SiCショットキーダイオードの特性と欠陥の関係

When using visual image technology to detect surface defects of sealing rings for aerospace, traditional image processing algorithms are constrained by surface defects types, scale differences, illumination variations, and non-uniformities of surface image. As a result, the application of each algorithm is relatively limited. To solve the problems, a general deep learning algorithm for surface defects detection of sealing rings is proposed. Texture features of defects, gradient features of edges and contour features are selected as main features of surface defects of sealing rings differentiated from the background, and a new cascade modular backbone network is design for extraction of these features. The average aspect ratio of label box for defects among dataset of defect images of sealing rings is calculated and aspect ratio distribution is counted to obtain the proportional parameter for generating prior box. Based on the calculated proportional parameters of prior box and scale features of defects, multi-scale defects detection network is designed. Meanwhile, defects classification and position regression compound loss function are defined. In the end, weighting parameters of the network are updated on the basis of end-to-end training. Experimental result shows that the accuracy of proposed algorithm for defects detection reach 94.03% under the condition that the original defects sample images is 107 and confidence is 0.6. Compared with RefineDet network, the depth of backbone network of feature extraction increases by 78% while the scale of parameters reduces by 84.82% and the accuracy of defects detection reduces by 3.01%.

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.

Characterization of surface defects after flanging of metallic sheets

Influences of Te-rich and Cd-rich precipitates of CdZnTe substrates on the surface defects of HgCdTe epilayers grown by Te-rich liquid-phase epitaxy were investigated. The results show that HgCdTe surface defects are mainly attributable to precipitates on CdZnTe substrate surfaces. At the same time, the remelting of substrate surface layers during the liquid-phase epitaxial process also affects the number and morphology of HgCdTe surface defects. According to the morphological characteristics of surface defects, three types of surface defects were observed on the surfaces of HgCdTe epilayers. There are no obvious differences in the morphologies of the surface defects grown on Te-rich and Cd-rich substrates. However, the dislocation distributions around surface defects are different for HgCdTe epilayers grown on different substrates.

Ultrasonic non-destructive inspection is today widely employed in industry for detecting embedded or surface defects in engineering structures. However, the processing of data from ultrasonic inspection is rarely automated. The objective of our study is to develop a data processing system which makes use of image processing techniques in order to assist the ultrasonic inspection operator in his difficult task. The research work described has thus been done with this objective in mind and it concerns a method that we have developed for the automatic detection and characterization of defects. This method is based on the Hough transform and it allows one to localize defects in the component under inspection. By an automatic analysis of the "ultrasonic" data. The defects that are considered are tiny cracks in thick metallic structures.

The quality of smooth technical surfaces is characterized by the surface roughness and by surface defects. For a stable quality control, objective measuring conditions are necessary. The objective measurement of surface defects especially is an unsolved problem. For the investigation of the scattering characteristics of different surface defects, a measuring device was developed. With this measuring device, the type of defect and the angle dependent scattering intensity were measured and compared with theoretical calculations.

Cascaded detection method for surface defects of lead frame based on high-resolution detection images

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.

Online detection of surface defects on automotive oil seal rings has become a critical process for improving their production efficiency. To address the problems of inaccurate feature representation and low detection efficiency for small defects in oil seal ring surface inspection, this study proposes an enhanced defect detection method, YOLO11-DCB, based on the YOLO11n architecture. First, a dynamic upsampling module is embedded into the backbone network to enhance spatial feature transformation and strengthen the model’s ability to perceive various defect characteristics. Second, the local window multi-head attention module (C2CGA) is improved to alleviate the information loss caused by spatial pyramid pooling, while reducing computational complexity and guiding the network to focus on key features. Third, a weighted bidirectional feature fusion network is developed by integrating the design principles of BiFPN into the neck of YOLO11, which enables simple and efficient multi-scale feature representation and cross-scale information interaction. Finally, the detection head is improved by designing a module-aided detection head module (DetectAux), which enhances the supervision signal during the training phase, reduces the number of parameters via depthwise separable convolution, and outputs the prediction information for various categories. Ablation experiments were conducted on the self-constructed dataset, and the results reveal that compared with the YOLO11n algorithm, the modified model increases the Mean Average Precision at an Intersection over Union (IoU) threshold of 0.5 (mAP@0.5) by 6.8%, the recall by 4.7%, and the precision by 15.8%. Compared with mainstream detection algorithms, the results demonstrate that the proposed model outperforms Fast R-CNN, YOLOv8n, RT-DETR, and MobileViT-v2 by 26.2%, 4.6%, 0.2%, and 8.3% in terms of mAP@0.5, respectively. In addition, it exhibits distinct advantages in parameter count, real-time performance and model size, which further verifies the effectiveness and superiority of the proposed online detection algorithm for oil seal ring surface defects in industrial scenarios.

Research on rapid detection of cross-scale defects in surface based on deep learning

A nondestructive testing method for detecting surface defects of Si3N4-Bearing cylindrical rollers based on an optimized convolutional neural network

Automatic classification of apples is an important application of machine vision technology in agricultural product detection. In this paper, we study apple grading method based on features of color and defect. First, the captured RGB-based apple images are transformed into HIS model. Then, the segmentation between fruit and background is realized via the Oust algorithm for the H values of the image, and the color feature is extracted by the appropriate range of H values. In addition, the Canny edge detection algorithm with hysteresis threshold is employed to extract the edge information of defect area from I values of fruit image, then the defect area is segmented by morphological operation. Finally, serving as input, the characteristic quantities of apple color and surface defect are sent into the SVM model based on particle swarm optimization. The experiment results indicate that accuracy rate can reach to 91%.

Electroplated thin-walled tubes were tested in compression. Most cracks were found at defects, i. e. protrusions on the surface of the tubes. The study focusses on the characterization of these defects. Optical microscopy revealed that the defects were already present in the metallization layer and occurred during the metallization process. When electrodepositing a Nickel coating on top, grains grow perpendicular to the surface of the metallization layer creating local orientation changes. Thus, protrusions occur on the surface of the tube where imperfections are located in the metallization layer. The results will be valuable for improving the deformation characteristics of the electrodeposited tubes; they can also be used to design new types of electrodeposits by patterning the substrate.

It is believed that surface and subsurface defects formed during standard grinding and polishing processes are mainly responsible for laser induced damage in fused silica. The correlation between the laser damage susceptibility and absorption property of these defects has not been totally understood. In this paper, we present the characterization of surface and subsurface defects of fused silica by measuring their absorption properties based on a photothermal technique at 355 nm. The photothermal microscopic imaging reveals that the surface/subsurface absorption defects in fused silica can be identified. In addition, a 3D photothermal imaging of a laser damage site on the silica is also obtained. Our results demonstrate that photothermal microscopy is a powerful tool for defect characterization of optical materials for high power laser applications.

Defect characterization in Al welded joints by non-contact Lamb wave technique