• 제어로봇시스템학회논문지
• /
• 제22권4호
• /
• pp.247-252
• /
• 2016

In this paper, we propose a new defect detection technology for micro-defect on the surface of steel products. Due to depth and size of microscopic defect, slop of surface and vibration of strip, the conventional optical method cannot guarantee the detection performance. To solve the above-mentioned problems and increase signal to noise ratio, a novel retro-schlieren method that consists of retro reflector and knife edge is proposed. Moreover dual switching lighting method is also applied to distinguish uneven micro defects and surface noise. In proposed method, defective regions are represented by a black and white pattern. This pattern is detected by a defect detection algorithm with Gabor filter. Experimental results by simulator for sample defects of cold rolled steel show that the proposed method is effective.

• International Journal of Internet, Broadcasting and Communication
• /
• 제14권2호
• /
• pp.136-146
• /
• 2022

Some surface defects make the weak quality of steel materials. To limit these defects, we advocate a one-stage detector model RetinaNet among diverse detection algorithms in deep learning. There are several backbones in the RetinaNet model. We acknowledged two backbones, which are ResNet50 and VGG19. To validate our model, we compared and analyzed several traditional models, one-stage models like YOLO and SSD models and two-stage models like Faster-RCNN, EDDN, and Xception models, with simulations based on steel individual classes. We also performed the correlation of the time factor between one-stage and two-stage models. Comparative analysis shows that the proposed model achieves excellent results on the dataset of the Northeastern University surface defect detection dataset. We would like to work on different backbones to check the efficiency of the model for real world, increasing the datasets through augmentation and focus on improving our limitation.

• 대한임베디드공학회논문지
• /
• 제17권3호
• /
• pp.129-138
• /
• 2022

Collecting and labeling sufficient training data, which is essential to deep learning-based visual inspection, is difficult for manufacturers to perform because it is very expensive. This paper presents a steel plate surface defect detection system with industrial-grade detection performance by training a small amount of steel plate surface images consisting of labeled and non-labeled data. To overcome the problem of lack of training data, we propose two data augmentation techniques: program-based augmentation, which generates defect images in a geometric way, and generative model-based augmentation, which learns the distribution of labeled data. We also propose a 4-step semi-supervised learning using pseudo labels and consistency training with fixed-size augmentation in order to utilize unlabeled data for training. The proposed technique obtained about 99% defect detection performance for four defect types by using 100 real images including labeled and unlabeled data.

• 한국컴퓨터정보학회논문지
• /
• 제25권3호
• /
• pp.19-26
• /
• 2020

일반적으로 품질 관리는 많은 제조 공정, 특히 주조 또는 용접과 관련된 공정의 기본 구성 요소가 된다. 그러나 사람이 일일이 수동으로 품질 관리 절차를 하는 것은 종종 시간이 걸리고 오류가 발생하기 쉽다. 최근 고품질 제품에 대한 요구를 만족시키기 위해 지능형 육안 검사 시스템의 사용이 생산 라인에서 필수적이 되고 있다. 본 논문에서는 이를 위해 딥 러닝 기반의 ShuffleDefectNet 결함 감지 시스템을 제안하고자 한다. 제안된 결함 검출 시스템은 NEU 데이터 세트의 결함 검출에 대한 여러 최신 성능들보다 높은 평균 정확도 99.75% 정도를 얻는다. 이 논문에서 여러 다른 트레이닝 데이터로부터 최상의 성능을 탐지하고 탐지 성능을 관찰하였다. 그 결과 ShuffleDefectNet의 전체 아키텍처를 사용할 때 정확성과 속도가 크게 향상됨을 알 수 있었다.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2008년도 추계학술대회A
• /
• pp.317-321
• /
• 2008

Piping in the Nuclear Power plants (NPP) are mostly consisted of carbon steel pipe. The wall thinning defect is mainly occurred by the affect of the flow accelerated corrosion (FAC) of fluid which flows in carbon steel pipes. This type of defect becomes the cause of damage or destruction of piping. Therefore, it is very important to measure defect which is existed not only on the welding partbut also on the whole field of pipe. Over the years, Infrared thermography (IRT) has been used as a non destructive testing methods of the various kinds of materials. This technique has many merits and applied to the industrial field but has limitation to the materials. Therefore, this method was combined with lock-in technique. So IRT detection resolution has been progressively improved using lock-in technique. In this paper, the quantitative analysis results of the location and the size of wall thinning defect that is artificially processed inside the carbon steel pipe by using IRT are obtained.

• Steel and Composite Structures
• /
• 제19권1호
• /
• pp.131-152
• /
• 2015

Easy detection and evaluation of defect in the tube structure is a continuous problem and remains a significant demand in tube inspection technologies. This study is aimed to automate defect detection using the pattern recognition approach based on the classification of high frequency stress wave signals. The stress wave signals from vibrational impact excitation on several tube conditions were captured to identify the defect in ASTM A179 seamless steel tubes. The variation in stress wave propagation was captured by a high frequency sensor. Stress wave signals from four tubes with artificial defects of different depths and one reference tube were classified using the autoregressive (AR) algorithm. The results were demonstrated using a dendrogram. The preliminary research revealed the natural arrangement of stress wave signals were grouped into two clusters. The stress wave signals from the healthy tube were grouped together in one cluster and the signals from the defective tubes were classified in another cluster. This approach was effective in separating different stress wave signals and allowed quicker and easier defect identification and interpretation in steel tubes.

• 비파괴검사학회지
• /
• 제23권3호
• /
• pp.270-279
• /
• 2003

Parametric studies have been conducted into the variability of the factors affecting the ultrasonic testing applied to weldments. The influence of ultrasonic equipment, transducer parameters, test technique, job parameters, defect type and characteristics on reliability far defect detection and sizing was investigated by experimentation. The investigation was able to build up substantial bank of information on the reliability of manual ultrasonic method for testing weldments. The major findings of the study separate into two parts, one dealing with correlation between ultrasonic techniques, equipment and defect parameters and inspection performance effectiveness and other with human factors. Defect detection abilities are dependent on the training, experience and proficiency of the UT operators, the equipment used, the effectiveness of procedures and techniques.

• Journal of Information Processing Systems
• /
• 제19권6호
• /
• pp.745-755
• /
• 2023

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

• 한국전자통신학회논문지
• /
• 제17권4호
• /
• pp.577-586
• /
• 2022

철강 표면 결함의 검출 및 분류는 철강 산업의 제품 품질 관리에 중요하다. 그러나 정확도가 낮고 속도가 느리기 때문에 기존 방식은 생산 라인에서 효과적으로 사용할 수 없다. 현재 널리 사용되는 알고리즘(딥러닝 기반)은 정확도 문제가 있으며 아직 개발의 여지가 있다. 본 논문에서는 이미지 분류를 위한 EfficientNetV2와 물체 검출기로 YOLOv5를 결합한 강철 표면 결함 검출 방법을 제안한다. 이 모델의 장점은 훈련 시간이 짧고 정확도가 높다는 것이다. 먼저 EfficientNetV2 모델에 입력되는 이미지는 결함 클래스를 분류하고 결함이 있을 확률을 예측한다. 결함이 있을 확률이 0.3보다 작으면 알고리즘은 결함이 없는 샘플로 인식한다. 그렇지 않으면 샘플이 YOLOv5에 추가로 입력되어 금속 표면의 결함 감지 프로세스를 수행한다. 실험에 따르면 제안된 모델은 NEU 데이터 세트에서 98.3%의 정확도로 우수한 성능을 보였고, 동시에 평균 훈련 속도는 다른 모델보다 단축된 것으로 나타났다.

• Journal of Welding and Joining
• /
• 제16권3호
• /
• pp.64-73
• /
• 1998

This paper is concerned with defects detection and evaluation of heat affected zone (HAZ) in austenitic stainless steel type 304 by ultrasonic wave and neural network. In experiment, the reflected ultrasonic defect signals from artificial defects (side hole, vertical hole, notch) of HAZ appears as beam distance of prove-defect, distance of probe-surface, depth of defect-surface on CRT. For defect classification simulation, neural network system was organized using total results of ultrasonic experiment. The organized neural network system was learned with the accuracy of 99%. Also it could be classified with the accuracy of 80% in side hole, and 100% in vertical hole, 90% in notch about ultrasonic pattern recognition. Simulation results of neural network agree fairly well with results of ultrasonic experiment. Thus were think that the constructed system (ultrasonic wave - neural network) in this work is useful for defects dection and classification such as holes and notches in HAZ of austenitic stainless steel 304.