Defects In Steel Research Articles

A steel defect detection method based on edge feature extraction via the Sobel operator.

Scratches and cracks in steel severely affect its service life and performance. However, owing to the irregular shapes and sizes of steel surface defects, defects within the same class may be different, whereas defects between classes may be similar. Existing methods focus only on spatial information, resulting in low detection accuracy. To alleviate these problems, this paper proposes the ECDY (EIFEM CARAFE DyHead) network to enhance the detection capability of steel defects. We first design a feature extraction module that focuses on the edge information of feature contours. This module uses the Sobel operator to extract the edge information of a feature and fuses it with the overall spatial information so that richer semantic information can be obtained. The module has improved accuracy in the YOLOv5, YOLOv8, and YOLOv10 versions, and uses fewer parameters and calculations. In particular, in YOLOv8x, mAP@0.5 increased by 2.5%, and the number of parameters was reduced by 12.4M. Second, to retain the detailed information in the feature pyramid, and to better reconstruct features, we choose the content-aware reassembly feature method (CARAFE) as the upsampling method. Finally, the detection head was replaced with a dynamic unified detection head (DyHead) to adapt to different defect sizes and different task requirements. Compared with YOLOv8s, the proposed method improves precision by 1.6%, recall by 4%, and mAP@0.5 by 4%. This value is 4.2% higher than the mAP@0.5 of the current SOTA model RT-DETR-L in the field of object detection and has 23.2M fewer parameters.

XAIP: An eXplainable AI‐Based Pipeline for Identifying Key Factors of Surface Defects in Strip Steel

The surface defect has a direct impact on the performance and quality of the final product, so it is crucial to identify the key factors causing the defect. To achieve accurate key factor identification, an eXplainable AI‐based Pipeline (XAIP) is proposed herein. The proposed XAIP combines data mode clustering and local model construction to meet practical application requirements. Meanwhile, after analyzing the characteristics of practical data, a strategy for defect rate calculation is designed to provide more fine‐grained defect‐related information to supervise model training. The final identification results are presented by a two‐stage explainable method, which is designed to reveal the information of data modes and key variables and can give engineers more specific defect‐related information. The experiment results based on two practical manufacturing datasets show the effectiveness of the proposed method.

A study on initial formation stage of proton irradiation defects in reactor pressure vessel steel

A study on initial formation stage of proton irradiation defects in reactor pressure vessel steel

Variations of the residual magnetic fields of X70 pipeline steels with double defects

The aim of this research is to correlate residual magnetic fields (RMFs) with double defects in ferromagnetic steels. Specimens of X70 pipeline steels were machined into smooth plates with two types of defect (single and double defects) for comparison. Tensile tests were carried out to detect the RMF signals on the surface of the defective specimens. The variation of the tangential component of the RMF signals was presented and magnetic parameters were defined to investigate the abnormal magnetic changes of the two types of defect. It was found that the peak value of the tangential component was not influenced by defect types and the valley value was capable of evaluating the interaction effect between defects. Correlation between the RMF signals and the location of double defects was also investigated. This research will promote the investigation of defect clusters in ferromagnetic steels based on the metal magnetic memory (MMM) technique.

Maximizing Steel Slice Defect Detection: Integrating ResNet101 Deep Features with SVM via Bayesian Optimization

Accurate detection of defects on steel surfaces is crucial for maintaining quality standards in steel production. This paper addresses the challenge of classifying steel sheets into distinct defect categories by presenting a robust method that leverages deep learning and advanced optimization techniques. We propose a novel approach that utilizes the ResNet101 model to extract deep features, which are then classified using a support vector machine (SVM). To enhance the SVM's performance, Bayesian optimization is employed for hyperparameter tuning. Our method is validated using the "Severstal: Steel Defect Detection" dataset from Kaggle, achieving a validation accuracy of 89.1% and a test accuracy of 90.6%, with a classification error of 0.10934. Additionally, the area under the curve (AUC) for each class exceeds 0.95 in both the validation and test sets, demonstrating excellent discriminatory power. Further evaluation on the DAGM dataset achieved flawless results, with an accuracy of 100%, AUC of 1, sensitivity of 100%, specificity of 100%, precision of 100%, MCC of 100%, F1 score of 1, and kappa of 100%. On the NEU dataset, our method achieved an accuracy of 97.92%, sensitivity of 97.92%, specificity of 99.58%, precision of 98.06%, F1 score of 0.9791, MCC of 97.55%, and kappa of 92.50%. These results demonstrate the robustness and adaptability of the proposed method, offering an efficient and reliable solution for automating steel defect detection and surface defect classification in industrial applications.

YOLO-LFPD: A Lightweight Method for Strip Surface Defect Detection.

Strip steel surface defect recognition research has important research significance in industrial production. Aiming at the problems of defect feature extraction, slow detection speed, and insufficient datasets, YOLOv5 is improved on the basis of YOLOv5, and the YOLO-LFPD (lightweight fine particle detection) model is proposed. By introducing the RepVGG (Re-param VGG) module, the robustness of the model is enhanced, and the expressive ability of the model is improved. FasterNet is used to replace the backbone network, which ensures accuracy and accelerates the inference speed, making the model more suitable for real-time monitoring. The use of pruning, a GA genetic algorithm with OTA loss function, further reduces the model size while better learning the strip steel defect feature information, thus improving the generalisation ability and accuracy of the model. The experimental results show that the introduction of the RepVGG module and the use of FasterNet can well improve the model performance, with a reduction of 48% in the number of parameters, a reduction of 13% in the number of GFLOPs, an inference time of 77% of the original, and an optimal accuracy compared with the network models in recent years. The experimental results on the NEU-DET dataset show that the accuracy of YOLO-LFPD is improved by 3% to 81.2%, which is better than other models, and provides new ideas and references for the lightweight strip steel surface defect detection scenarios and application deployment.

Preparation and properties of ZTA/alloyed high manganese steel composites

In the long-term use of high manganese steels, it is not desirable to achieve wear resistance by austenite deformation strengthening alone. The wear resistance of high manganese steel is much lower than that of ordinary wear-resistant steel under medium and low stress conditions. Improving the instability of wear resistance caused by defects in high manganese steels is an important problem to be solved in current industrial production. In this study, a new type of high manganese alloy with high hardness and high wear resistance was prepared by multi-alloying with Cr-W-Mo elements on the basis of 20Mn1.2C. ZTA ceramic particles reinforced high manganese steel composites were prepared by selecting high manganese steel materials with excellent mechanical properties as the metal matrix of ceramic reinforced metal matrix composites. The Cr-W-Mo multi-alloyed high manganese alloys are mainly composed of a mixed austenite and ferrite matrix, M3C-type cementite and M6C-type carbides. The Cr2W6Mo6 sample has the best overall mechanical properties. Its hardness reached 49.8 HRC, which is 1.20 times higher than that of the Cr2 sample. The mass loss was 0.2571 g, which is 79.92% of the Cr16 sample (0.3217 g). The ZTA ceramic particles were well composited with the alloyed high manganese steel matrix, and the thickness of the interfacial layer was 20-30 μm, with the formation of Mn2AlO4 and (Fe, Mn)2SiO4, and (Al, Cr)2O3 in the interfacial layer. The best abrasion resistance was obtained at a ZTA content of 40 vol.%. The mass loss was 0.1669 g, which is 51.88% of the Cr16 material (0.3217 g).

A Surface Defect Detection Method for Cold-rolled Strip Steel Based on Improved YOLOv8

Cold-rolled strip steel has excellent mechanical properties, and it is widely used in the fields such as automotive manufacturing, construction industry, aircraft manufacturing and electronic product manufacturing. However, many different processing defects occur in the manufacturing process of cold-rolled strip steel, and this article proposes a visual detection method based on YOLOv8 to identify the surface defects on cold-rolled strip steel more accurately. Firstly, several common types of defects in cold-rolled strip steel were analyzed. Then, in order to enrich the dataset for subsequent detection, wavelet transform was used for filtering, denoising, and canny edge detection in the image processing stage for obtaining the clearer input model image with the more prominent graphics. Lastly, the CA attention mechanism was added into the YOLOv8 which is useful to improve the features recognition ability of the model, at the same time, the original standard convolution was replaced by DCS convolution and the loss function was optimized which is useful to get the lightweight models. The improved YOLOv8 model was validated on the NEU-DET dataset, the overall detection performance of the model such as the recall, the accuracy, and the average precision has significantly improved.

TAFENet: A Two-Stage Attention-Based Feature-Enhancement Network for Strip Steel Surface Defect Detection

Strip steel serves as a crucial raw material in numerous industries, including aircraft and automobile manufacturing. Surface defects in strip steel can degrade the performance, quality, and appearance of industrial steel products. Detecting surface defects in steel strip products is challenging due to the low contrast between defects and background, small defect targets, as well as significant variations in defect sizes. To address these challenges, a two-stage attention-based feature-enhancement network (TAFENet) is proposed, wherein the first-stage feature-enhancement procedure utilizes an attentional convolutional fusion module with convolution to combine all four-level features and then strengthens the features of different levels via a residual spatial-channel attention connection module (RSC). The second-stage feature-enhancement procedure combines three-level features using an attentional self-attention fusion module and then strengthens the features using a RSC attention module. Experiments on the NEU-DET and GC10-DET datasets demonstrated that the proposed method significantly improved detection accuracy, thereby confirming the effectiveness and generalization capability of the proposed method.

An efficient detector for detecting surface defects on cold-rolled steel strips

Surface-defect inspection is vital in cold-rolled steel-strip manufacturing, given the complexities of production environments and the high speeds involved. Further, the defects on cold-rolled steel strips are often characterized by their small size, diversity of types, and similarities among different types, posing significant challenges in balancing detection accuracy and efficiency. To address the challenges, we designed a detector based on You Only Look Once version 5 (YOLOv5) to achieve precise detection of surface defects on cold-rolled steel strips. First, a dataset containing seven types of defects was curated, named the Cold-Rolled Steel Defect Dataset (CR7-DET). Next, a feature-extraction network based on residual-like connections within a single residual block (Res2net) was developed to enhance the model’s feature-extraction capability, alongside introducing a multi-head attention module to focus on key information features. To reduce the information loss during feature fusion, we established an adaptive feature-fusion Path Aggregation Network (aff-PAN), which was optimized by designing a lightweight adaptive down-sampling module (LAD) to increase the sensory-field implementation of feature fusion. The ghost convolution effectively reduced the number of parameters and increased the speed without affecting the model’s performance. Finally, experiments were conducted on our CR7-DET and a public dataset (GC10-DET). With a reduced parameter count of 6.85 million, our model achieved a mean average precision(mAP) of 87.6% on CR7-DET and 79.7% on GC10-DET. The experimental results demonstrated that our model achieved a balance between detection accuracy and inference efficiency. The model has the potential to reduce scrap rates caused by defects and improve the overall surface quality of cold-rolled steel strips.

Research on the Detection of Steel Plate Defects Based on SimAM and Twin-NMF Transfer

Pulsed eddy current thermography can detect surface or subsurface defects in steel, but in the process of combining deep learning, it is expensive and inefficient to build a complete sample of defects due to the complexity of the actual industrial environment. Consequently, this study proposes a transfer learning method based on Twin-NMF and combines it with the SimAM attention mechanism to enhance the detection accuracy of the target domain task. First, to address the domain differences between the target domain task and the source domain samples, this study introduces a Twin-NMF transfer method. This approach reconstructs the feature space of both the source and target domains using twin non-negative matrix factorization and employs cosine similarity to measure the correlation between the features of these two domains. Secondly, this study integrates a parameter-free SimAM into the neck of the YOLOv8 model to enhance its capabilities in extracting and classifying steel surface defects, as well as to alleviate the precision collapse phenomenon associated with multi-scale defect recognition. The experimental results show that the proposed Twin-NMF model with SimAM improves the detection accuracy of steel surface defects. Taking NEU-DET and GC10-DET as source domains, respectively, in the ECTI dataset, mAP@0.5 reaches 99.3% and 99.2%, and the detection accuracy reaches 98% and 98.5%.

Multiclass small target detection algorithm for surface defects of chemicals special steel

Multiclass small target detection algorithm for surface defects of chemicals special steel

Research on steel surface defect detection system based on YOLOv5s-SE-CA model and BEMD image enhancement

ABSTRACT The nondestructive testing capability of steel surface defects has a significant impact on quality of industrial production. However, the single-stage detection network YOLOv5s model for steel surface defect detection is of insufficient feature extraction ability and susceptibility to noise interference in extracting surface defect images. Accordingly, a steel surface defect detection system based on YOLOv5s-SE-CA model and bi-dimensional empirical mode decomposition (BEMD) image enhancement is proposed. Firstly, the BEMD is used for image threshold denoising to improve the quality of surface defect images and achieve preprocessing of the dataset. Secondly, the squeeze and excitation network (SENet) attention mechanism is introduced into the backbone network of YOLOv5s model to adaptively adjust weights of each feature channel. Meanwhile, the coordinate attention (CA) attention mechanism is integrated to improve network model’s ability to focus on surface defects. Therefore, the YOLOv5s-SE-CA model is designed to enhance detection capability of steel surface defects. Experimental verification was carried out using the NEU-DET noisy dataset with specific evaluation indicators of image enhancement detection system. Results showed the proposed system has superior performance when compared to traditional models trained on noisy and denoising datasets and achieved more accurate detection of surface defects in steel.

An efficient steel defect detection model based on multi-scale information extraction

PurposeIn the field of steel defect detection, the existing detection algorithms struggle to achieve a satisfactory balance between detection accuracy, computational cost and inference speed due to the interference from complex background information, the variety of defect types and significant variations in defect morphology. To solve this problem, this paper aims to propose an efficient detector based on multi-scale information extraction (MSI-YOLO), which uses YOLOv8s as the baseline model.Design/methodology/approachFirst, the authors introduce an efficient multi-scale convolution with different-sized convolution kernels, which enables the feature extraction network to accommodate significant variations in defect morphology. Furthermore, the authors introduce the channel prior convolutional attention mechanism, which allows the network to focus on defect areas and ignore complex background interference. Considering the lightweight design and accuracy improvement, the authors introduce a more lightweight feature fusion network (Slim-neck) to improve the fusion effect of feature maps.FindingsMSI-YOLO achieves 79.9% mean average precision on the public data set Northeastern University (NEU)-DET, with a model size of only 19.0 MB and an frames per second of 62.5. Compared with other state-of-the-art detectors, MSI-YOLO greatly improves the recognition accuracy and has significant advantages in computational cost and inference speed. Additionally, the strong generalization ability of MSI-YOLO is verified on the collected industrial site steel data set.Originality/valueThis paper proposes an efficient steel defect detector with high accuracy, low computational cost, excellent detection speed and strong generalization ability, which is more valuable for practical applications in resource-limited industrial production.

Investigation on the characteristics of porosity, melt pool in 316L stainless steel manufactured by laser powder bed fusion

Pores are among the primary defects in 316L stainless steel when fabricated through laser powder bed fusion (L-PBF). To better understand and precisely control the formation behavior of pores in the L-PBF-manufactured 316L stainless steel, effects of L-PBF process parameters on the melt pool and pore characteristics have been investigated. A method utilized for extreme values statistics analysis was also applied to investigate and predict the sizes of pores. Relationships among the count of measurements, the laser energy density, the reduced variate, and the maximum pore size were revealed. The findings showed an overall increase in melt pool depth as the laser energy densities was raised, yet the magnitude of this growth weakened as the laser energy density continued to increase. Conversely, it was discovered that the connection between the width of the melt pool and the density of laser energy exhibited a markedly less distinct correlation. As laser energy density escalated, there was a shift in the melt pool mode from conduction-based to a transitional phase, and upon further elevation of the laser energy density, it transitioned to keyhole mode. To obtain a reliable statistical analysis of pores, at least 40 measurements should be acquired for the estimation of the pore sizes by taking comprehensive consideration of time cost. Beside, in all three melt pool modes, at a fixed observation area, the maximum size of pores generally decreased with the escalation in laser energy densities.

Segmenting hydrogen‐induced cracking defects in steel through scanning acoustic microscopy and deep neural networks

AbstractHydrogen‐induced cracking (HIC) presents a significant concern in industries, such as oil and gas, petrochemicals, and aerospace, where high‐strength steel is prevalently used. This phenomenon compromises the structural integrity of steel pipelines and equipment. Accurate detection and monitoring of HIC are crucial for the safety and reliability of these assets. While traditional defect detection methods are usually costly and easily affected by human physiological state, deep learning approaches offer both time and financial benefits along with high accuracy. This study focuses on employing deep learning to segment HIC in steel, utilizing the robust and state‐of‐the‐art YOLOv8‐seg architecture for defect identification and segmentation. The process involves acquiring two‐dimensional B‐scan images through a scanning acoustic microscopy (SAM) system, followed by employing the YOLOv8‐seg architecture to address the segmentation task within these images. The experimental results demonstrate the effectiveness of the YOLOv8‐seg model, achieving a mean average precision (mAP) score greater than ˜0.95. Notably, this research pioneers the development of a framework for reconstructing HIC within steel based on B‐scan image segmentation results, offering researchers and professionals a comprehensive understanding of internal defects in steel blocks. This work underscores the potential of YOLOv8‐seg architecture for accurate detection and segmentation of HIC in steel, providing a valuable tool for inspection and maintenance activities.

TSEDNet:Task-specific encoder–decoder network for surface defects of strip steel

Deep learning faces challenges in the surface defect segmentation of strip steel. Firstly, insufficient processing of feature maps leads to the loss of task-specific feature information. Secondly, the segmentation of defects with long-tail distributions is not accurate enough. To address these issues, a pixel-level deep segmentation method called task-specific encoder–decoder network (TSEDNet) is proposed to construct an end-to-end defect segmentation model. TSEDNet includes the encoder-multi-decoder structure based on domain knowledge settings tailored to specific tasks, which can achieve effective feature representation and significantly reduce the impact of imbalanced defect quantities. Additionally, a novel metric learning method is introduced to optimize decoder selection. Furthermore, the feature fusion module based on metric learning is proposed to utilize general features for restoring task-specific details, thereby enhancing pixel-level segmentation accuracy. Through experiments and industrial validation, the defect segmentation network demonstrates superior performance compared to other advanced segmentation methods and proves its applicability in practical scenarios.

Unsupervised method for detecting surface defects in steel based on joint optimization of pseudo-labeling and clustering

Abstract Advances in the field of measurement science and technology have improved the detection of defects in industrial production. One of the key challenges in steel plate surface defect detection is the need to quickly detect a small number of defects in an overwhelmingly defect-free sample. Unlike supervised learning, which relies heavily on precise sample labeling, unsupervised learning leverages its inherent learning capabilities for detection. This paper introduces an innovative method for smart steel diagnosis, integrating joint optimization of feature extraction and clustering. The proposed approach merges mini-batch K-Means clustering with a feature extraction network to acquire pseudo-label information for current images. It employs a multi-view transformation strategy, enabling classification through the optimized feedback from pseudo-labels. This method allows the network to self-optimize the distinction of image features through backpropagation. The method exhibits a mere 4% classification failure rate for steel surface images. This significant reduction in additional data processing requirements enhances the inspection system's efficiency and accuracy. Furthermore, the versatility of this method extends beyond steel defect diagnosis. It holds potential for application in various engineering domains, particularly in scenarios characterized by data imbalance.

Research on strip surface defect detection based on improved YOLOv5 algorithm

In the production process of hot rolled strip, there will inevitably be defects such as iron scale, slag inclusion and scratch on the surface, and there is no effective identification method for these defects. Therefore, based on the improved YOLOv5s algorithm, this article proposes an improved YOLOv5s-GCB model by introducing the coordinate attention module, improving the feature fusion structure and lightening the feature extraction backbone network. The experiment shows that the precision of YOLOv5s-GCB is 89.7%, recall is 90.2% and mAP@0.5 is 93.1%, which are 2.1%, 3.0% and 1.6% higher than YOLOv5s, respectively. The average detection time of a single image is 7.9 ms, and the detection speed is improved. Finally, the ablation experiment shows that the proposed improved strategy is feasible, and the detection effect of YOLOv5s-GCB is further verified by the comparison experiment with other target detection models. Therefore, it can be concluded that the proposed method provides an important reference for the detection of indicated defects in strip steel.

Lightweight-detection: The strip steel surface defect identification based on improved YOLOv5d

The surface defect of strip steel seriously affects the product quality, the current identification methods have the inherent defects of low detection efficiency and poor detection accuracy, and it is important an improved an algorithm based on the modified YOLOv5 framework to enhance the defect detection effectiveness and accuracy. To create a more lightweight network model, the C3 module and part of the convolutional structure in the original YOLOv5 network were replaced with the GhostBottleneck structure. Additionally, the Coordinate Attention (CA) mechanism was incorporated into the Backbone section to compensate for the original model's lack of attention mechanisms. To address the angular mismatch between the actual frame and the predicted bounding box, a limitation overlooked by the CIOU loss function was further refined. Experimental results demonstrate that the enhanced YOLOv5s-CSG model outperformed the original YOLOv5s by 7.3 %, achieving a significant 37.9 % reduction in model size and an mAP value of 77.5 %. Furthermore, the detection precision and speed were notably higher compared to several widely-used algorithms. The proposed YOLOv5s-CSG model is well-suited for deployment on mobile devices and shows great potential for rapidly and accurately detecting both the type and location of strip surface defects, surpassing the performance of existing methods.