CNN 알고리즘을 이용한 인공지지체의 3D프린터 출력 시 실시간 출력 불량 탐지 시스템에 관한 연구

이송연,허용정,Lee, Song Yeon,Huh, Yong Jeong 한국반도체디스플레이기술학회 2021 반도체디스플레이기술학회지 Vol.20 No.3

Scaffold is used to produce bio sensor. Scaffold is required high dimensional accuracy. 3D printer is used to manufacture scaffold. 3D printer can't detect defect during printing. Defect detection is very important in scaffold printing. Real-time defect detection is very necessary on industry. In this paper, we proposed the method for real-time scaffold defect detection. Real-time defect detection model is produced using CNN(Convolution Neural Network) algorithm. Performance of the proposed model has been verified through evaluation. Real-time defect detection system are manufactured on hardware. Experiments were conducted to detect scaffold defects in real-time. As result of verification, the defect detection system detected scaffold defect well in real-time.

객체 탐지 기술을 통한 휠 너트 제품의 단조 공정에서 불량 검출

김창대,백승욱,정완진,이창환 한국정밀공학회 2024 한국정밀공학회지 Vol.41 No.4

This study developed a defect-detecting system for automotive wheel nuts. We proposed an image processing method using OpenCV for efficient defect-detection of automotive wheel nuts. Image processing method focused on noise removal, ratio adjustment, binarization, polar coordinate system formation, and orthogonal coordinate system conversion. Through data collection, preprocessing, object detection model training, and testing, we established a system capable of accurately classifying defects and tracking their positions. There are four defect types. Type 1 and type 2 defects are defects of products where the product is completely broken circumferentially. Type 3 and type 4 defects are defects are small circumferential dents and scratches in the product. We utilized Faster R-CNN and YOLOv8 models to detect defect types. By employing effective preprocessing and post-processing steps, we enhanced the accuracy. In the case of Fast RCNN, AP values were 0.92, 0.93, 0.76, and 0.49 for types 1, 2, 3, and 4 defects, respectively. The mAP was 0.77. In the case of YOLOv8, AP values were 0.78, 0.96, 0.8, and 0.51 for types for types 1, 2, 3, and 4 defects, respectively. The mAP was 0.76. These results could contribute to defect detection and quality improvement in the automotive manufacturing sector.

A study on defect detection in X-ray image castings based on unsupervised learning

이수환,서홍일,성주현,주양익,서동환 한국마린엔지니어링학회 2020 한국마린엔지니어링학회지 Vol.44 No.6

In this paper, we propose a deep-learning-based defect detection system for the non-destructive quality inspection of castings based on X-ray images. Our system comprises a defect classification network and a defect search network and achieves high classifi-cation performance with limited data by minimizing the overfitting for one type of object. The proposed defect classification network determines whether the acquired X-ray image is Defect by using a convolution neural network and outputs the defect probability through softmax. Compared to binarized defect classification or defect location tracking, this method of outputting the defect proba-bility does not require a separate reworking of the training dataset, because the data labeling is the same as the existing quality evalu-ation task. In addition, to detect the location of the defect causing the defect classification, our proposed defect search network estimates the region where the defect is likely to exist through a Grad-CAM based on the feature map of the classification network. The proposed network then determines the ROI around each peak of the estimated regions and detects the exact shape and location of the defect through boundary detection. It is, therefore, possible to minimize quality control costs through a precise quality analysis of each casting product by simultaneously detecting small defects that are easy to ignore because large defects are found in the image. To verify the validity of this study, an experiment was conducted by constructing a dataset of actual cast products, and the proposed detection model achieved an accuracy of 90%. In addition, by comparing the fully connected network and the SVM-based model, the model improved by about 20%, demonstrating that it is possible to detect defects without labeling defect locations.

FCDD 기반 웨이퍼 빈 맵 상의 결함패턴 탐지

장승준,배석주 한국산업경영시스템학회 2023 한국산업경영시스템학회지 Vol.46 No.2

To make semiconductor chips, a number of complex semiconductor manufacturing processes are required. Semiconductor chips that have undergone complex processes are subjected to EDS(Electrical Die Sorting) tests to check product quality, and a wafer bin map reflecting the information about the normal and defective chips is created. Defective chips found in the wafer bin map form various patterns, which are called defective patterns, and the defective patterns are a very important clue in determining the cause of defects in the process and design of semiconductors. Therefore, it is desired to automatically and quickly detect defective patterns in the field, and various methods have been proposed to detect defective patterns. Existing methods have considered simple, complex, and new defect patterns, but they had the disadvantage of being unable to provide field engineers the evidence of classification results through deep learning. It is necessary to supplement this and provide detailed information on the size, location, and patterns of the defects. In this paper, we propose an anomaly detection framework that can be explained through FCDD(Fully Convolutional Data Description) trained only with normal data to provide field engineers with details such as detection results of abnormal defect patterns, defect size, and location of defect patterns on wafer bin map. The results are analyzed using open dataset, providing prominent results of the proposed anomaly detection framework.

Identification and Detection of Surface Defects of Outer Package Printed Matter Based on Machine Vision

Shuo Wang,Jiangfeng Xu,Fangzhou Wang,Shenshen Ruan 한국펄프·종이공학회 2020 펄프.종이기술 Vol.52 No.2

In the printing process, the surface of the outer package printed matter is prone to defects such as chromatic aberration and misting, leading to a defective product. It is necessary to take an effective method to identify and detect surface defects in printed matter. In this paper, the application of machine vision technology in the detection of defects in outer package was studied. Firstly, a machine vision image acquisition device based on charge coupled device (CCD) camera was designed; secondly, the obtained image was processed by graying the average method, then OTSU binarization was performed after denoising by median filtering, and finally an improved differential matching method was designed for defect detection. The example analysis showed that the clear defect image of the outer package could be obtained by using the method proposed in this paper. The detection rate of the method in detecting 2,000 images reached 99.4%, and the average detection time was 103 ms. In the detection of 5,000 images, the detection rate of the manual detection method was 81%, but the detection rate of the method proposed in this paper was 99.1%. The experimental results proved the reliability of the method and provided some theoretical basis for the further application of defect detection technology based on machine vision in the print industry, which was conducive to the good development of the print industry.

병렬 구조의 다중 필터 CNN을 이용한 골절합용 판의 불량 탐지 모델에 관한 연구

이송연,허용정 한국정밀공학회 2023 한국정밀공학회지 Vol.40 No.9

Bone plates are a medical device used for fixing broken bones, which should not have a crack and hole defect. Defect detection is very important because bone plate defect is very dangerous. In this study, we proposed a defect detection model based on a parallel type convolution neural network for detecting bone plate crack and pore deformation. All size filters were different according to the defect shape. A convolution neural network detected pore defects. Another convolution neural network detected the crack. Two convolution neural networks simultaneously detected different defect types. The performance of the defect detection model was measured and used for the F1-score. We confirmed that performance of the defect detection model was 98.4%. We confirmed that the defect detection time was 0.21 seconds.

Defect Detection of Steel Wire Rope in Coal Mine Based on Improved YOLOv5 Deep Learning

Xiaolei Wang,Zhe Kan 한국정보처리학회 2023 Journal of information processing systems Vol.19 No.6

The wire rope is an indispensable production machinery in coal mines. It is the main force-bearing equipmentof the underground traction system. Accurate detection of wire rope defects and positions exerts an exceedinglycrucial role in safe production. The existing defect detection solutions exhibit some deficiencies pertaining tothe flexibility, accuracy and real-time performance of wire rope defect detection. To solve the aforementionedproblems, this study utilizes the camera to sample the wire rope before the well entry, and proposes an objectbased on YOLOv5. The surface small-defect detection model realizes the accurate detection of small defectsoutside the wire rope. The transfer learning method is also introduced to enhance the model accuracy of smallsample training. Herein, the enhanced YOLOv5 algorithm effectively enhances the accuracy of target detectionand solves the defect detection problem of wire rope utilized in mine, and somewhat avoids accidentsoccasioned by wire rope damage. After a large number of experiments, it is revealed that in the task of wirerope defect detection, the average correctness rate and the average accuracy rate of the model are significantlyenhanced with those before the modification, and that the detection speed can be maintained at a real-time level.

Vertical Scratch Detection Algorithm for High-speed Scale-covered Steel BIC(Bar in Coil)

Jong Pil Yun,Changhyun Park,Homoon Bae,Hwawon Hwang,Seho Choi 제어로봇시스템학회 2010 제어로봇시스템학회 국제학술대회 논문집 Vol.2010 No.10

Recently, vision-based inspection systems have been widely investigated for the defect inspection in various industrial products. This paper proposes a vision-based method for detection of scratches in the surfaces of scale-covered steel wire rods. Scales are formed on the surface of wire rods owing to the deposition of oxidized substances that are produces during manufacturing. Because of the variety in the types of steel, presence of scales, and manufacturing conditions, the features of wire rod surface images are not uniform. Moreover, the similarities in the gray-level and shape of the defect and defect-free regions make it very difficult to accurately detect defects. In order to solve the abovementioned problems and to detect defects more effectively, we propose a new defect detection algorithm, which is based on edge pair detection, binarization with double threshold, morphological operation, and SVM(Support Vector Machine). Finally, the experimental results conducted on steel wire rod images obtained from actual steel production lines show that the proposed algorithm is effective for defect detection of scale-covered steel wire rods.

Detection and Identification of Defects in Transparent Film

Bao-yuan Chen,Chao Zheng,Zhong-xiang Sun,Xiao-yang Yu 보안공학연구지원센터 2015 International Journal of Future Generation Communi Vol.8 No.4

Biaxially oriented polyester film (BOPET) defect is an important factor affecting the quality of the film. In view of identification of defects in the conventional film production process, this mathod resulted in the identification of defects inaccurate. and low labor efficiency and machine vision recognition on identification of specific defect. This paper presents a LVQ neural network-based BOPET film of defects detection and identification methods. In this algorithm, the film images were processed and the outlines of the membrane defects were obtained. Through extracting the aspect ration, circularity, complexity and elongation , projection histogram central moment and so on, the characteristic values of membrane defects, which from the image of film images after image processing, and then input to the defects recognition system based on LVQ neural network that had been trained, in order to achieve the film defects identification, classification and localization. Through the study of features of the defects in BOPET and extracted some quantities as character input of the LVQ neural network, then input some characteristic values as training value into the LVQ neural network to achieve the learning and prediction purpose, and the LVQ neural network was designed. The experiments show that, the proposed method can meet the requirements analysis of air defects in transparent film.

영상 처리를 이용한 슬라브 표면 검출 알고리즘 개발

전용주,최두철,윤종필,김상우 제어로봇시스템학회 2010 제어로봇시스템학회 국내학술대회 논문집 Vol.2010 No.5

This paper proposed an algorithm to detect defects such as bleeding defect in slab through the use of image processing. The surface of a slab is partially covered with scales composed of oxidized substance. Because these scales can be visually similar to defects, and because the surface features of slab images vary under different lighting conditions, defect detection can be difficult. To minimize the influence of scales and to improve the accuracy of detection, anew detection method is proposed. The bleeding defects are extracted by wavelet transform. Also, the morphological features are used fer defect detection of bleeding defects. Finally, the experimental results show the effectiveness of the proposed algorithm.