Edge-aware interactive refinement network for strip steel surface defects detection

With the development of productivity, people set higher demands on the quality of steel. In recent years, artificial intelligence, especially deep learning-based computer vision technology has attracted great attention, which can be used for detecting steel surface defects such as scratches, patches, and rust spots. However, due to the complexity of the strip steel surface, it is still a challenge to accurately and effectively detect defect regions by the existing defects detection methods. Therefore, we propose a unique saliency model, i.e., deeper feature integration network to highlight the defect regions on the strip steel surface. To be specific, after each encoder stage, we introduce the multiscale global feature extraction module to elevate the multiscale deep features from the encoder. Meanwhile, we deploy the deeper feature extraction module, which contains a bidirectional feature extraction unit, to dig the effective representation for defects. Particularly, the forward one is equipped with a channel-space weighted module and the backward one is equipped with a split attention module. After that, the features from the two branches are progressively integrated by the decoder, yielding the final high-quality saliency maps that give a good depiction of the strip steel surface defects. Extensive experiments are executed on the public dataset, and the comparison results show that our model performs better than the 15 state-of-the-art methods, which proves the effectiveness and superiority of the proposed model.

In the context of resource constrained embedded terminals, the current deep learning-based technology for detecting surface defects in strip steel faces challenges with low detection accuracy and efficiency. This study introduces a lightweight convolution neural network (CNN) model for detecting surface defects of strip steel, which is based on deep learning. Through the integration of non-parameter attention mechanism SimAM, inverse residual structure, and depth-wise convolution module, a lightweight attention mobile backbone network is developed to achieve optimal feature extraction. To address the challenge of detecting small surface defects the context augmentation module is introduced to provide more information for small defects detection by using multi-scale features. To improve the efficiency of feature fusion and reduce parameter redundancy, the GVFPN neck network is proposed. The network aims to represent and deal with multi-scale features objectively while minimizing costs. The experimental results indicate that on the NEU-DET dataset, the proposed network attains an mAP of 78.8% and FPS at 97 frame/s. Moreover, the model requires only 2.39 M parameters and 3.1 G FLOPs. Compared to YOLOv5s, the proposed network reduces parameters by 65.9% and FLOPs by 80.7%, while achieving a 1.3% higher mAP and a 30 frame/s increase in detection speed. These results effectively demonstrate the effectiveness and superiority of the proposed method.

An efficient re-parameterization feature pyramid network on YOLOv8 to the detection of steel surface defect

Steel is widely used in the aerospace, machinery and automotive industries. Surface defects not only have a negative impact on the appearance of steel but also significantly reduce its wear resistance, high temperature resistance, corrosion resistance and fatigue strength. Therefore, the detection of steel surface defects is very important to improve the quality of steel production. The limited availability of surface defect samples in the industrial sector poses significant challenges for the accurate detection of defects in high-quality materials. In addition, the existing defect detection model is highly complex and not easy to deploy. To solve this problem, a lightweight defect detection network suitable for steel defects is proposed. The cross-layer feature fusion (CFF) in the design enables effective utilisation of multi-layer semantic features, facilitating the detection of small defects in steel. Secondly, a new loss function is designed to make up for the problems of small data volume and uneven data distribution. The experimental results demonstrate that the steel surface defect detection method proposed in this paper achieves the highest detection performance on widely used public datasets such as RSDDS, NEUS and NRSD-CR(test), while maintaining the lowest model complexity.

The performance of the salient object detection of strip surface defects has been promoted largely by deep learning based models. However, due to the complexity of strip surface defects, the existing models perform poorly in the challenging scenes such as noise disturbance, and low contrast between defect regions and background. Meanwhile, the detection results of existing models often suffer from coarse boundary details. Therefore, we propose a novel saliency model, namely an Edge-aware Multi-level Interactive Network, to detect the defects from the strip steel surface. Concretely, our model adopts the U-shape architecture where the two crucial points are the interactive feature integration and the edge-guided saliency fusion. Firstly, except the skip connection that combines the same stage of encoder and decoder, we deploy another connection, where the features from adjacent levels of encoder are transferred to the same stage of decoder. By this way, we are able to provide an effective fusion of multi-level deep features, yielding a well depiction for defects. Secondly, to give well-defined boundaries for prediction results, we add the edge extraction branch after each decoder block, where the progressive feature aggregation endows the edge with precise details and complete object cues. Meanwhile, together with the edge extraction branches, we deploy the saliency prediction branch at each decoder stage. After that, coupled with the fine edge information, we fuse all outputs of saliency prediction branches into the final saliency map, where the edge cue steers the saliency result to pay more attention to the boundary details. Following this way, we can provide a high-quality saliency map which can accurately locate and segment the defects. Extensive experiments are performed on the public dataset, and the results prove the effectiveness and robustness of our model which consistently outperforms the state-of-the-art models.

The automatic detection and recognition of steel surface defects is very important in the steel manufacturing industry based on the classification of defect types using artificial intelligence. Deep learning plays an important role to decrease the defection rate in the steel manufacturing industry. Defects in the surface of steel have a serious effect on the quality of steel. Previous research for the NEU-DET dataset has shown that there are some limitations, such as low detection accuracy. In this paper Feature Pyramid Network (FPN) + Resnet neural network has been proposed for detecting the overlapping and multiple defects in the complex background for improving the defect detection rate. The histogram and edge detection approach is used for feature extraction for the classification of defects. The final result shows that the proposed FPN + Resnet model trained with good steel surface defect detection performance, and the dice score is 0.7963, IoU score is 0.6818 and losses is 0.0522 which is very low as compared to others. The proposed detection approach can efficiently detect minor targeted defects on the steel surface, which can be used as a benchmark for automated steel surface defect identification.

This study aims to enhance the accuracy and robustness of surface defect detection in steel strips. Addressing the challenges of complex defect morphology, low detection accuracy, and high false alarm rates in existing methods, this paper introduces deep learning techniques. It optimizes the YOLOv7 algorithm, proposing multiple improvement strategies. Specifically, these include: employing deformable convolutions (DConv) to address morphological variations in defects; designing a bidirectional cross-attention feature fusion module (BCC) to leverage information across different feature layers fully; constructing a decoupled detection head (TSCODE) to optimize classification and localization tasks; utilizing the SIoU loss function to accelerate bounding box regression; and applying the K-means++ algorithm to obtain predefined anchor boxes. Experimental results demonstrate that the optimized algorithm achieves a mean average precision (mAP) of 80.1% on the strip steel surface defect dataset, representing a 6.0% improvement over the original method. The proposed optimization strategies significantly enhance the performance of strip steel surface defect detection.

The accurate and efficient detection of steel surface defects remains challenging due to complex backgrounds, diverse defect types, and varying defect scales. The existing CNN-based methods often struggle with capturing long-range dependencies and handling complex background noise, resulting in suboptimal performance. Meanwhile, although Transformer-based approaches are effective in modeling global context, they typically require large-scale datasets and are computationally expensive, limiting their practicality for industrial applications. To address these challenges, we introduce a novel attention-based salient object detector, called the ASOD, to enhance the effectiveness of detectors for strip steel surface defects. In particular, we first design a novel channel-attention-based block including global max/average pooling to focus on the relevant channel-wise features while suppressing irrelevant channel responses, where maximizing pooling extracts the main features of local regions, while removing irrelevant features and average pooling obtain the overall features while removing local details. Then, a new block based on spatial attention is designed to emphasize the area with strip steel surface defects while suppressing irrelevant background areas. In addition, a new cross-spatial-attention-based block is designed to fuse the feature maps with multiple scales filtered through the proposed channel and spatial attention to produce features with better semantic and spatial information such that the detector adapts to strip steel defects of multiple sizes. The experiments show that the ASOD achieves superior performance across multiple evaluation metrics, with a weighted F-measure of 0.9559, an structure measure of 0.9230, a Pratt’s figure of meri of 0.0113, and an mean absolute error of 0.0144. In addition, the ASOD demonstrates strong robustness to noise interference, maintaining consistently high performance even with 10–20% dataset noise, which confirms its stability and reliability.

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%.

To address the limitations of traditional continuous casting billet surface defect detection methods in practical applications, such as insufficient real-time performance and low detection accuracy, this study proposes an improved YOLOv8-based billet surface defect detection model, termed LRCR-YOLOv8. First, a Lightweight Spatial Cross-Down sampling (LSCD) structure
 is introduced into the network neck, which effectively reduces model parameters and computational complexity while maintaining detection accuracy. Second, an RFCAConv module is embedded into the backbone network to enhance the capability of capturing fine grained surface features of cast billets. Finally, based on the C2f module, a C2f_RFCBAMConv structure is constructed. which consists of one 3 × 3 convolutional layer and two 1 × 1 convolutional layers, thereby further optimizing feature extraction and improving the overall detection performance. Experimental results on the publicly available NEU-DET dataset demonstrate that the proposed model achieves superior detection performance across six typical defect detection categories. Specifically, the precision, recall, and mAP reach 77.8%, 73%, and 77.2%, respectively, representing improvements of 1.0 percentage point, 0.5 percentage point, and 2.7 percentage points over the original model. These results effectively validate the practical applicability and technical advancement of the proposed method in billet surface defect detection, providing technical, support for early warning and accurate identification of surface defects in the continuous casting process.

QRNet: Query-based reparameterization net for real-time detection of power adapter surface defects

In steel surface defect detection, accurately identifying various types of de-fects is essential. However, the diverse morphologies of defects and com-plex backgrounds encountered in real-world industrial production pose sig-nificant challenges for existing object detection networks. To overcome these issues, this paper presents a deep-learning-based network model named MDTH based on YOLOv10, which integrates multi-scale deep convolutional feature extraction with Swin Transformer encoding through an enhanced hy-brid attention mechanism Trans-HAM . Firstly, the Multi-Angle Perception and Depth-wise separable convolution module MAPD is employed to cap-ture the edges and texture details of steel surfaces, effectively identifying minor defects. Secondly, the Trans-HAM module extracts more comprehen-sive and fine-grained feature information, enabling the model to simultane-ously focus on both local details and global structures. Finally, MPDIoU is employed to optimize the overlap and shape matching of bounding boxes, improving the accuracy of defect localization. Experimental results on NEU-DET dataset and PKU-Market-PCB dataset show that the mAP@0.5 of the proposed MDTH model achieves a mean average precision of 81.2 and 95.3 , respectively, which greatly improves the detection accuracy, and the experimental results outperform those of the commonly used model.

Production defects caused by irresistible factors such as process design problems or differences in steel properties in strip production affect the economic benefits of the enterprise and threaten production safety. Traditional defect detection methods are difficult to achieve real-time and high-precision detection, so developing surface defect detection methods based on deep learning is of great significance for strip production. In order to effectively improve the accuracy of the deep learning model in detecting surface defects on hot-rolled strip, in this work we propose a real-time detection model for surface defects on strip steel based on the YOLOv8n model. Firstly, the newly convolutional layer Con5v is designed to replace the original convolutional layer in the neck, and an attention mechanism is added in front of each Con5v to improve the algorithm’s ability to extract small target information. Secondly, an additional set of upsampled feature extraction units is added to the neck in order to enhance the spatial information of the feature map. Subsequently, a set of feature fusion units is incorporated and the convolutional layers in it are improved to provide better feature maps. Thirdly, the number of decoupling detection heads is increased to receive more high-quality features. The final experimental results show that YOLOv8n-GAM (YOLOv8 Nano Model with Global Attention Mechanism) achieves 81.4mAP and 82.0FPS on the NEU-DET dataset and 71.2mAP and 55.0FPS on the GC10-DET dataset, which are 5.7% and 6.9% higher than those of YOLOv8n, respectively. The model proposed in this paper achieves a comprehensive performance improvement in strip steel.

Surface defect detection aims to classify and locate a certain defect that exists in the target surface area. It is an important part of industrial quality inspection. Most of the research on surface defect detection are currently based on convolutional neural networks (CNNs), which are more concerned with local information and lack global perception. Thus, CNNs are unable to effectively extract the defect features. In this paper, a defect detection method based on the Swin transformer is proposed. The structure of the Swin transformer has been fine-tuned so that it has five scales of output, making it more suitable for defect detection tasks with large variations in target size. A bi-directional feature pyramid network is used as the feature fusion part to efficiently fuse to the extracted features. The focal loss is used as a loss function to weight the hard- and easy-to-distinguish samples, potentially making the model fit the surface defect data better. To reduce the number of parameters in the model, a shared detection head was chosen for result prediction. Experiments were conducted on the flange surface defect dataset and the steel surface defect dataset, respectively. Compared with the classical CNNs target detection algorithm, our method improves the mean average precision (mAP) by about 15.4%, while the model volume and detection speed are essentially the same as those of the CNNs-based method. The experimental results show that our proposed method is more competitive compared with CNNs-based methods and has some generality for different types of defects.

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.