Recently, there has been an increasing attempt to replace defect detection inspections in the manufacturing industry using deep learning techniques. However, obtaining substantial high-quality labeled data to enhance the performance of deep learning models entails economic and temporal constraints. As a solution for this problem, semi-supervised learning, using a limited amount of labeled data, has been gaining traction. This study assesses the effectiveness of semi-supervised learning in the defect detection process of manufacturing using the MixMatch algorithm. The MixMatch algorithm incorporates three dominant paradigms in the semi-supervised field: Consistency regularization, Entropy minimization, and Generic regularization. The performance of semi-supervised learning based on the MixMatch algorithm was compared with that of supervised learning using defect image data from the metal casting process. For the experiments, the ratio of labeled data was adjusted to 5%, 10%, 25%, and 50% of the total data. At a labeled data ratio of 5%, semi-supervised learning achieved a classification accuracy of 90.19%, outperforming supervised learning by approximately 22%p. At a 10% ratio, it surpassed supervised learning by around 8%p, achieving a 92.89% accuracy. These results demonstrate that semi-supervised learning can achieve significant outcomes even with a very limited amount of labeled data, suggesting its invaluable application in real-world research and industrial settings where labeled data is limited.

In factory automation, efforts are being made to increase productivity while maintaining high-quality products. In this study, a CNN network structure was designed to quickly and accurately recognize a cigarette located in the opposite direction or a cigarette with a loose end in an automated facility rotating at high speed for cigarette production. Tobacco inspection requires a simple network structure and fast processing time and performance. The proposed network has an excellent accuracy of 96.33% and a short processing time of 0.527 msec, showing excellent performance in learning time and performance compared to other CNN networks, confirming its practicality. In addition, it was confirmed that efficient learning is possible by increasing a small number of image data through a rotation conversion method.

This research proposes a novel approach to tackle the challenge of categorizing unstructured customer complaints in the automotive industry. The goal is to identify potential vehicle defects based on the findings of our algorithm, which can assist automakers in mitigating significant losses and reputational damage caused by mass claims. To achieve this goal, our model uses the Word2Vec method to analyze large volumes of unstructured customer complaint data from the National Highway Traffic Safety Administration (NHTSA). By developing a score dictionary for eight pre-selected criteria, our algorithm can efficiently categorize complaints and detect potential vehicle defects. By calculating the score of each complaint, our algorithm can identify patterns and correlations that can indicate potential defects in the vehicle. One of the key benefits of this approach is its ability to handle a large volume of unstructured data, which can be challenging for traditional methods. By using machine learning techniques, we can extract meaningful insights from customer complaints, which can help automakers prioritize and address potential defects before they become widespread issues. In conclusion, this research provides a promising approach to categorize unstructured customer complaints in the automotive industry and identify potential vehicle defects. By leveraging the power of machine learning, we can help automakers improve the quality of their products and enhance customer satisfaction. Further studies can build upon this approach to explore other potential applications and expand its scope to other industries.

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.

Recently, the development of computer vision with deep learning has made object detection using images applicable to diverse fields, such as medical care, manufacturing, and transportation. The manufacturing industry is saving time and money by applying computer vision technology to detect defects or issues that may occur during the manufacturing and inspection process. Annotations of collected images and their location information are required for computer vision technology. However, manually labeling large amounts of images is time-consuming, expensive, and can vary among workers, which may affect annotation quality and cause inaccurate performance. This paper proposes a process that can automatically collect annotations and location information for images using eXplainable AI, without manual annotation. If applied to the manufacturing industry, this process is thought to save the time and cost required for image annotation collection and collect relatively high-quality annotation information.

I propose an algorithm to detect defects in the production of wire mesh using computer image processing. The process is explained as follows, First reading consecutive frames coming through the camera, then the preprocessing process is performed. Second calculate the absolute difference between the two images to distinguish the moving wire mesh from the unnecessary background image. Third based on the past moving data of the welded wire mesh, predict and track future movement. As a result of observing the samples of some defective welded wire mesh products, it was confirmed that the horizontal line of the defective wire mesh had a higher height value of the tracked wire netting. Therefore it is possible to judge whether there is a defect or not at the same time without any additional process to judge. Finally, shear strength test were performed on the welds determined to be normal products by the algorithm proposed in this paper, so that I could verify the reliability and validity of the proposed algorithm.

Nondestructive testing is a method of inspecting particular target objects without destructing them in industrial sites. Infrared thermal imaging is one of the nondestructive testing techniques. Among them, lock-in infrared thermography technique is a technique to detect a defect by generating a temperature difference of an object using periodic heat waves. This paper deals with the development of lock-in infrared thermography technique by using numerical analysis model for SM45C metal specimens. As a result, the appropriate frequency was determined for defect detection in SM45C metal specimen by using the established thermal behavior mechanism by periodic heat wave.

A image defect detecting vision system for the automatic optical inspection of wafer has been developed. For the successful detection of various kinds of defects, the performance of two threshold selection methods are compared and the improved Otsu method is adopted so that it can handle both unimodal and bimodal distributions of the histogram equally well. An automatic defect detection software for practical use was developed with the function of detection of ROI, fast thresholding and area segmentation. Finally each defect pattern in the wafer is classified and grouped into one of user-defined defect categories and more than 14 test wafer samples are tested for the evaluation of detection and classification accuracy in the inspection system.

본 연구에서는 경계 요소법을 이용하여 2차원 비등방성 탄성체의 손상 규명을 수행한다. 경계에서의 적분항만을 포함하는 본 수치모델은 1차원으로 줄게된다. 이러한 장점은 특히 균열 역학과 같은 문제에 있어서 중요한 의미를 갖는다. 또한 일정 영역을 분할하는 기법을 피함으로서 수치해석 과정을 간편하고 효율적으로 수행할수 있기 때문에 역문제 해결에 있어서 장점을 갖는다. 본 연구에서는 기존의 등방성 재료에 대한 비파괴 추정기법을 복합신소재와 같은 비등방성 재료로 이루어진 탄성체의 해석에 대하여 확장한다. 먼저 경계요소법에 의한 수치모델의 타당성을 기존의 문헌과 비교 검증하며, 서로 다른 특성을 보이는 비등방성 형식의 변화에 따라 실제 측정시 발생하는 노이즈 영향을 분석한다. 수치예제는 적층 형태 및 하중조건에 대하여 수행하며, 결함 추정에 미치는 적층 형태의 영향을 시험한다.

This study presents numerical analysis of elastic waves for detecting damage in epoxy adhesive zone. For the finite element analysis, a finite element program ANSYS LS-Dyna is used. The result signals of finite element analysis were analyzed by using pitch-catch method. It is shown that the received time signals successfully show the existence of defects

현재 진동 정보를 통해 기계 설비의 상태나 고장 유무를 판단하는 연구들이 다수 진행 중에 있는데, 대부분의 연구에서는 설비에 대한 진동을 모니터링하거나 고장 유무를 판별하여 사용자에게 알리는 수준이다. 본 논문에서는 진동 정보 적용 대상을 선박으로 정하고, 진동에 의한 고장 진단과 판별을 보다 정교하게 수행하는 선박 엔진 감지 기법과 시스템을 제안하였다. 일차적으로 이중화된 진동 정보 판별 기법을 적용하여 진동 정보를 확인한 다음에 고장 유무를 검사한다. 만일 고장이 발생한 경우에는 적분을 이용하여 고장 진동 파형에 대한 넓이를 기준으로 어떤 유형의 고장인지를 판별할 수 있는 기법을 적용하였다. 또한 선박의 진동 경향 분석과 엔진 안전 보존을 목적으로 진동 정보를 데이터베이스에 저장하고 추적할 수 있도록 시스템을 구현하였다. 제안 시스템을 선박 엔진의 고장 판별 유무와 고장 진동 파형 감별 인자에 대해 실험을 수행한 결과 고장 판별은 약 98% 정확성을 가졌고 고장 진동 파형 감별에서는 약 72% 정확성을 가졌다.

결함검사는 생산공정에 있어서 상품의 디자인과 함께 매우 중요한 부분으로서, 상품의 경쟁력을 높이는데 필수 불가결한 것이다. 만약, 실시간 결함검출이 상품에 대한 어떤 손상도 없이 할 수 있다면, 품질 및 공정의 효율적 관리와 고비용 인력의 절감을 통하여 생산원가를 줄일 수 있다. 본 논문에서는 철판과 같은 표면에 결함이 있는 경우 필요한 정보만을 추출할 수 있는 3가지 공간필터법에 대하여 제안하였고, 공간필터의 특성을 통하여 결함검출 시스템을 구성하였다. 그리고, 최적의 표면결함 계측용 공간필터법을 개발하기 위하여 결함의 크기와 형태, 광도의 크기 및 외부 광간섭 그리고 슬리트의 개수와 같은 파라메타의 변화에 따른 측정 성능을 비교 및 분석하였다.

A quick and automatic detection with no harm to the goods is very important task for improving quality control, process control and labour reduction. In real fields of industry, defect detection is mostly accomplished by skillful workers. A narrow band eliminating spatial filter having characteristics of removing the specified spatial frequency is developed by the author, and it is proved that the filter has an excellent ability for on-line and real time detection of surface defect. By the way,. this spatial filter shows a ripple phenominum in filtering characteristics. So, it is necessary to remove the ripple component for the improvement of filter gain, moreover efficiency of defect detection. The spatial filtering method has a remarkable feature which means that it is able to set up weighting function for its own sake, and which can to obtain the best signal relating to the purpose of the measurement. Hence, having an eye on such feature, theoretical analysis is carried out at first for optimal design of narrow band eliminating spatial filter, and secondly, on the basis of above results spatial filter is manufactured, and finally advanced effectiveness of spatial filter is evaluated experimentally.