Defect Detection Research Articles

BGA-YOLOX-s: Real-time fine-grained detection of silkworm cocoon defects with a ghost convolution module and a joint multiscale fusion attention mechanism

The study addresses deficiencies in silkworm cocoon defect detection, enhancing the YOLOX-s network with the BGA-YOLOX-s model. By incorporating BiFPN-m, it reduces feature information loss, improving model reasoning speed. Ghost convolution reduces complexity and parameters, decreasing computational expenses. An attention module (CA) enhances fine-grained feature extraction. Experimental results on a cocoon dataset reveal a 4.1% accuracy boost to 94.89% compared to YOLOX-s. Furthermore, BGA-YOLOX-s outperforms SSD, YOLOv3, YOLOv4, and YOLOv5 in defect detection. The model proves effective in online cocoon defect detection, offering guidance for future applications in the production process.

An automatic defect detection and localization method using imaging geometric features for sewer pipes

Accurate longitudinal localization of defects in sewer pipes is crucial for efficient maintenance and renewal. However, traditional closed-circuit television (CCTV)-based localization methods have been inefficient and imprecise, impeding real-time inspection performance. In this paper, we firstly point out that the inaccuracy of CCTV-based localization methods stems from the oversight of monocular imaging geometry, which leads to a deviation in sewer defect localization. Then, we propose an automated framework for sewer defect detection and longitudinal localization based on a deep-learning algorithm and monocular imaging geometry. Specifically, structural defects are qualitatively analyzed to explore their intrinsic correlation with the pipe wall. Then, the imaging geometry is leveraged to establish the projection relationship between the defects and the pipe joints. The longitudinal localization correction model for structural defects is then developed using the pipe diameter as the actual size. Our experiments show that this framework enhances the mean average precision (mAP) for multi-defects by 7.2 % and achieves a theoretical mean absolute error of 0.2 m and a practical mean absolute error of 0.28 m for defect localization, surpassing current research. Finally, with the generated detection results and localization records, the proposed framework can promote the efficiency of the sewer investigation and accelerate the development of intelligent sewer systems.

Automatic detection and classification of road defects on a global-scale: Embedded system

Automatic detection and classification of road defects on a global-scale: Embedded system

Automatic detection and localization of internal defects in additively manufactured aluminum alloy based on deep learning

Automatic detection and localization of internal defects in additively manufactured aluminum alloy based on deep learning

Automating quality control: real-time defect detection and automated decision-making with ai and doosan robotics

Automating quality control: real-time defect detection and automated decision-making with ai and doosan robotics

Automatic crack defect detection via multiscale feature aggregation and adaptive fusion

Automatic crack defect detection via multiscale feature aggregation and adaptive fusion

Nondestructive testing of GFRP composites with compressive sensing-based terahertz single-pixel imaging

ABSTRACT Terahertz (THz) imaging technique has a wide range of applications, from industrial non-destructive testing (NDT) to various biomedical applications. Although the capabilities of terahertz radiation in defect detection are well-proven, the practical limitations have been associated with the long image acquisition time. Hence, to improve the image acquisition speed, the compressive sensing technique has been employed. However, the challenge is identifying the optimal modulation mask for compressive sensing as the image reconstruction metrics hugely depend on the mask. Hence, a systematic investigation of the different modulation masks has been done to reconstruct THz images of glass fibre-reinforced polymer (GFRP) composites using TVAL3 (Total Variation minimization by Augmented Lagrangian and ALternating direction Algorithm). The image reconstruction quality has been studied using mean square error, peak signal-to-noise ratio, and structural similarity index. From the results, it can be noticed with a 0.3 sampling ratio, reliable reconstruction of the THz image is possible, saving 70% of the image acquisition time. Further, the discrete cosine transform (DCT) mask is ideal for high frame rate NDT in low and medium noise scenarios. However, the Bernoulli basis offers high resistance to noise by resulting in the best image reconstruction results at high noise cases, outperforming the DCT.

The revolutionary impact of ai in the automotive industry

The automotive industry is undergoing a revolutionary transformation through the integration of Artificial Intelligence (AI) technologies. This article examines the multifaceted impact of AI across manufacturing, autonomous vehicle development, smart factory solutions, and customer experience enhancement. The article highlights significant improvements in manufacturing efficiency, with AI-driven quality control systems achieving high accuracy in defect detection and reducing production costs substantially. In autonomous vehicle development, AI systems have demonstrated remarkable capabilities, with object detection accuracy reaching exceptional levels under optimal conditions and decision-making architectures processing multiple discrete decisions per second. The implementation of AI in smart factories has led to considerable improvement in overall equipment effectiveness, while customer experience enhancements have resulted in a significant increase in satisfaction scores. The integration of AI in supply chain management and market intelligence has yielded substantial operational improvements, with demand forecasting accuracy reaching impressive levels for short-term predictions and enabling meaningful reduction in inventory costs.

YOLOv8-SC: Improving the YOLOv8 Network for Real-Time Detection of Automotive Coated Surface Defects

YOLOv8-SC: Improving the YOLOv8 Network for Real-Time Detection of Automotive Coated Surface Defects

An optimized lightweight real-time detection network model for IoT embedded devices.

With the rapid development of Internet of Things (IoT) technology, embedded devices in various computer vision scenarios can realize real-time target detection and recognition tasks, such as intelligent manufacturing, automatic driving, smart home, and so on. YOLOv8, as an advanced deep learning model in the field of target detection, has attracted much attention for its excellent detection speed, high precision, and multi-task processing capability. However, since IoT embedded devices typically own limited computing resources, direct deployment of YOLOv8 is a big challenge, especially for real-time detection tasks. To address this vital issue, this work proposes and deploys an optimized lightweight real-time detection network model that well-suits for IoT embedded devices, denoted as FRYOLO. To evaluate its performance, a case study based on real-time fresh and defective fruit detection in the production line is performed. Characterized by low training cost and high detection performance, this model accurately detects various types of fruits and their states, as the experimental results show that FRYOLO achieves 84.7% in recall and 89.0% in mean Average Precision (mAP), along with a precision of 92.5%. In addition, it provides a detection frame rate of up to 33 Frames Per Second (FPS), satisfying the real-time requirement. Finally, an intelligent production line system based on FRYOLO is implemented, which not only provides robust technical support for the efficient operation of fruit production processes but also demonstrates the availability of the proposed network model in practical IoT applications.

PPLA-Transformer: An Efficient Transformer for Defect Detection with Linear Attention Based on Pyramid Pooling

PPLA-Transformer: An Efficient Transformer for Defect Detection with Linear Attention Based on Pyramid Pooling

Efficient fabric defect detection based on lightweight model

Efficient fabric defect detection based on lightweight model

Convolutional neural network-based wire-cut image recognition and defect detection research

Abstract This paper presents an advanced defect detection system for wire Electrical Discharge Machining (EDM), utilizing Convolutional Neural Networks (CNNs) to automatically identify, classify, and localize defects such as cracks, notches, and burrs. Wire EDM is a precision manufacturing process critical for cutting conductive materials, where defect detection plays a vital role in ensuring product quality. The proposed method incorporates a modified ResNet-50 architecture, optimized specifically for defect detection in wire EDM. The architecture leverages deep residual learning to enhance feature extraction, allowing the system to detect minute defects effectively. A dataset of 10,000 RGB images (224x224 pixels) was used for training, with the model achieving an impressive 95.3% accuracy, 94.2% recall, 95.8% precision, and 94.7% F1 score on the test set. The system demonstrated excellent performance in detecting cracks, though it showed slightly lower performance on deformation-related defects. A comprehensive comparison with traditional defect detection methods and other deep learning models underscores the superiority of the proposed approach in terms of both accuracy and robustness. The results indicate that this CNN-based system offers a reliable and efficient solution for quality control in wire EDM processes. Future research will focus on further optimizing the network for real-time defect detection and extending the approach to incorporate multi-modal data, such as sensor and acoustic signals, to improve overall detection performance.

Detection of Defects on Metal Surfaces Based on Deep Learning

Various types of defects can occur on metal surfaces during production due to various factors. Detecting these defects is of great importance for the quality and reliability of the product. Manual inspections are time-consuming and prone to errors, especially as production scales increase Although Deep Learning and Computer Vision techniques show promise, the large data sizes of datasets created for deep learning and the high training costs of deep learning models lead to negative effects in terms of storage and energy efficiency. We propose a new method to improve defect detection rates, reduce labor losses, decrease data sizes, and improve energy efficiency. For the experiments, we used the Northeastern University (NEU) surface defect database as a reference, and the MobileNetV2 architecture as the model. The deep learning model was trained separately using both the grayscale-converted NEU database and the database created with the proposed method, and the accuracies of the datasets were compared. Image preprocessing techniques such as morphological operations, Gaussian noise addition, Principal Component Analysis, and image thresholding with Otsu thresholding were used for defect detection. The model was trained using the newly created database, achieving a successful result with an average accuracy rate of 87% using the proposed algorithm.

Real-Time High Dynamic Equalization Industrial Imaging Enhancement Based on Fully Convolutional Network

Severe reflections on the surfaces of smooth objects can result in low dynamic range and uneven illumination in images, which negatively impacts downstream tasks such as defect detection and QR code recognition on images of smooth workpieces. Consequently, this paper proposes a novel approach to real-time high dynamic equalization imaging based on a fully convolutional network, termed Multi-exposure Image Fusion with Multi-dimensional Attention Mechanism and Training Storage Units (MEF-AT). Specifically, this paper innovatively proposes using training storage units, which utilize intermediate results during network training as auxiliary images, to remove uneven illumination and enhance image dynamic range effectively. Furthermore, by integrating a multi-dimensional attention mechanism into the backbone network, the model can more efficiently extract and utilize critical image information. Additionally, this paper introduces a Deep Guided Filter (DGF) with learnable parameters, which upsample the weight maps generated by the network, thus better adapting to complex industrial scenarios and producing higher quality fused images. An image evaluation metric assessing the lighting uniformity is introduced to thoroughly evaluate the proposed method’s performance. Given the lack of an MEF dataset for smooth workpieces, this paper collects a new dataset for multi-exposure fusion tasks on metallic workpieces. Our method takes less than 4 ms to run four 2K images on a GPU 3090. Both qualitative and quantitative experimental results demonstrate our method’s superior comprehensive performance in proprietary industrial and public datasets.

Development of an AI-Based Image Analysis Model for Verifying Partial Defects in Nuclear Fuel Assemblies

The increase in the number of nuclear power plants utilized for achieving carbon neutrality has emphasized the importance of managing high-radiation spent nuclear fuel (SNF). Traditional inspection methods, such as gamma emission tomography (GET), have limitations in terms of detecting partial defects within SNF assemblies. This study aims to increase the accuracy of SNF defect detection by optimizing artificial intelligence (AI)-based classification algorithms. By using emission tomography image data acquired from 3 × 3 nuclear fuel assemblies, we compare the performance of neural network models (AlexNet, ResNet, and the squeeze-and-excitation network (SENet)) and tree-based ensemble models (extreme gradient boosting (XGBoost), random forest model, and light gradient boosting machine (LightGBM)). Our results show that the neural network models, particularly ResNet and SENet, achieve superior classification accuracy with limited training data. SENet in particular demonstrates high performance with fewer samples, indicating its defect detection effectiveness in scenarios with minimal data. Tree-based models such as XGBoost and LightGBM also exhibit high accuracy but are slightly less effective than the neural networks are. In conclusion, AI-based classification systems, especially those utilizing advanced neural networks, can significantly improve the inspection and management processes related to SNFs, ensuring safety and compliance in nuclear energy operations. Future work should explore these methodologies for larger configurations beyond 3 × 3 assemblies to further validate their effectiveness.

Research on the lightweight detection method of rail internal damage based on improved YOLOv8

To address the challenges of high computational costs, large storage demands, and low detection accuracy in internal rail damage identification, we propose a lightweight detection model, GhostMicroNet-YOLOv8n, as an enhancement of YOLOv8n. This model offers efficient and reliable technical support for detecting and classifying internal rail damage in rail flaw detection tasks. The proposed model introduces four key innovations. Firstly, the GhostHGNetV2 network is adopted as the feature extraction backbone, which reduces computational costs through structural optimization. Secondly, the Triplet Attention (TA) mechanism is incorporated to enhance the model’s ability to distinguish internal rail damage from complex backgrounds, thereby improving detection accuracy. Thirdly, the network structure is refined to better capture the scale characteristics of damage in B-scan data, improving small-target detection. Finally, the model is compressed using the Layer-Adaptive Sparsity for Magnitude-Based Pruning (LAMP) technique, significantly reducing model complexity while maintaining performance. Experimental results validate the effectiveness of the proposed model, achieving a 2.67% improvement in detection accuracy, a 91.67% reduction in parameters, a 64.20% decrease in computational cost, and an 84.87% reduction in model size compared to YOLOv8n. The model achieves an optimal balance between detection accuracy and computational efficiency, addressing the railroad industry’s demand for real-time defect detection and ensuring accurate flaw identification in resource-constrained Rail Fault Detection (RFD) vehicles.

SF-YOLO: designed based on tiny feature for PCB surface defect detection and deployment in embedded systems

SF-YOLO: designed based on tiny feature for PCB surface defect detection and deployment in embedded systems

A Novel YOLOv10-Based Algorithm for Accurate Steel Surface Defect Detection

To address challenges like manual processes, complicated detection methods, high false alarm rates, and frequent errors in identifying defects on steel surfaces, this research presents an innovative detection system, YOLOv10n-SFDC. The study focuses on the complex dependencies between parameters used for defect detection, particularly the interplay between feature extraction, fusion, and bounding box regression, which often leads to inefficiencies in traditional methods. YOLOv10n-SFDC incorporates advanced elements such as the DualConv module, SlimFusionCSP module, and Shape-IoU loss function, improving feature extraction, fusion, and bounding box regression to enhance accuracy. Testing on the NEU-DET dataset shows that YOLOv10n-SFDC achieves a mean average precision (mAP) of 85.5% at an Intersection over Union (IoU) threshold of 0.5, a 6.3 percentage point improvement over the baseline YOLOv10. The system uses only 2.67 million parameters, demonstrating efficiency. It excels in identifying complex defects like ’rolled in scale’ and ’inclusion’. Compared to SSD and Fast R-CNN, YOLOv10n-SFDC outperforms these models in accuracy while maintaining a lightweight architecture. This system excels in automated inspection for industrial environments, offering rapid, precise defect detection. YOLOv10n-SFDC emerges as a reliable solution for the continuous monitoring and quality assurance of steel surfaces, improving the reliability and efficiency of steel manufacturing processes.

Research on meshing method for industrial CT volume data based on iterative smooth signed distance surface reconstruction

Industrial Computed Tomography (CT) technology is increasingly applied in fields such as additive manufacturing and non-destructive testing, providing rich three-dimensional information for various fields, which is crucial for internal structure detection, defect detection, and product development. In subsequent processes such as analysis, simulation, and editing, three-dimensional volume data models often need to be converted into mesh models, making effective meshing of volume data essential for expanding the application scenarios and scope of industrial CT. However, the existing Marching Cubes algorithm has issues with low efficiency and poor mesh quality during the volume data meshing process. To overcome these limitations, this study proposes an innovative method for industrial CT volume data meshing based on the Iterative Smooth Signed Surface Distance (iSSD) algorithm. This method first refines the segmented voxel model, accurately extracts boundary voxels, and constructs a high-quality point cloud model. By randomly initializing the normals of the point cloud and iteratively updating the point cloud normals, the mesh is reconstructed using the SSD algorithm after each iteration update, ultimately achieving high-quality, watertight, and smooth mesh model reconstruction, ensuring the accuracy and reliability of the reconstructed mesh. Qualitative and quantitative analyses with other methods have further highlighted the excellent performance of the method proposed in this paper. This study not only improves the efficiency and quality of volume data meshing but also provides a solid foundation for subsequent three-dimensional analysis, simulation, and editing, and has important industrial application prospects and academic value.