Defect Detection Model Research Articles

Surface defect detection model of laser cutting polycrystalline cubic boron nitride tool based on asymptotic fusion strategy

Due to the polycrystalline cubic boron nitride tool has the characteristics of high hardness, brittleness, etc., it is easy to break the tool or produce defects in the laser cutting process, which affects the cutting performance of the tool. Traditional defect detection methods can no longer meet the needs of modern manufacturing. Aiming at the problems of low accuracy and poor real-time detection of surface defects on laser-cutting polycrystalline cubic boron nitride tools, this study proposes the surface defect detection model of laser cutting polycrystalline cubic boron nitride tool based on asymptotic fusion strategy, which fills the gap in the field. In the backbone network, the C3SE module is constructed by modeling the correlation between feature channels to improve the model’s focus on key features in order to enhance the feature extraction and processing capability of the backbone network; In the neck network, adaptive spatial fusion operation and direct interaction of non-adjacent layers are utilized for multi-scale information fusion, and the asymptotic feature pyramid network for object detection (AFPN) is used instead of the FPN structure to improve the detection performance; In the head network, a soft suppression mechanism is introduced to reduce the overlapping frame score using a decay function, thus improving the detection accuracy. The experimental results based on the self-constructed laser-cutting polycrystalline cubic boron nitride tool surface defects dataset show that the average accuracy of the AFFS-YOLO model is improved by 5.6% compared with that of the YOLOv5 model, reaching 86.1%, and the detection effect is better than that of the original network and other classical target detection networks.

DCS-YOLO: Defect detection model for new energy vehicle battery current collector.

The future trend in global automobile development is electrification, and the current collector is an essential component of the battery in new energy vehicles. Aiming at the misjudgment and omission caused by the confusing distribution, a wide range of sizes and types, and ambiguity of target defects in current collectors, an improved target detection model DCS-YOLO (DC-SoftCBAM YOLO) based on YOLOv5 is proposed. Firstly, the detection rate of defects with different scales is improved by adding detection layers; Secondly, we use the designed DC module as the backbone network to help the model capture the global information and semantic dependencies of the target, and effectively improve the generalization ability and detection performance of the model. Finally, in the neck part, we integrate our designed Convolutional Block Attention Module (SoftPool Convolutional Block Attention Module, SoftCBAM), which can adaptively learn the importance of channels, enhance feature representation, and enable the model to better deal with target details. Experimental results show that the mAP50 of the proposed DCS-YOLO model is 92.2%, which is 5.1% higher than the baseline model. The FPS reaches 147.1, and the detection accuracy of various defect categories is improved, especially Severely bad and No cover, and the detection recall rate reaches 100%. This method has high target detection model efficiency and meets the requirements of real-time detection of battery collector defects.

Hyper CLS-Data-Based Robotic Interface and Its Application to Intelligent Peg-in-Hole Task Robot Incorporating a CNN Model for Defect Detection

Various types of numerical control (NC) machine tools can be standardly operated and controlled based on NC data that can be easily generated using widespread CAD/CAM systems. On the other hand, the operation environments of industrial robots still depend on conventional teaching and playback systems provided by the makers, so it seems that they have not been standardized and unified like NC machine tools yet. Additionally, robotic functional extensions, e.g., the easy implementation of a machine learning model, such as a convolutional neural network (CNN), a visual feedback controller, cooperative control for multiple robots, and so on, has not been sufficiently realized yet. In this paper, a hyper cutter location source (HCLS)-data-based robotic interface is proposed to cope with the issues. Due to the HCLS-data-based robot interface, the robotic control sequence can be visually and unifiedly described as NC codes. In addition, a VGG19-based CNN model for defect detection, whose classification accuracy is over 99% and average time for forward calculation is 70 ms, can be systematically incorporated into a robotic control application that handles multiple robots. The effectiveness and validity of the proposed system are demonstrated through a cooperative pick and place task using three small-sized industrial robot MG400s and a peg-in-hole task while checking undesirable defects in workpieces with a CNN model without using any programmable logic controller (PLC). The specifications of the PC used for the experiments are CPU: Intel(R) Core(TM) i9-10850K CPU 3.60 GHz, GPU: NVIDIA GeForce RTX 3090, Main memory: 64 GB.

Bilateral Defect Cutting Strategy for Sawn Timber Based on Artificial Intelligence Defect Detection Model.

Solid wood is renowned as a superior material for construction and furniture applications. However, characteristics such as dead knots, live knots, piths, and cracks are easily formed during timber's growth and processing stages. These features and defects significantly undermine the mechanical characteristics of sawn timber, rendering it unsuitable for specific applications. This study introduces BDCS-YOLO (Bilateral Defect Cutting Strategy based on You Only Look Once), an artificial intelligence bilateral sawing strategy to advance the automation of timber processing. Grounded on a dual-sided image acquisition platform, BDCS-YOLO achieves a commendable mean average feature detection precision of 0.94 when evaluated on a meticulously curated dataset comprising 450 images. Furthermore, a dual-side processing optimization module is deployed to enhance the accuracy of defect detection bounding boxes and establish refined processing coordinates. This innovative approach yields a notable 12.3% increase in the volume yield of sawn timber compared to present production, signifying a substantial leap toward efficiently utilizing solid wood resources in the lumber processing industry.

Insulator Defect Detection Model based on Improved YOLOv7

Insulator Defect Detection Model based on Improved YOLOv7

A Lightweight Strip Steel Surface Defect Detection Network Based on Improved YOLOv8

Strip steel surface defect detection has become a crucial step in ensuring the quality of strip steel production. To address the issues of low detection accuracy and long detection times in strip steel surface defect detection algorithms caused by varying defect sizes and blurred images during acquisition, this paper proposes a lightweight strip steel surface defect detection network, YOLO-SDS, based on an improved YOLOv8. Firstly, StarNet is utilized to replace the backbone network of YOLOv8, achieving lightweight optimization while maintaining accuracy. Secondly, a lightweight module DWR is introduced into the neck and combined with the C2f feature extraction module to enhance the model’s multi-scale feature extraction capability. Finally, an occlusion-aware attention mechanism SEAM is incorporated into the detection head, enabling the model to better capture and process features of occluded objects, thus improving performance in complex scenarios. Experimental results on the open-source NEU-DET dataset show that the improved model reduces parameters by 34.4% compared with the original YOLOv8 algorithm while increasing average detection accuracy by 1.5%. And it shows good generalization performance on the deepPCB dataset. Compared with other defect detection models, YOLO-SDS offers significant advantages in terms of parameter count and detection speed. Additionally, ablation experiments validate the effectiveness of each module.

Augmenting human-guided progressive learning with machine vision systems for robust surface defect detection

Machine vision systems commonly utilize Convolutional Neural Networks (CNNs) for in-line surface defect detection of manufactured components. The prediction abilities of vision-based inspection systems deteriorate with time as the defect detection model trained on fixed image datasets fails to accommodate deviations. This paper proposes a human-guided progressive learning approach that systematically imparts learning of new features to the CNN-powered vision-based defect detection system. The approach augments the surface defect detection model with human intelligence, using an intuitive user interface to address model drift. The human expert monitors the trained model performance under specific conditions leading to the change of characteristics during implementation, identifies misclassifications, and initiates re-training. The algorithm accumulates misclassified data till a pre-defined threshold level is reached or a human expert terminates inspection. The misclassified results merge with the original datasets for progressive re-training using a strategy similar to the base model development. The present work utilizes pre-trained CNN Efficientnet-b0 to develop the surface defect detection model for tapered roller inspection through transfer learning. It is concluded that the progressive re-training improves defect detection performance and reduces misclassifications. The Matthews Correlation Coefficient (MCC) score, derived from the confusion matrix, showed improvement from 0.6 to 0.82 after four iterations. A cross-model benchmarking study is also performed to show the versatility of the proposed approach. The present work demonstrated that the human-guided progressive learning approach can provide adaptability to vision-based surface defect detection utilizing deep learning algorithms and enhance system performance during real-time implementation.

Attention Pyramid Dilated Region-based Model for Metallurgical Defect Detection

Abstract Defect recognition is the key to realizing automatic visual inspection and quality control in intelligent manufacturing. Deep learning (DL) has been widely applied to locate damaged areas in images, characterize impurities of materials and further analyze the quality of products. However, automatic defect detection by DL in practical industrial applications is still a challenge due to the lack of sufficient datasets and appropriate recognition methods. Here, a novel Attention Pyramid Dilated Region-based Convolutional Neural Network (ADRCNN) is proposed to realize the multi-scale defect recognition and pixel-level instance segmentation of metallographic images. We also collected a dataset containing 900 images of commercial A356 aluminum alloy with different casting defects. The ADRCNN model is evaluated on our dataset with an average detection accuracy of 87.2% and 93.3% on validation and test sets respectively. To address the overfitting problem, a pretraining fine-tuning strategy is implemented by using the pretraining weights from large-scale datasets and temporarily freezing the weights of the backbone network during the training process. The experimental results show that the proposed model can achieve satisfactory defect segmentation in metallographic images, promoting the development of intelligent manufacturing in alloy industries.

Lightweight bearing defect detection method based on collaborative attention and domain adaptive technology

Abstract With the rapid development of industrial manufacturing, bearing defect detection has become a key link to ensure the safe operation of equipment and improve production efficiency. Aiming at the problems of low accuracy and large parameters of traditional bearing defect detection models, this paper proposes a lightweight bearing defect detection method based on collaborative attention and domain adaptive technology. Firstly, the collaborative attention mechanism uses multiple parallel attention heads to extract the features of different regions in the image respectively. Each attention head can independently extract and weigh the features of specific regions, which can capture the complex features of bearing defects more comprehensively, including shape, texture, edge and other key information. At the same time, the domain adaptation technology aims to make the model adapt to the data distribution of different domains. It reduces the difference between the source domain and the object domain by aligning the feature distribution between the source domain and the object domain during the training process, thereby improving the performance of the model on the object domain. The experimental results show that the proposed method is 2.75% higher than the mAP@0.5 of YOLOv7, and has higher computational efficiency and better generalization ability than the traditional method.

YOLO-Based Design and Optimization of Weld Seam Detection Model

Abstract The traditional welding seam inspection efficiency is low, the model possesses a significant amount of computational parameters, and it is not suitable for the application of small and medium-sized welding seam recognition machines. In view of the wide application and remarkable effect of deep learning in the domain of machine vision, a welding seam defect detection model designed by G-Efficientnet-CA neural network was proposed and optimized. EfficientNet was employed as the core architecture for extracting features to greatly reduce calculation parameters and model volume. The CA attention mechanism is incorporated to enhance the model’s capacity for focusing attention on the weld image, thereby improving its ability to discern and analyze relevant features, and the accuracy is improved. The Generalized Intersection over Union (GIoU) loss function is changed from the original loss function to optimize the calculation of the coincidence degree between the real frame and the predicted frame. The efficient K-Means++ clustering algorithm is utilized to calculate the initial anchor frame which is more suitable for different weld data sets. The experimental outcomes demonstrate that the optimized model, when compared to the YOLOv3 model, exhibits superior effectiveness in detecting the VOC2007 dataset, as evidenced by a notable 12.7% increase in the average precision (mAP) and a significant reduction of 88% in the number of parameters.

Novel intelligent defects detection of boiler water walls in thermal power plants based on OFM_SSD

The boiler is a critical component of conventional thermal power systems, where surface flaws in boiler water walls can significantly compromise safety and availability, potentially leading to substantial loss of life and property. Traditional detection methods, whether manual or based on machine learning, often prove costly, inefficient and time-consuming, failing to meet the stringent requirements for water wall inspection. Therefore, a novel surface defect detection model integrating an improved single shot multibox detector (SSD) with the optical flow method (OFM) (OFM_SSD) is proposed. The OFM enhances data sample diversity by augmenting the dataset derived from thermal power plants, while the incorporation of deconvolution techniques improves the model receptive field, thereby enhancing its ability to detect and classify small defects. Comprehensive experiments demonstrate that the OFM_SSD outperforms several existing models including the SSD model based on traditional expanded datasets (T_SSD), you only look once (YOLO), ordinary SSD, Regions with the CNN(R_CNN), and Deconvolution-only SSD (DSSD) in terms of accuracy in defect localization and classification. This advancement of the OFM_SSD not only reduces operational costs but also enhances detection capabilities, ultimately contributing to safer and more efficient operations within thermal power plants.

RCYOLO: an innovative surface defect detection model for magnetic blocks integrating RevCol and Yolov8s

ABSTRACT The surface defect detection of magnetic blocks faces challenges such as low accuracy, high missed detection rates, and weak anti-interference capabilities. Additionally, existing models are often large in size and require significant computational resources. To address these issues, this article integrated the Yolov8 framework and designed the RCYOLO model to improve detection performance and resource utilization. Firstly, we used RevCol as the backbone, and explored its optimal number of sub-networks to reduce model parameters and complexity, as well as improve model robustness. Secondly, we removed some deep structures from Yolov8s to simplify the model, making it easier to deploy. Afterwards, we developed a more efficient feature extraction module, C2f_SA, and replaced all existing modules with it to compensate for accuracy loss caused by simplification and improve overall detection performance. Finally, we optimized reg_max to explore the best minimum value for detecting defects in magnetic blocks to reduce unnecessary computational burden. Experimental results show that compared to Yolov8s, although RCYOLO’s mAP0.5 was reduced by 0.2%, it significantly reduced the model parameters, FLOPs, and model size by 51.64%, 30.31%, and 50.22%, respectively, achieving a better balance between accuracy and resources. Moreover, RCYOLO demonstrated good detection performance compared to other improved models.

SCS-YOLO: A Defect Detection Model for Cigarette Appearance

Appearance defects significantly impact cigarette quality. However, in the current high-speed production lines, manual inspection and traditional methods are unable to satisfy the actual demands of inspection. Therefore, a real-time and high-precision defect detection model for cigarette appearance, SCS-YOLO, is presented. The model integrates space-to-depth convolution (SPD-Conv), a convolutional block attention module (CBAM), and a self-calibrated convolutional module (SCConv). SPD-Conv replaces the pooling structure to enhance the granularity of feature information. CBAM improves the ability to pay attention to defect locations. Improved self-calibrated convolution broadens the network’s receptive field and feature fusion capability. Additionally, Complete IoU loss (CIoU) is replaced with Efficient IoU Loss (EIoU) to enhance model localization and mitigate sample imbalance. The experimental results show that the accuracy of SCS-YOLO is 95.5% and the mAP (mean average precision) value is 95.2%. Compared with the original model, the accuracy and mAP value of the SCS-YOLO model are improved by 4.0%. Furthermore, the model achieves a detection speed of 216 FPS, meeting cigarette production lines’ accuracy and speed demands. Our research will positively impact the real-time detection of appearance defects in cigarette production lines.

A photovoltaic cell defect detection model capable of topological knowledge extraction

As the global transition towards clean energy accelerates, the demand for the widespread adoption of solar energy continues to rise. However, traditional object detection models prove inadequate for handling photovoltaic cell electroluminescence (EL) images, which are characterized by high levels of noise. To address this challenge, we developed an advanced defect detection model specifically designed for photovoltaic cells, which integrates topological knowledge extraction. Our approach begins with the introduction of a multi-scale dynamic context-based feature extraction method, capable of generating static context by thoroughly capturing the local texture and structural information of multi-scale defects. This static context is then combined with dynamic context to produce fine-grained local features. Subsequently, we developed a centralized feature pyramid structure, enhanced by spatial semantics, which models the explicit visual center. This structure effectively elucidates the relationship between local and global features in defect images, thereby improving the representation of defect characteristics. Finally, we implemented a feature enhancement strategy grounded in spatial semantic knowledge extraction. This strategy uncovers potential correlations among defect targets by constructing a spatial semantic topology of features, mapping these features to a higher-order representation, and ultimately delivering precise defect detection results.

MT-U2Net: Lightweight detection network for high-precision magnetic tile surface defect localization

Automated surface defect localization is closely related to product quality control. Although many image segmentation models have achieved excellent results in industrial defect localization, the wide-ranging defects in magnetic tile materials and the similarity between textures and background textures make it difficult to balance detection model performance and model size. Therefore, we propose a new magnetic tile defect localization model called MT-U2Net. The model consists of three parts: Dres-Ublock, U2 structure, and attention mechanism. Dres-Ublock is used to enhance the model's feature extraction capability and reduce its size; the U2-Net structure is utilized to learn cross-scale defect information; the attention mechanism is employed to eliminate redundant information. MT-U2Net improves detection performance across various defect scales. In the test set, MT-U2Net achieves an F1 Score of 0.840 and an MAE of 0.024 and compresses the model size to 3.39 M. Extensive experimental results show that MT-U2Net outperforms existing state-of-the-art algorithms in magnetic tile defect detection performance and model size.

Automatic defect detection in infrared thermal images of ancient polyptychs based on numerical simulation and a new efficient channel attention mechanism aided Faster R-CNN model

In recent years, the preservation and conservation of ancient cultural heritage necessitate the advancement of sophisticated non-destructive testing methodologies to minimize potential damage to artworks. Therefore, this study aims to develop an advanced method for detecting defects in ancient polyptychs using infrared thermography. The test subjects are two polyptych samples replicating a 14th-century artwork by Pietro Lorenzetti (1280/85–1348) with varied pigments and artificially induced defects. To address these challenges, an automatic defect detection model is proposed, integrating numerical simulation and image processing within the Faster R-CNN architecture, utilizing VGG16 as the backbone network for feature extraction. Meanwhile, the model innovatively incorporates the efficient channel attention mechanism after the feature extraction stage, which significantly improves the feature characterization performance of the model in identifying small defects in ancient polyptychs. During training, numerical simulation is utilized to augment the infrared thermal image dataset, ensuring the accuracy of subsequent experimental sample testing. Empirical results demonstrate a substantial improvement in detection performance, compared with the original Faster R-CNN model, with the average precision at the intersection over union = 0.5 increasing to 87.3% and the average precision for small objects improving to 54.8%. These results highlight the practicality and effectiveness of the model, marking a significant progress in defect detection capability, providing a strong technical guarantee for the continuous conservation of cultural heritage, and offering directions for future studies.

MSIDetector: Detecting Multi-Scenario industrial defects using an adapted visual foundation model and dual thresholding discriminator

Industrial defect detection is crucial for enhancing product quality. The diverse nature of industrial scenarios has posed challenges for developing a unified defect detection model that can address multiple industrial scenarios. To meet this challenge, we started from a data perspective, developing three self-designed data acquisition apparatuses to capture defect samples from multiple industrial scenarios. Leveraging grounding DINO (GDINO), an open-set detection approach, we propose a unified defect detection method, MSIDetector. By integrating an industrial feature adapter and a context-aware dual-thresholding defect discriminator, we successfully incorporate prior industrial knowledge into the model. The performance of the MSIDetector was evaluated across four industrial scenarios, including a public defect dataset, achieving a total state-of-the-art mAP@50 of 76.2, surpassing the performance of FasterRCNN, YOLO-7X, and the visual foundation model GDINO, with quantitative increases of 13.93, 6.55, and 2.1, respectively. This report represents the first successful attempt to apply foundation models to defect detection.

SGM-YOLO: YOLO based defect detection model for wood lumber

SGM-YOLO: YOLO based defect detection model for wood lumber

PCB defect detection algorithm based on deep learning

Deep learning gained great popularity in the task of object detection. This paper proposes a printed circuit board (PCB) defect detection algorithm based on deep learning, which can improve product quality and avoid potential failures and accidents in the electronics manufacturing industry. In this paper, the YOLOv7 model is selected as the original model for PCB defect detection. Firstly, the K-means++ clustering algorithm is used to calculate the target anchor parameters which can enhance the dataset. Secondly, the receptive field enhancement (RFE) module is added to the head layer of the network to take full advantage of the receptive field in the feature map. Thirdly, the loss function CIoU of the YOLOv7 model is changed to WIoUv2. Fourthly, add the Triplet attention mechanism to the CBS and SPPCSPC modules. Finally, the detection accuracy of the improved YOLOv7 model is compared with that of Faster R-CNN, SSD, YOLOv3-tiny, YOLOv5s, and YOLOv7 models. The experimental results show that the detection accuracy and detection speed of the improved YOLOv7 model are enhanced compared with the original YOLOv7 model.

MFAD-RTDETR: A Multi-Frequency Aggregate Diffusion Feature Flow Composite Model for Printed Circuit Board Defect Detection

To address the challenges of excessive model parameters and low detection accuracy in printed circuit board (PCB) defect detection, this paper proposes a novel PCB defect detection model based on the improved RTDETR (Real-Time Detection, Embedding and Tracking) method, named MFAD-RTDETR. Specifically, the proposed model introduces the designed Detail Feature Retainer (DFR) into the original RTDETR backbone to capture and retain local details. Subsequently, based on the Mamba architecture, the Visual State Space (VSS) module is integrated to enhance global attention while reducing the original quadratic complexity to a linear level. Furthermore, by exploiting the deformable attention mechanism, which dynamically adjusts reference points, the model achieves precise localization of target defects and improves the accuracy of the transformer in complex visual tasks. Meanwhile, a receptive field synthesis mechanism is incorporated to enrich multi-scale semantic information and reduce parameter complexity. In addition, the scheme proposes a novel Multi-frequency Aggregation and Diffusion feature composite paradigm (MFAD-feature composite paradigm), which consists of the Aggregation Diffusion Fusion (ADF) module and the Refiner Feature Composition (RFC) module. It aims to strengthen features with fine-grained awareness while preserving a certain level of global attention. Finally, the Wise IoU (WIoU) dynamic nonmonotonic focusing mechanism is used to reduce competition among high-quality anchor boxes and mitigate the effects of the harmful gradients from low-quality examples, thereby concentrating on anchor boxes of average quality to promote the overall performance of the detector. Extensive experiments are conducted on the PCB defect dataset released by Peking University to validate the effectiveness of the proposed model. The experimental results show that our approach achieves the 97.0% and 51.0% performance in mean Average Precision (mAP)@0.5 and mAP@0.5:0.95, respectively, which significantly outperforms the original RTDETR. Moreover, the model reduces the number of parameters by approximately 18.2% compared to the original RTDETR.