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

We present a novel method for small surface defect detection based on the spatially filtered dynamic speckles. This method possesses high fidelity and versatility. Factors defining resolution of the proposed method is estimated and it is shown that resolution depends solely on the geometrical parameters of the optical system. Experimental results demonstrate feasibility of the proposed method for surface defect detection and are in good agreement with the theoretical estimations. A prototype for online detection of the defects with diameter of 400 µm is presented. Ways to improve prototype performance and the method resolution are discussed.

Various methods of detecting surface defects are being used in automated industrial manufacturing environments. This work presents the design and development of a laser charged couple device (CCD) displacement scanning system. The surface defect detection method using a laser CCD displacement sensor is derived from an idea in which surface defects such as cracks, inclusions and holes of three‐dimensional morphology characteristics are compared to normal surface especially in continuous casting slabs. Some novel research methods have been applied to develop the surface defect detection system used: first, getting a one‐dimensional distance matrix along transverse direction and a two‐dimensional matrix combining with a certain moving speed through the laser CCD displacement sensor; second, obtaining the slab surface profile and mapping to a greyscale image and finally, obtaining the surface defect regions by an image processing and searching algorithm and quantitatively detecting slab surface defect shape and depth. The research results in the lab trials have shown that the methodology proposed is effective to detect two‐dimensional defect size and reconstruct a three‐dimensional surface defect shape. At the same time, it is also able to accurately locate and identify surface defects and realise automatic surface defect non‐destructive detection online, and provides a theoretical base and technology idea for further studying surface defects online inspection for hot continuous casting slab.

Surface defect detection is challenging due to varying defect types and their novelties. Because of this, it is hard for algorithms to implement across datasets. Moreover, current automated optical inspection (AOI) machines cannot handle this novelty effectively. In this work, we develop a new method for surface defect detection based on generative models, which can detect novelty according to learned distributions. Experimental results on real industrial datasets show that the proposed method can successfully construct the surface texture pattern generator. By transforming the image through the generator to the corresponding latent space, the defects can be separated effectively without a tedious effort of annotation in a large amount of training data.

At present, the detection of surface defects of paper-plastic composite bags still mainly depends on manual visual inspection, which is very inefficient and easy to cause false detection. Based on the algorithm which combines edge detection and adaptive region growth, binary images of the surface defect areas is extracted, six types of shape features and seven types of invariant moment features are defined by calculation as the basis to complete the effective extraction of the surface features, then a paper-plastic composite bags surface defect detection platform is built to complete the defect detection experiment, the defect screening experiment was completed by the rapid screening method of its surface defect image based on gradient projection difference. At the same time, based on Genetic Algorithm (GA), Particle Swarm Optimization, and Grey Wolf Optimization, parameter optimization models of Support Vector Machine were established, respectively. Through experimental comparison, some results show that the defect detection and classification accuracy rate reach 96.83% based on the GA, and the detection speed with the screening method is 3.75 times faster than that without the screening method. Therefore, the reliability of the image classification and screening method for bags surface defects proposed in this study is verified.

Sanitary ceramic products, such as toilet and wash basin, are widely used in our daily life. Sanitary ceramics are expected to have some excellent physical properties, such as corrosion resistance, easy cleaning, and low water absorption. However, surface defects in sanitary ceramics are inevitable due to complex production processes and changing production environment. Therefore, surface defect detection must be performed in the manufacturing process of sanitary ceramics. There are many types of surface defects in sanitary ceramics, and different types of defects have large differences in characteristics and scales. Traditional detection methods with artificially designed features and classifiers are difficult to apply in this context. In addition, there are few studies on surface defect detection methods of sanitary ceramics based on deep neural networks. In this article, a lightweight real-time defect detection network based on the lightweight backbone MobileNetV3 is presented. The proposed network achieves multi-scale detection of surface defects in sanitary ceramics with a multi-layer feature pyramid. Combining region proposal network and anchor-free method, real-time defect detection is achieved. Finally, a detection head with channel attention structure and a low-level mixed feature classification strategy is used to perform defect classification with higher accuracy. Experimental results show that the proposed approach achieves at least 22.9% detection speed improvement and 35.0% average precision improvement while reducing memory consumption by at least 8.4% compared with the classic one-stage SSD, YOLO V3 and two-stage Faster R-CNN methods.

In order to solve the problems of low recognition rate, incapability of autonomous detection and weak generality of the existing surface defect detection methods, an improved depth learning surface defect detection method is proposed. This method improves the convolution neural network model in depth learning and divides it into two modules: segmentation module and decision module. After preprocessing, the image is input to the segmentation module for training, and then the output of the segmentation module and network features are used as input to the decision module to detect defects in the image. In the improved model, the convolution layer and convolution kernel size in the segmentation module are optimized, and a new convolution network model is constructed. In downsampling, the maximum pool is used instead of the maximum stride, and the loss function and activation function are designed at the same time. Experiments show that the method has a high defect detection accuracy rate of 99%, realizes autonomous detection, and has certain universality.

Traditional manual inspection approaches face challenges due to the reliance on the experience and alertness of operators, which limits their ability to meet the growing demands for efficiency and precision in modern manufacturing processes. Deep learning techniques, particularly in object detection, have shown significant promise for various applications. This paper proposes an improved YOLOv11-based method for surface defect detection in electronic products, aiming to address the limitations of existing YOLO models in handling complex backgrounds and small target defects. By introducing the MD-C2F module, DualConv module, and Inner_MPDIoU loss function, the improved YOLOv11 model has achieved significant improvements in precision, recall rate, detection speed, and other aspects. The improved YOLOv11 model demonstrates notable improvements in performance, with a precision increase from 90.9% to 93.1%, and a recall rate improvement from 77.0% to 84.6%. Furthermore, it shows a 4.6% rise in mAP50, from 84.0% to 88.6%. When compared to earlier YOLO versions such as YOLOv7, YOLOv8, and YOLOv9, the improved YOLOv11 achieves a significantly higher precision of 89.3% in resistor detection, surpassing YOLOv7’s 54.3% and YOLOv9’s 88.0%. In detecting defects like LED lights and capacitors, the improved YOLOv11 reaches mAP50 values of 77.8% and 85.3%, respectively, both outperforming the other models. Additionally, in the generalization tests conducted on the PKU-Market-PCB dataset, the model’s detection accuracy improved from 91.4% to 94.6%, recall from 82.2% to 91.2%, and mAP50 from 91.8% to 95.4%.These findings emphasize that the proposed YOLOv11 model successfully tackles the challenges of detecting small defects in complex backgrounds and across varying scales. It significantly enhances detection accuracy, recall, and generalization ability, offering a dependable automated solution for defect detection in electronic product manufacturing.

Electrolytic capacitor surface defect detection based on deep convolution neural network

Surface defect inspection methods have proven effective in addressing casting quality control tasks. However, traditional inspection methods often struggle to achieve high-precision detection of surface defects in castings with similar characteristics and minor scales. The study introduces DES-YOLO, a novel real-time method for detecting castings' surface defects. In the DES-YOLO model, we incorporate the DSC-Darknet backbone network and global attention mechanism (GAM) module to enhance the identification of defect target features. These additions are essential for overcoming the challenge posed by the high similarity among defect characteristics, such as shrinkage holes and slag holes, which can result in decreased detection accuracy. An enhanced pyramid pooling module is also introduced to improve feature representation for small defective parts through multi-layer pooling. We integrate Slim-Neck and SIoU bounding box regression loss functions for real-time detection in actual production scenarios. These functions reduce memory overhead and enable real-time detection of surface defects in castings. Experimental findings demonstrate that the DES-YOLO model achieves a mean average precision (mAP) of 92.6% on the CSD-DET dataset and a single-image inference speed of 3.9 milliseconds. The proposed method proves capable of swiftly and accurately accomplishing real-time detection of surface defects in castings.

Surface defects of fiber-reinforced resin matrix composites (FRRMCs) adversely affect their appearance and performance. To accurately and efficiently detect the three-dimensional (3D) surface defects of FRRMCs, a novel lightweight and two-stage semantic segmentation network, i.e., Mask-Point, is proposed. Stage 1 of Mask-Point is the multi-head 3D region proposal extractors (RPEs), generating several 3D regions of interest (ROIs). Stage 2 is the 3D aggregation stage composed of the shared classifier, shared filter, and non-maximum suppression (NMS). The two stages work together to detect the surface defects. To evaluate the performance of Mask-Point, a new 3D surface defects dataset of FRRMCs containing about 120 million points is produced. Training and test experiments show that the accuracy and the mean intersection of union (mIoU) increase as the number of different 3D RPEs increases in Stage 1, but the inference speed becomes slower when the number of different 3D RPEs increases. The best accuracy, mIoU, and inference speed of the Mask-Point model could reach 0.9997, 0.9402, and 320,000 points/s, respectively. Moreover, comparison experiments also show that Mask-Point offers relatively the best segmentation performance compared with several other typical 3D semantic segmentation networks. The mIoU of Mask-Point is about 30% ahead of the sub-optimal 3D semantic segmentation network PointNet. In addition, a distributed surface defects detection system based on Mask-Point is developed. The system is applied to scan real FRRMC products and detect their surface defects, and it achieves the relatively best detection performance in competition with skilled human workers. The above experiments demonstrate that the proposed Mask-Point could accurately and efficiently detect 3D surface defects of FRRMCs, and the Mask-Point also provides a new potential solution for the 3D surface defects detection of other similar materials

Carbon fiber reinforced polymer (CFRP) has become an essential structural material in aerospace, new energy, rail transportation, and other fields due to its lightweight and high-strength properties. However, its complex manufacturing processes and demanding service environments can lead to various types of damage on both the surface and inside the material, significantly compromising safety. Existing detection techniques often adopt a step-by-step inspection mode, which results in complex processes and makes it difficult to achieve cross-dimensional correlation analysis of defects, leading to blind spots in structural health assessment. To address these issues, this paper proposes a method for simultaneous detection of surface and subsurface defects in CFRP based on infrared polarization imaging. First, we developed an infrared polarization imaging-based defect detection system and collected a CFRP defect dataset of samples containing various surface and subsurface defects. Then, we proposed a surface and subsurface defect detection network, which integrates extracted thermal diffusion features and polarization features to decouple and enhance surface and subsurface features. Through the constraints of multi-task defect detection, simultaneous detection of surface and subsurface defects is achieved. The experiments on the collected CFRP defect dataset demonstrate the effectiveness of the proposed method.

Particleboard surface defect detection technology is of great significance to the automation of particleboard detection, but the current detection technology has disadvantages such as low accuracy and poor real-time performance. Therefore, this paper proposes an improved lightweight detection method of You Only Live Once v5 (YOLOv5), namely PB-YOLOv5 (Particle Board-YOLOv5). Firstly, the gamma-ray transform method and the image difference method are combined to deal with the uneven illumination of the acquired images, so that the uneven illumination is well corrected. Secondly, Ghost Bottleneck lightweight deep convolution module is added to Backbone module and Neck module of YOLOv5 detection algorithm to reduce model volume. Thirdly, the SELayer module of attention mechanism is added into Backbone module. Finally, replace Conv in Neck module with depthwise convolution (DWConv) to compress network parameters. The experimental results show that the PB-YOLOv5 model proposed in this paper can accurately identify five types of defects on the particleboard surface: Bigshavings, SandLeakage, GlueSpot, Soft and OliPollution, and meet the real-time requirements. Specifically, recall, F1 score, mAP@.5, mAP@.5:.95 values of pB-Yolov5s model were 91.22%, 94.5%, 92.1%, 92.8% and 67.8%, respectively. The results of Soft defects were 92.8%, 97.9%, 95.3%, 99.0% and 81.7%, respectively. The detection of single image time of the model is only 0.031 s, and the weight size of the model is only 5.4 MB. Compared with the original YOLOv5s, YOLOv4, YOLOv3 and Faster RCNN, the PB-Yolov5s model has the fastest Detection of single image time. The Detection of single image time was accelerated by 34.0%, 55.1%, 64.4% and 87.9%, and the weight size of the model is compressed by 62.5%, 97.7%, 97.8% and 98.9%, respectively. The mAP value increased by 2.3%, 4.69%, 7.98% and 13.05%, respectively. The results show that the PB-YOLOV5 model proposed in this paper can realize the rapid and accurate detection of particleboard surface defects, and fully meet the requirements of lightweight embedded model.

Mechanical parts often have surface defects such as scratches, cracks and pits during the production process, which seriously affect product quality and service life. To address this challenge, this paper proposes a method for detecting and quantifying surface defects of mechanical parts based on image processing. First, this paper uses high-resolution image acquisition technology to obtain surface images of mechanical parts, and improves image quality through preprocessing steps. Then, this paper uses edge detection, morphological operations, and image segmentation algorithms to extract the features of surface defects, thereby realizing automatic identification of defective areas. Finally, this paper combines the Faster R-CNN (Faster Region-Based Convolutional Neural Network) algorithm to further refine the classification and quantification of defects and obtain the specific location, size and type of defects. Experimental results show that among the 500 mechanical parts samples tested, the proposed method has a mean average precision (mAP) of 0.93 in surface defect detection. Compared with other image processing methods, this method has significantly improved defect detection accuracy and speed. Especially when processing higher-resolution images, the Faster R-CNN model can achieve efficient defect classification and quantification to meet the needs of real-time detection in industrial production.

Aim at the problem of near surface blind area in ultrasonic TOFD technique, a new testing mode combined to ultrasound time of flight diffraction-reflection(TOFDR) and the three-fold reflected(TOFDW) based on secondary longitudinal waves was put forward. Through analysis the transmission characteristics of TOFDR and TOFDW, the two modes of the detection principle were illustrated, and discussed the ability in near surface detection of the two methods. Finally through the detecting artificial defects detection, the signal and image characteristics and detection sensitivity under the modified detection mode were studied. The artificial defect with buried depth of 1mm can be effectively detected from the D-scan image by the combined TOFDR and TOFDW methods.

Carbon fiber prepreg is the key material for preparing carbon fiber composites, and its surface defects directly affect the performance of composites. Existing supervised learning defect detection methods require predefined defect types and rely on a large number of defect labeled samples, making it difficult to adapt to the challenges of unknown defects due to changes in the production environment. An unsupervised anomaly detection method for surface defects of carbon fiber prepregs is developed and the corresponding carbon fiber prepreg surface anomaly detection model (CFP-AD) is constructed in this paper, which only needs to use merely non-defective images for training. Firstly, the various features taken from VGG19 are fed into the designed multi-branch dimensional cross-refinement feature fusion module, which enhances the representation ability of multi-scale convolutional feature. Secondly, a convolutional autoencoder with residual pooling is designed to efficiently realize feature reconstruction, improving the reconstruction ability of the CFP-AD model for the edges of carbon fiber prepregs. Lastly, a context semantic similarity measurement function is introduced based on the l 2 norm anomaly score measurement to make the CFP-AD model more effective in highlighting defective regions. Extensive experimental results indicate that the CFP-AD model is able to accurately identify the image anomaly and locate defective regions in carbon fiber prepregs.