• Journal of the Korean Society of Safety
• /
• v.15 no.2
• /
• pp.1-7
• /
• 2000

This paper presents the approach involving fault detection and diagnosis of gears using pattern recognition and Wavelet transform. It describes result of the comparison between KDI (Kullback Discrimination Information) with the nearest neighbor classification rule as one of pattern recognition methods and Wavelet transform to know a way to detect and diagnosis of gear damages experimentally. To model the damages 1) Normal (no defect), 2) one tooth is worn out, 3) All teeth faces are worn out 4) One tooth is broken. The vibration sensor was attached on the bearing housing. This produced the total time history data that is 20 pieces of each condition. We chose the standard data and measure distance between standard and tested data. In Wavelet transform analysis method, the time series data of magnitude in specified frequency (rotary and mesh frequency) were earned. As a result, the monitoring system using Wavelet transform method and KDI with nearest neighbor classification rule successfully detected and classified the damages from the experimental data.

• Information Systems Review
• /
• v.8 no.1
• /
• pp.159-179
• /
• 2006

With the advances in information technologies and the wide acceptance of IT outsourcing practices, subscription-based information & telecommunications services(ITS) become more available. Convergence and intensified industry competition have made it an imperative for the ITS providers to keep their current customers and acquire new customers at the same time. In this study, we developed a framework for effective customer management based on the factors influencing the post-purchase customer choice: stay with the present provider or switch to another one. Specifically, we classified the factors into four categories: Holding factors, Defect factors, Inducement factors, and Hurdle factors depending on the characteristics of the influence and direction of the influence. Based on the classification, we developed a post-purchase customer choice model for the subscription-based ITS providers. Then, we illustrated a possible application of the model in the context of the broadband Internet access service. The model could be used to increase the competitive advantage of service providers through the effective customer management in the subscription-based ITS market.

• Journal of the Korea Convergence Society
• /
• v.13 no.2
• /
• pp.249-255
• /
• 2022

This study proposed an analysis framework for real-time prediction of CNC processing defects using machine learning-based models that are recently attracting attention as processing defect prediction methods, and applied it to CNC machines. Analysis shows that the XGBoost, CatBoost, and LightGBM models have the same best accuracy, precision, recall, F1 score, and AUC, of which the LightGBM model took the shortest execution time. This short run time has practical advantages such as reducing actual system deployment costs, reducing the probability of CNC machine damage due to rapid prediction of defects, and increasing overall CNC machine utilization, confirming that the LightGBM model is the most effective machine learning model for CNC machines with only basic sensors installed. In addition, it was confirmed that classification performance was maximized when an ensemble model consisting of LightGBM, ExtraTrees, k-Nearest Neighbors, and logistic regression models was applied in situations where there are no restrictions on execution time and computing power.

• Journal of Korea Water Resources Association
• /
• v.55 no.spc1
• /
• pp.1177-1185
• /
• 2022

The water and sewage system is an infrastructure that provides safe and clean water to people. In particular, since the water and sewage pipelines are buried underground, it is very difficult to detect system defects. For this reason, the diagnosis of pipelines is limited to post-defect detection, such as system diagnosis based on the images taken after taking pictures and videos with cameras and drones inside the pipelines. Therefore, real-time detection technology of pipelines is required. Recently, pipeline diagnosis technology using advanced equipment and artificial intelligence techniques is being developed, but AI-based defect detection technology requires a variety of learning data because the types and numbers of defect data affect the detection performance. Therefore, in this study, various defect scenarios are implemented using 3D printing model to improve the detection performance when detecting defects in pipelines. Afterwards, the collected images are performed to pre-processing such as classification according to the degree of risk and labeling of objects, and real-time defect detection is performed. The proposed technique can provide real-time feedback in the pipeline defect detection process, and it would be minimizing the possibility of missing diagnoses and improve the existing water and sewerage pipe diagnosis processing capability.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.16 no.2
• /
• pp.236-250
• /
• 2016

Electrical Designs for Application Specific Integrated Circuits (ASIC) has undergone a change recently with the advent of the sub-wavelength lithography. The optical projection with 193 nm wavelength has been further extended with the use of immersion and other techniques. The competing trends for printing smaller design features have been discussed in this paper with the discussion of the electrical layout analysis to find unfriendly design features. The early knowledge of the unfriendly design features allows remedial actions in time for better yield on the wafer. There are existing standard design qualification criteria being used in the design and fabrication community, but they seem to be insufficient to guarantee defect free designs. This paper proposes an integrated approach for screening the layout with multiple aspects: layout geometry based, graphical analysis and process model based verification. The results have been discussed with few example design features from the 28nm design layout.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.5
• /
• pp.669-674
• /
• 2018

Data augmentation is an efficient way to reduce overfitting on models and to improve a performance supplementing extra data for training. It is more important in deep learning based industrial machine vision. Because deep learning requires huge scale of learning data to learn a model, but acquisition of data can be limited in most of industrial applications. A very generic method for augmenting image data is to perform geometric transformations, such as cropping, rotating, translating and adjusting brightness of the image. The effectiveness of data augmentation in image classification has been reported, but it is rare in defect inspections. We explore and compare various basic augmenting operations for the metal surface defects. The experiments were executed for various types of defects and different CNN networks and analysed for performance improvements by the data augmentations.

• Childhood Kidney Diseases
• /
• v.14 no.2
• /
• pp.120-131
• /
• 2010

Renal tubular acidosis (RTA) is a metabolic acidosis due to impaired excretion of hydrogen ion, or reabsorption of bicarbonate, or both by the kidney. These renal tubular abnormalities can occur as an inherited disease or can result from other disorders or toxins that affect the renal tubules. Disorders of bicarbonate reclamation by the proximal tubule are classified as proximal RTA, whereas disorders resulting from a primary defect in distal tubular net hydrogen secretion or from a reduced buffer trapping in the tubular lumen are called distal RTA. Hyperkalemic RTA may occur as a result of aldosterone deficiency or tubular insensitivity to its effects. The clinical classification of renal tubular acidosis has been correlated with our current physiological model of how the nephron excretes acid, and this has facilitated genetic studies that have identified mutations in several genes encoding acid and base ion transporters. Growth retardation is a consistent feature of RTA in infants. Identification and correction of acidosis are important in preventing symptoms and guide approved genetic counseling and testing.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.459-462
• /
• 2021

본 연구는 반도체 제조 공정중 발생하는 센서 데이터를 활용하여 딥러닝기반으로 불량을 예측하는 모델을 제안한다. 반도체 공장에서는 FDC((Fault Detection and Classification)라는 불량을 예측하는 시스템이 있지만, 공정의 복잡도가 높고 센서의 종류가 많아 공정 관리자가 모든 센서의 기준을 설정 및 관리하는데 한계가 있다. 이를 해결하기 위해 공정 설비의 센서 데이터를 딥러닝을 활용하여 학습시켜 센서 기준정보로 임계치를 제공하고, 가공중 발생하는 센서 데이터가 입력되면 정상 여부를 판정하는 모델을 제안한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.1-2
• /
• 2023

본 연구는 환경 요인이 통제되어 있는 실험실 데이터에 산업 현장에서 발생하는 유사 잡음을 노이즈로 추가하였을 때, SNR비에 따른 노이즈별 STFT Log Spectrogram, Mel-Spectrogram, CWT Spectrogram 총 3가지의 이미지를 생성하고, 각 이미지를 입력으로 한 CNN 결함 분류 모델의 성능 결과를 확인하였다. 원본 데이터의 영향력이 큰 0db 이상의 SNR비로 합성할 경우 원본 데이터와 분류 결과상 큰 차이가 존재하지 않았으며, 노이즈 데이터의 영향이 큰 0db 이하의 SNR비로 합성할 경우, -20db의 STFT 이미지 기준 약 26%의 성능 저하가 발생하였다. 또한, Wiener Filtering을 통한 디노이징 처리 이후, 노이즈를 효과적으로 제거하여 분류 성능의 결과가 높아지는 점을 확인하였다.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.7
• /
• pp.299-306
• /
• 2022

In recent, sensors embedded in robots, equipment, and circuits have become common, and research for diagnosing device failures by learning measured sensor data is being actively conducted. This failure diagnosis study is divided into a classification model for predicting failure situations or types and a regression model for numerically predicting failure conditions. In the case of a classification model, it simply checks the presence or absence of a failure or defect (Class), whereas a regression model has a higher learning difficulty because it has to predict one value among countless numbers. So, the reason that regression modeling is more difficult is that there are many irregular situations in which it is difficult to determine one output from a similar input when predicting by matching input and output. Therefore, in this paper, we focus on input and output data with periodicity, analyze the input/output relationship, and secure regularity between input and output data by performing sliding window-based input data patterning. In order to apply the proposed method, in this study, current and temperature data with periodicity were collected from MMC(Modular Multilevel Converter) circuit system and learning was carried out using ANN. As a result of the experiment, it was confirmed that when a window of 2% or more of one cycle was applied, performance of 97% or more of fit could be secured.