Search Results (52)

In recent years, deep learning-based methods for surface defect detection in steel strips have advanced rapidly. Nevertheless, existing approaches still face several challenges in practical applications, such as insufficient dimensionality of feature information, inadequate representation capability for single-modal samples, poor adaptability to few-shot scenarios, and difficulties in cross-domain knowledge transfer. To overcome these limitations, this paper proposes a multi-modal fusion framework based on graph neural networks for few-shot classification and detection of surface defects. The proposed architecture consists of three core components: a multi-modal feature fusion module, a graph neural network module, and a cross-modal transfer learning module. By integrating heterogeneous data modalities—including visual images and textual descriptions—the method facilitates the construction of a more efficient and accurate defect classification and detection model. Experimental evaluations on steel strip surface defect datasets confirm the robustness and effectiveness of the proposed method under small-sample conditions. The results demonstrate that our approach provides a novel and reliable solution for automated quality inspection of surface defects in the steel industry. Full article

Surface defects in hot-rolled steel strip alter the material’s properties and degrade its overall quality. Especially in real production environments, due to time sensitivity, lightweight Convolutional Neural Network models are suitable for inspecting these defects. However, in real-time applications, the acquired images are subjected to various degradations, including noise, motion blur, and non-uniform illumination. The performance of lightweight CNN models on degraded images is crucial, as improved performance on such images reduces the reliance on preprocessing techniques for image enhancement. Thus, this study focuses on analyzing pre-trained lightweight CNN models for surface defect classification in hot-rolled steel strips under degradation conditions. Six state-of-the-art lightweight CNN architectures—MobileNet-V1, MobileNet-V2, MobileNet-V3, NasNetMobile, ShuffleNet V2 and EfficientNet-B0—are evaluated. Performance is assessed using standard classification metrics. The results indicate that MobileNet-V1 is the most effective model among those used in this study. Additionally, a new performance metric is proposed in this study. Using this metric, the misclassification distribution is evaluated for concentration versus homogeneity, thereby facilitating the identification of areas for model improvement. The proposed metric demonstrates that the MobileNet-V1 exhibits good performance under both low and high degradation conditions in terms of misclassification robustness. Full article

In the steel manufacturing process, defect classification is a critical step to ensure product performance and safety. However, due to the complexity of defect types and their multi-scale distribution characteristics, surface defect classification for steel plates remains a significant challenge. To address this issue, this paper proposes a deep learning model based on the ConvNeXt architecture, FAX-Net, which is designed to further improve the accuracy of steel surface defect classification. The FAX-Net architecture incorporates a Symmetric Dual-dimensional Attention Module (SDAM), which employs structurally symmetric and parallel modeling paths to effectively enhance the model’s responsiveness to critical defect regions. In addition, a Transformer-Fused Feature Pyramid Network (TF-FPN) is designed by integrating a lightweight Transformer to improve information interaction and integration across features of different scales, thereby enhancing the model’s discriminative capability in multi-scale scenarios. Experimental results demonstrate that the proposed FAX-Net model offers significant advantages in steel surface defect classification tasks. On the NEU-CLS dataset, FAX-Net achieves a classification accuracy of 97.78%, outperforming existing mainstream methods. These findings validate that FAX-Net possesses superior classification capabilities and is well-suited to handle a wide variety of defect types and scales effectively. Full article

One of the important parameters of the sheet metal forming process is the coefficient of friction (CoF). Therefore, monitoring the friction coefficient value is essential to ensure product quality, increase productivity, reduce environmental impact, and avoid product defects. Conventional CoF monitoring techniques pose a number of problems, including the difficulty in identifying the features of force signals that are sensitive to the variation in the coefficient of friction. To overcome these difficulties, this paper proposes a new approach to apply unsupervised artificial intelligence techniques with unbalanced data to classify the CoF of DP780 (HCT780X acc. to EN 10346:2015 standard) steel sheets in strip-drawing tests. During sheet metal forming (SMF), the CoF changes owing to the evolution of the contact conditions at the tool–sheet metal interface. The surface topography, the contact loads, and the material behaviour affect the phenomena in the contact zone. Therefore, classification is required to identify possible disturbances in the friction process causing the change in the CoF, based on the analysis of the friction process parameters and the change in the sheet metal’s surface roughness. The Kohonen self-organising map (SOM) was created based on the surface topography parameters collected and used for CoF classification. The CoF determinations were performed in the strip-drawing test under different lubrication conditions, contact pressures, and sliding speeds. The results showed that it is possible to classify the CoF using an SOM for unbalanced data, using only the surface roughness parameter Sq and selected friction test parameters, with a classification accuracy of up to 98%. Full article

Eddy current testing (ECT) has become a widely adopted technique for non-destructive testing (NDT) due to its effectiveness in detecting surface and near-surface defects in conductive materials. However, traditional methods mainly focus on defect detection and face significant challenges in extracting geometric information such as defect size and shape, which is crucial for structural health monitoring (SHM) and remaining useful life (RUL) assessment. To address these challenges, this study proposes a defect reconstruction approach based on a complex-valued convolutional neural network (CV-CNN), which directly leverages both amplitude and phase information inherent in complex-valued impedance signals. The proposed framework employs convolution, pooling, and activation operations specifically designed within the complex-valued domain to facilitate the high-fidelity reconstruction of defect morphology as well as precise multi-class defect classification. Notably, this approach processes the complete complex-valued signal without relying on prior structural parameters or baseline data, thereby achieving substantial improvements in both defect visualization and classification performance. Moreover, when compared to a complex-valued fully convolutional neural network (CV-FCNN), CV-CNN demonstrates a superior average classification accuracy of 85%, significantly outperforming the CV-FCNN model. Experimental results on carbon steel specimens with standard electrical discharge machining (EDM) notches under multi-frequency excitation confirm these advantages. This contribution provides a promising solution in the field of NDT for intelligent and precise defect detection. Full article

Defect detection is still challenging to apply in reality because the goal of the entire classification assignment is to identify the exact type and location of every problem in an image. Since defect detection is a task that includes location and categorization, it is difficult to take both accuracy factors into account when designing related solutions. Flaw detection deployment requires a unique detection dataset that is accurately annotated. Producing steel free of flaws is crucial, particularly in large production systems. Thus, in this study, we proposed a novel deep learning-based flaw detection system with an industrial focus on automated steel surface defect identification. To create processed images from raw steel surface images, a novel method was applied. A new deep learning model called the Parallel Attention–Residual CNN (PARC) model was constructed to extract deep features concurrently by training residual structures and attention. The Iterative Neighborhood Component Analysis (INCA) technique was chosen for distinguishing features to lower the computational cost. The classification assessed the SVM method using a convincing dataset (Severstal: Steel Defect Detection). The accuracy in both the binary and multi-class classification tests was above 90%. Moreover, using the same dataset, the suggested model was contrasted with pre-existing models. Full article

This paper presents the development and analysis of a bridge bearing database consistent with the 2020 Italian Guidelines (LG2020), currently enforced by the Italian law for risk classification and management of existing bridges. The database was developed by putting together the contribution of 24 research teams from 18 Italian universities in the framework of a research project foreseen by the agreement between the High Council of Public Works (CSLP, part of the Italian Ministry of Transportation) and the research consortium ReLUIS (Network of Italian Earthquake and Structural Engineering University Laboratories). This research project aimed to apply LG2020 to a set of about 600 bridges distributed across the Italian country, in order to find possible issues and propose modifications and integrations. The database includes almost 12,000 bearing defect forms related to a portfolio of 255 existing bridges located across the entire country. This paper reports a preliminary analysis of the dataset to provide an overview of the bearings installed in a significant bridge portfolio, referring to major highways and state roads. After a brief state of the art about the main bearing types installed on the bridges, along with inspection procedures, the paper describes the database structure, showing preliminary analyses related to bearing types and defects. The results show the prevalence of elastomeric pads, representing more than 55% of the inspected bearings. The remaining bearings are pot, low-friction with steel–Teflon surfaces and older-type steel devices. Lastly, the study provides information about typical defects for each type of bearing, while also underscoring some issues related to the current version of the LG2020 bearing inspection form. Full article

Surface defect detection is essential for ensuring the quality and safety of steel products. While Transformer-based methods have achieved state-of-the-art performance, they face several limitations, including high computational costs due to the quadratic complexity of the attention mechanism, inadequate detection accuracy for small-scale defects due to substantial downsampling, inconsistencies between classification scores and localization confidence, and feature resolution loss caused by simple upsampling and downsampling strategies. To address these challenges, we propose the HCT-Det model, which incorporates a window-based self-attention residual (WSA-R) block structure. This structure combines window-based self-attention (WSA) blocks to reduce computational overhead and parallel residual convolutional (Res) blocks to enhance local feature continuity. The model’s backbone generates three cross-scale features as encoder inputs, which undergo Intra-Scale Feature Interaction (ISFI) and Cross-Scale Feature Interaction (CSFI) to improve detection accuracy for targets of various sizes. A Soft IoU-Aware mechanism ensures alignment between classification scores and intersection-over-union (IoU) metrics during training. Additionally, Hybrid Downsampling (HDownsample) and Hybrid Upsampling (HUpsample) modules minimize feature degradation. Our experiments demonstrate that HCT-Det achieved a mean average precision (mAP@0.5) of 0.795 on the NEU-DET dataset and 0.733 on the GC10-DET dataset, outperforming other state-of-the-art approaches. These results highlight the model’s effectiveness in improving computational efficiency and detection accuracy for steel surface defect detection. Full article

In the process of steel strip production, the accuracy of defect detection remains a challenge due to the diversity of defect types, complex backgrounds, and noise interference. To improve the effectiveness of surface defect detection in steel strips, we propose an enhanced detection model known as YOLOv8-BSPB. First, we propose a novel pooling layer module, SCRD, which replaces max pooling with average pooling. This module introduces the receptive field block (RFB) and deformable convolutional network version 4 (DCNv4) to obtain learnable offsets, allowing convolutional kernels to flexibly move and deform on the input feature map, thus, more effectively extracting multi-scale features. Second, we integrate a polarized self-attention (PSA) mechanism to improve the model’s feature representation and enhance its ability to focus on relevant information. Additionally, we incorporate the BAM attention mechanism after the C2f module to strengthen the model’s feature selection capabilities. A bidirectional feature pyramid network is introduced at the neck of the model to improve feature transmission efficiency. Finally, the WIoU loss function is employed to accelerate the model’s convergence speed and enhance regression accuracy. Experimental results on the NEU-DET dataset demonstrate that the improved model achieves a classification accuracy of 81.3%, an increase of 4.9% over the baseline, with a mean average precision of 86.9%. The model has a parameter count of 5.5 M and operates at 103.1 FPS. To validate the model’s effectiveness, we conducted tests on the Kaggle steel strip dataset and our custom dataset, where the average accuracy improved by 2.3% and 5.5%, respectively. The experimental results indicate that the model meets the requirements for real-time, lightweight, and portable deployment. Full article

The accurate and efficient classification of steel surface defects is critical for ensuring product quality and minimizing production costs. This paper proposes a novel method based on wavelet transform and texture descriptors for the robust and precise classification of steel surface defects. By leveraging the multiscale analysis capabilities of wavelet transforms, our method extracts both broad and fine-grained textural features. It involves decomposing images using multi-level wavelet transforms, extracting a series set of statistical and textural features from the resulting coefficients, and employing Recursive Feature Elimination (RFE) to select the most discriminative features. A comprehensive series of experiments was conducted on two datasets, NEU-CLS and X-SDD, to evaluate the proposed method. The results highlight the effectiveness of the method in accurately classifying steel surface defects, outperforming the state-of-the-art techniques. Our method achieved an accuracy of 99.67% for the NEU-CLS dataset and 98.24% for the X-SDD dataset. Furthermore, we demonstrate the robustness of our method in scenarios with limited data, maintaining high accuracy, making it well-suited for practical industrial applications where obtaining large datasets can be challenging. Full article

This study introduces Hybrid-DC, a hybrid deep-learning model integrating ResNet-50 and Vision Transformer (ViT) for high-accuracy steel surface defect classification. Hybrid-DC leverages ResNet-50 for efficient feature extraction at both low and high levels and utilizes ViT’s global context learning to enhance classification precision. A unique hybrid attention layer and an attention fusion mechanism enable Hybrid-DC to adapt to the complex, variable patterns typical of steel surface defects. Experimental evaluations demonstrate that Hybrid-DC achieves substantial accuracy improvements and significantly reduced loss compared to traditional models like MobileNetV2 and ResNet, with a validation accuracy reaching 0.9944. The results suggest that this model, characterized by rapid convergence and stable learning, can be applied for real-time quality control in steel manufacturing and other high-precision industries, enhancing automated defect detection efficiency. Full article

Defect detection on steel surfaces with complex textures is a critical and challenging task in the industry. The limited number of defect samples and the complexity of the annotation process pose significant challenges. Moreover, performing defect segmentation based on accurate identification further increases the task’s difficulty. To address this issue, we propose VQGNet, an unsupervised algorithm that can precisely recognize and segment defects simultaneously. A feature fusion method based on aggregated attention and a classification-aided module is proposed to segment defects by integrating different features in the original images and the anomaly maps, which direct the attention to the anomalous information instead of the irregular complex texture. The anomaly maps are generated more confidently using strategies for multi-scale feature fusion and neighbor feature aggregation. Moreover, an anomaly generation method suitable for grayscale images is introduced to facilitate the model’s learning on the anomalous samples. The refined anomaly maps and fused features are both input into the classification-aided module for the final classification and segmentation. VQGNet achieves state-of-the-art (SOTA) performance on the industrial steel dataset, with an I-AUROC of 99.6%, I-F1 of 98.8%, P-AUROC of 97.0%, and P-F1 of 80.3%. Additionally, ViT-Query demonstrates robust generalization capabilities in generating anomaly maps based on the Kolektor Surface-Defect Dataset 2. Full article

Strip steel plays a crucial role in modern industrial production, where enhancing the accuracy and real-time capabilities of surface defect classification is essential. However, acquiring and annotating defect samples for training deep learning models are challenging, further complicated by the presence of redundant information in these samples. These issues hinder the classification of strip steel surface defects. To address these challenges, this paper introduces a high real-time network, ODNet (Orthogonal Decomposition Network), designed for few-shot strip steel surface defect classification. ODNet utilizes ResNet as its backbone and incorporates orthogonal decomposition technology to reduce the feature redundancies. Furthermore, it integrates skip connection to preserve essential correlation information in the samples, preventing excessive elimination. The model optimizes the parameter efficiency by employing Euclidean distance as the classifier. The orthogonal decomposition not only helps reduce redundant image information but also ensures compatibility with the Euclidean distance requirement for orthogonal input. Extensive experiments conducted on the FSC-20 benchmark demonstrate that ODNet achieves superior real-time performance, accuracy, and generalization compared to alternative methods, effectively addressing the challenges of few-shot strip steel surface defect classification. Full article

In this study, the problem of a limited number of data samples, which affects the detection accuracy, arises for the image classification task of steel plate surface defects under conditions of small sample sizes. A data enhancement method based on generative adversarial networks is proposed. The method introduces a two-way attention mechanism, which is specifically designed to improve the model’s ability to identify weak defects and optimize the model structure of the network discriminator, which augments the model’s capacity to perceive the overall details of the image and effectively improves the intricacy and authenticity of the generated images. By enhancing the two original datasets, the experimental results show that the proposed method improves the average accuracy by 8.5% across the four convolutional classification models. The results demonstrate the superior detection accuracy of the proposed method, improving the classification of steel plate surface defects. Full article

In the competitive landscape of steel-strip production, ensuring the high quality of steel surfaces is paramount. Traditionally, human visual inspection has been the primary method for detecting defects, but it suffers from limitations such as reliability, cost, processing time, and accuracy. Visual inspection technologies, particularly automation techniques, have been introduced to address these shortcomings. This paper conducts a thorough survey examining vision-based methodologies related to detecting and classifying surface defects on steel products. These methodologies encompass statistical, spectral, texture segmentation based methods, and machine learning-driven approaches. Furthermore, various classification algorithms, categorized into supervised, semi-supervised, and unsupervised techniques, are discussed. Additionally, the paper outlines the future direction of research focus. Full article