel tube steel are investigated. In the long strip defects on the longitudinal cross section of the steel tube after the rolling bar piercing, the defect is mainly formed by Al2O3·SiO2·CaO·MgO inclusions and Al2O3·SiO2·CaO·inclusions dotted with·CaS inclusions after the rolling. The typical inclusions in the different steelmaking stages are mainly composed of CaS, Al2O3·(SiO2), CaO·(SiO2), MnS·(TiN), Al2O3·SiO2·CaO·(CaS)·(MnS), Al2O3·SiO2·CaO·MgO·(MnO), Al2O3·SiO2·CaO·MgO·(CaS)·(MnS), etc. In the billet, the average sizes of Al2O3·SiO2·CaO‐based and Al2O3·SiO2·CaO·MgO‐based inclusions are much larger than those of the other types of inclusions. Part of SiO2 in the deoxidized products SiO2 can be reduced by [Al], resulting in the formation of the Al2O3·SiO2 composite inclusions. The SiO2 in Al2O3·SiO2 inclusions can continuously be reduced by the dissolved [Ca] to form the Al2O3·SiO2·CaO composite inclusions. The SiO2 in the Al2O3·SiO2·CaO inclusions can be reduced by the dissolved [Mg] to form the Al2O3·SiO2·CaO·MgO composite inclusions. Another formation process of Al2O3·SiO2·CaO·MgO inclusions is the entrapment of ladle slag in the vacuum degassing (VD) stage, due to the strong agitation of the rising Ar bubbles in the vacuum condition of the VD stage.

Defect modes and localisation of quasi-Lamb waves along a sidewall of corrugated aluminium plates

This study presents an observation of quasi-Lamb wave (QLW) localisation in a periodically corrugated plate with defects. The QLWs are excited and detected on one side of aluminium plates that are periodically grooved on the upper and lower planes with a strip defect. The periodic grooves result in the frequency forbidden band, whereas the defect is responsible for the additional transmission in this band. The QLW-amplitude measurements along the aluminium plates exhibit the transmission spectra of the defect modes as well as the QLW localisation near the middle strip. The numerical and experimental results confirm the additional transmission of the QLW defect mode and its frequency shifting. As the defect length increases, the transmission peak moves from the upper to the lower edges of the forbidden band. Furthermore, the calculated dispersion curves of the QLWs break at the frequency of the forbidden bands, and a localised mode appears in the middle when the defect length is nonzero. The experimentally observed QLW defect modes in elastic plates not only enrich our knowledge on the interaction between elastic waves and structures but also significantly benefit related engineering applications, such as ultrasonic non-destructive evaluation, elastic-wave filtering, and undersea acoustic-signal enhancement.

Steel Strip Defect Sample Generation Method Based on Fusible Feature GAN Model under Few Samples.

Due to the shortage of defect samples and the high cost of labelling during the process of hot-rolled strip production in the metallurgical industry, it is difficult to obtain a large quantity of defect data with diversity, which seriously affects the identification accuracy of different types of defects on the steel surface. To address the problem of insufficient defect sample data in the task of strip steel defect identification and classification, this paper proposes the Strip Steel Surface Defect-ConSinGAN (SDE-ConSinGAN) model for strip steel defect identification which is based on a single-image model trained by the generative adversarial network (GAN) and which builds a framework of image-feature cutting and splicing. The model aims to reduce training time by dynamically adjusting the number of iterations for different training stages. The detailed defect features of training samples are highlighted by introducing a new size-adjustment function and increasing the channel attention mechanism. In addition, real image features will be cut and synthesized to obtain new images with multiple defect features for training. The emergence of new images is able to richen generated samples. Eventually, the generated simulated samples can be directly used in deep-learning-based automatic classification of surface defects in cold-rolled thin strips. The experimental results show that, when SDE-ConSinGAN is used to enrich the image dataset, the generated defect images have higher quality and more diversity than the current methods do.

Surface Defect Detection of Steel Strip with Double Pyramid Network

Defect detection on the surface of the steel strip is essential for the quality assurance of the steel strip. Precise localization and classification, the two significant tasks of defect detection, still need to be completed due to the diversity of defect scales. In this paper, a residual atrous spatial pyramid pooling (RASPP) module is first designed to enrich the multi-scale information of the feature maps and increase the receptive field of the feature maps. Secondly, a double pyramid network (DPN) that combines RASPP and feature pyramid is proposed to fuse multi-scale features further so that similar semantic features are shared among the features of each layer. Finally, DPN-Detector, an automatic surface defects detection network, is proposed, which embeds the DPN module into Faster R-CNN and replaces the original detection head with a designed double head. Experiments are carried out on the steel strip surface defect dataset (NEU-DET), and the results show that the mAP of DPN-Detector is as high as 80.93%, which is 3.52% higher than that of the baseline network Faster R-CNN. The classification accuracy is 74.64%, and the detection speed reaches 18.62 FPS. The proposed method performs better robustness, classification and regression capability than other steel strip defect detection methods.

Faster Metallic Surface Defect Detection Using Deep Learning with燙hannel燬huffling

Deep learning has been constantly improving in recent years, and a significant number of researchers have devoted themselves to the research of defect detection algorithms. Detection and recognition of small and complex targets is still a problem that needs to be solved. The authors of this research would like to present an improved defect detection model for detecting small and complex defect targets in steel surfaces. During steel strip production, mechanical forces and environmental factors cause surface defects of the steel strip. Therefore, the detection of such defects is key to the production of high-quality products. Moreover, surface defects of the steel strip cause great economic losses to the high-tech industry. So far, few studies have explored methods of identifying the defects, and most of the currently available algorithms are not sufficiently effective. Therefore, this study presents an improved real-time metallic surface defect detection model based on You Only Look Once (YOLOv5) specially designed for small networks. For the smaller features of the target, the conventional part is replaced with a depth-wise convolution and channel shuffle mechanism. Then assigning weights to Feature Pyramid Networks (FPN) output features and fusing them, increases feature propagation and the network’s characterization ability. The experimental results reveal that the improved proposed model outperforms other comparable models in terms of accuracy and detection time. The precision of the proposed model achieved by mAP@0.5 is 77.5% on the Northeastern University, Dataset (NEU-DET) and 70.18% on the GC10-DET datasets.

A Lightweight Network for Defect Detection in Nickel-Plated Punched Steel Strip Images

As a critical component of power battery, the quality of nickel-plated punched steel strip (NPSS) is closely related to the performance of battery. In practice, however, the real-time detection for defects of NPSS with limited computating resources is a challenging task. Current research on vision-based strip defect detectors emphasizes the use of large neural network models to pursue high accuracy while ignoring the training cost and hardware requirements. To accelerate the model update and deployment cycles and reduce the application cost, a lightweight detection network for accurate and fast detection of surface defects in NPSS is developed in this article. First, a new lightweight backbone network, lightweight efficient detection network (LEDNet), is designed to extract features. Depth dynamic convolution is used as the basic structure of the network to reduce the computational complexity while adaptively extracting effective features. Thereafter, a refine-residual bidirectional aggregation network is built to enhance the bidirectional propagation and reuse high- and low-level features by further optimizing and adjusting the extracted features. On this basis, feature aggregation capability is improved. Finally, the intersection-over-union k-means algorithm is used to adjust the anchor box size, which balances the significant difference in aspect ratio of surface defects of NPSS. Experimental results on the NPSS defect dataset show that our network detection accuracy can reach 87.17%, the single-sheet detection rate is 0.09 s, and the computational complexity is reduced. Compared with the state-of-the-art detectors, it achieves a strong competitive accuracy and low computational effort, which fully meets the accuracy and real-time requirements in the production environment of NPSS.

Semi‐analytical solution for the two‐dimensional transport of organic contaminant through geomembrane with strip defects to the underlying soil liner

AbstractGeosynthetic materials are widely adopted as part of barrier liners in landfills, while the existence of defects in geomembrane (GM) will significantly reduce the barrier efficiency and lead to unexpected pollution in the surrounding environment. In this study, a novel semi‐analytical model was proposed to investigate the two‐dimensional (2D) migration of organic contaminant through the GM with strip defects to the underlying soil liner (SL). This model has the superiority to consider the concentration condition in the defects, and describe more accurate concentration profiles in the SL. The combination of discretization method and integral transforms were applied to obtain semi‐analytical solutions, which were then verified by numerical solutions. Results show that the existence of defects can substantially accelerate the migration process of contaminant through flawed GM to the underlying SL. Specifically, the time interval between migration curves in the model with defects can be 2 or 3 orders of magnitude shorter than that without defects under the same condition.

Surface Defect Detection of Rolled Steel Based on Lightweight Model

A lightweight rolled steel strip surface defect detection model, YOLOv5s-GCE, is proposed to improve the efficiency and accuracy of industrialized rolled steel strip defect detection. The Ghost module is used to replace the CBS structure in a part of the original YOLOv5s model, and the Ghost bottleneck is employed to replace the bottleneck structure in C3 to minimize the model’s size and make the network lightweight. The EIoU function is added to improve the accuracy of the regression of the prediction frame and accelerate its convergence. The CA (Coordinate Attention) attention method is implemented to reinforce critical feature channels and their position information, enabling the model to identify and find targets correctly. The experimental results demonstrate that the accuracy of YOLOv5s-GCE is 85.7%, which is 3.5% higher than that of the original network; the model size is 7.6 MB, which is 44.9% smaller than that of the original network; the number of model parameters and calculations are reduced by 47.1% and 48.8%, respectively; and the detection speed reached 58.8 fps. YOLOv5s-GCE meets the necessity for real-time identification of rolled steel flaws in industrial production compared to other common algorithms.

Surface defect detection of steel strips based on improved YOLOv4

During the production and processing of steel strips, the production process and external factors lead to surface defects that negatively impact the strips’ integrity and functionality. However, traditional manual defect detection algorithms cannot meet modern accuracy requirements. Therefore, we propose a steel strip surface defect detection method based on the improved you-only-look-once version 4 (YOLOv4) algorithm. The attention mechanism is embedded in the backbone network structure, and the path aggregation network is modified into a customised receptive field block structure, which strengthens the feature extraction functionality of the network model. From the final experimental results, relative to the original YOLOv4 algorithm, the proposed algorithm's mean average precision values in the detection of four types of steel strip defects is improved by 3.87%, reaching 85.41%, thereby providing a new detection method for daily steel strip surface defects.

SOD‐YOLO: A Small Target Defect Detection Algorithm for Wind Turbine Blades Based on Improved YOLOv5

AbstractEarly and effective detection of wind turbine blade (WTB) surface defects can avoid complex and expensive repair problems and serious safety hazards. The traditional target detection methods have the problems of insufficient detection capability, long model inference time and low recognition accuracy for small targets and long strip defects in WTB datasets. This paper proposes a high‐precision model SOD‐YOLO for WTB surface defect detection based on UAVs image analysis of YOLOv5. First, the WTB images are preprocessed by foreground segmentation and Hough transform to build the WTB defect dataset. Then, a micro‐scale detection layer is added to the original YOLOv5, and the K‐means algorithm is used to re‐cluster anchors and add the CBAM attention mechanism to each feature fusion layer to reduce the loss of feature information for small target defects and other defects. In addition, to improve the detection efficiency, the channel pruning algorithm is used to reduce the model size. The experimental results show that the average accuracy (mAP) of the SOD‐YOLO algorithm on the WTB dataset reaches 95.1%, which is 7.82% better than YOLOv5, and the FPS is 28.3% better. Therefore, SOD‐YOLO is able to detect small target defects and other defects quickly and effectively.

CASI-Net: A Novel and Effect Steel Surface Defect Classification Method Based on Coordinate Attention and Self-Interaction Mechanism

The surface defects of a hot-rolled strip will adversely affect the appearance and quality of industrial products. Therefore, the timely identification of hot-rolled strip surface defects is of great significance. In order to improve the efficiency and accuracy of surface defect detection, a lightweight network based on coordinate attention and self-interaction (CASI-Net), which integrates channel domain, spatial information, and a self-interaction module, is proposed to automatically identify six kinds of hot-rolled steel strip surface defects. In this paper, we use coordinate attention to embed location information into channel attention, which enables the CASI-Net to locate the region of defects more accurately, thus contributing to better recognition and classification. In addition, features are converted into aggregation features from the horizontal and vertical direction attention. Furthermore, a self-interaction module is proposed to interactively fuse the extracted feature information to improve the classification accuracy. The experimental results show that CASI-Net can achieve accurate defect classification with reduced parameters and computation.

Factors Affecting the Cathode Edge Nodulation in Copper Electrorefining Process

In this study the factors that are affecting the copper nodular growth on the cathode edge were investigated from metallurgical and operation point of view. Statistical analysis was performed to evaluate the effect of operational conditions on the nodular copper growth by characterization of the nodule-containing cathodes. Besides, the effects of defects on polymer edge strips as well as changes in weight and thickness of anodes on the formation of nodules were investigated. Electrochemical galvanostatic experiments were employed to study the effect of electrolyte additives and the distance between the anode and cathode on cathode surface quality. A relatively large porosities of about 50 µm were observed in the microstructure of the cathode edge nodules. In addition, few nodule samples that were taken was observed to have a higher concentration of Fe, Cd and Pb, up to 25 ppm. Low probability (1%) in the repeatability of the nodule formation over the same position on the edge strip was approved the insignificant effect of possible edge strip defects on nodulation. The large weight variation of anodes can cause the anode thickness variation by 10 mm and consequently alter the distance between the anode and the cathode. This was shown to cause formation of nodules at the cathode edge. The peaks that were observed in the cathodic potential curves in galvanostatic tests, were believed to be the sign of nodulation and therefore was investigated further using the optical microscopic images.

A lightweight detector based on attention mechanism for aluminum strip surface defect detection

Many problems associated with the visual inspection of surface defects on aluminum strips remain to be solved, including the inapplicability of large-scale algorithm and computing equipment on site, and the balance between detection speed and accuracy. This paper proposes a novel and lightweight detection method based on attention mechanism, and focuses on the industrial application of aluminum strip defect inspection. On the basis of the YOLOv4 framework, the backbone network YOLO-DCSAM is constructed to utilize depthwise separable convolution and to design a parallel dual-channel attention module. It compresses the network scale and better enhances the effect of different channels on the feature map. At the same time, the neck network is redesigned and lightweighted for feature fusion, which can increase the receptive field and further simplify the network through SPPM-PANet module. Moreover, by optimization measure, such as the anchor box size of the cluster and improved loss function, the pertinence of model is strengthened to defect objects. The proposed method is trained and tested on the straightening aluminum strip surface data collected from the cold rolling workshop of Liuzhou Yinhai Aluminum Co., Ltd. Experiments show that the proposed method achieves a mAP of 96.28%, thereby outperforming the original YOLOv4 model. Moreover, as compared with YOLOv4, the model volume is reduced by 83.38% and the detection speed is increased by 3 times, thereby exhibiting the potential for real-time detection on the embedded systems.

Copper Strip Surface Defect Detection Model Based on Deep Convolutional Neural Network

Surface defect automatic detection has great significance for copper strip production. The traditional machine vision for surface defect automatic detection of copper strip needs artificial feature design, which has a long cycle, and poor ability of versatility and robustness. However, deep learning can effectively solve these problems. Therefore, based on the deep convolution neural network and the transfer learning strategy, an intelligent recognition model of surface defects of copper strip is established in this paper. Firstly, the defects were classified in accordance with the mechanism and morphology, and the surface defect dataset of copper strip was established by comprehensively adopting image acquisition and image augmentation. Then, a two-class discrimination model was established to achieve the accurate discrimination of perfect and defect images. On this basis, four CNN models were adopted for the recognition of defect images. Among these models, the EfficientNet model through transfer learning strategy had the best comprehensive performance with a recognition accuracy rate of 93.05%. Finally, the interpretability and deficiency of the model were analysed by the class activation map and confusion matrix, which point toward the direction of further optimization for future research.

A ResNet50-Based Method for Classifying Surface Defects in Hot-Rolled Strip Steel

Hot-rolled strip steel is widely used in automotive manufacturing, chemical and home appliance industries, and its surface quality has a great impact on the quality of the final product. In the manufacturing process of strip steel, due to the rolling process and many other reasons, the surface of hot rolled strip steel will inevitably produce slag, scratches and other surface defects. These defects not only affect the quality of the product, but may even lead to broken strips in the subsequent process, seriously affecting the continuation of production. Therefore, it is important to study the surface defects of strip steel and identify the types of defects in strip steel. In this paper, a scheme based on ResNet50 with the addition of FcaNet and Convolutional Block Attention Module (CBAM) is proposed for strip defect classification and validated on the X-SDD strip defect dataset. Our solution achieves a classification accuracy of 94.11%, higher than more than a dozen other compared deep learning models. Moreover, to adress the problem of low accuracy of the algorithm in classifying individual defects, we use ensemble learning to optimize. By integrating the original solution with VGG16 and SqueezeNet, the recognition rate of oxide scale of plate system defects improved by 21.05 percentage points, and the overall defect classification accuracy improved to 94.85%.

Suberin plasticity to developmental and exogenous cues is regulated by a set of MYB transcription factors

Suberin is a hydrophobic biopolymer that can be deposited at the periphery of cells, forming protective barriers against biotic and abiotic stress. In roots, suberin forms lamellae at the periphery of endodermal cells where it plays crucial roles in the control of water and mineral transport. Suberin formation is highly regulated by developmental and environmental cues. However, the mechanisms controlling its spatiotemporal regulation are poorly understood. Here, we show that endodermal suberin is regulated independently by developmental and exogenous signals to fine-tune suberin deposition in roots. We found a set of four MYB transcription factors (MYB41, MYB53, MYB92, and MYB93), each of which is individually regulated by these two signals and is sufficient to promote endodermal suberin. Mutation of these four transcription factors simultaneously through genome editing leads to a dramatic reduction in suberin formation in response to both developmental and environmental signals. Most suberin mutants analyzed at physiological levels are also affected in another endodermal barrier made of lignin (Casparian strips) through a compensatory mechanism. Through the functional analysis of these four MYBs, we generated plants allowing unbiased investigation of endodermal suberin function, without accounting for confounding effects due to Casparian strip defects, and were able to unravel specific roles of suberin in nutrient homeostasis.