• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2005년도 춘계학술대회 논문집
• /
• pp.228-233
• /
• 2005

The damage of the pressure courage by degradation can become the reason of unexpected break down or failure accident and it is very important because safety accident, the production loss, environmental pollution, social problems are occur. Consequently The result to investigat of failure accident for domestic pressure vessel, the factor of degradation is SCC, Sorrosion, Cavity, Crack.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2015년도 제46회 하계학술대회
• /
• pp.1517-1518
• /
• 2015

The paper deals with the real time sensing of a chatter vibration in grinding machine line of automobile bearings using machine black box. The chatter vibration plays bad role in machining quality such as high roughness as well as tool life and machine failure. In this paper, the vibration signals of the automobile hub bearing in the grinding process are shown in the time domain and frequency domain. Through the vibrational signals, chatter vibration badness is detected using machine black box. Therefore, machine black box can be applied to the real time detection of the grinding process in engineering fields.

• 한국경영과학회지
• /
• 제3권2호
• /
• pp.91-93
• /
• 1978

A methodology which can be employed to obtain an optimal preventive maintenance policy that maximizes the total machine running time over the specified working period is proposed. A system considered is comprised of m machines and r

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권8호
• /
• pp.2016-2029
• /
• 2023

Accurate prediction of critical illness is significant for ensuring the lives and health of patients. The selection of indicators affects the real-time capability and accuracy of the prediction for critical illness. However, the diversity and complexity of these indicators make it difficult to find potential connections between them and critical illnesses. For the first time, this study proposes an indicator analysis model to extract key indicators from the preoperative and intraoperative clinical indicators and laboratory results of critical illnesses. In this study, preoperative and intraoperative data of heart failure and respiratory failure are used to verify the model. The proposed model processes the datum and extracts key indicators through four parts. To test the effectiveness of the proposed model, the key indicators are used to predict the two critical illnesses. The classifiers used in the prediction are light gradient boosting machine (LightGBM) and eXtreme Gradient Boosting (XGBoost). The predictive performance using key indicators is better than that using all indicators. In the prediction of heart failure, LightGBM and XGBoost have sensitivities of 0.889 and 0.892, and specificities of 0.939 and 0.937, respectively. For respiratory failure, LightGBM and XGBoost have sensitivities of 0.709 and 0.689, and specificity of 0.936 and 0.940, respectively. The proposed model can effectively analyze the correlation between indicators and postoperative critical illness. The analytical results make it possible to find the key indicators for postoperative critical illnesses. This model is meaningful to assist doctors in extracting key indicators in time and improving the reliability and efficiency of prediction.

• 융합정보논문지
• /
• 제7권1호
• /
• pp.55-60
• /
• 2017

사물인터넷 환경에서 인간의 개입 없는 지능화된 서비스를 위해서는 IoT 디바이스에서 생성되는 빅데이터로 부터 정상 패턴을 학습하고 이를 기반으로 불량, 오작동과 같은 이상 징후에 대해 예측하는 과정이 요구된다. 본 연구의 목적은 제품 공정의 다양한 기기에서 발생되는 빅데이터를 분석함으로써 제품 불량을 예측할 수 있는 기계 학습모델을 구현하는 것이다. 기계 학습 모델은 어느 정도 볼륨을 가진 기존 데이터를 기반으로 분석을 해야 하므로 빅데이터 분석도구 R을 사용하였으며, 제품 공정에서 수집된 데이터에는 제품에 대한 불량 여부가 포함되어 있으므로 지도 학습 모델을 활용하였다. 연구의 결과, 제품 불량에 영향을 주는 변수 및 변수 조건을 분류하였고, 의사결정 트리를 기반으로 제품의 불량 여부에 대한 예측 모델을 제시하였다. 또한, ROC Curve를 이용한 모델의 적합성 및 성능평가 분석에서 모델의 예측력은 상당히 높게 나타났다.

• 품질경영학회지
• /
• 제49권4호
• /
• pp.581-594
• /
• 2021

Purpose: The purpose of this study is to compare machine learning models for anomaly detection of mechanical facility equipment and suggest an anomaly detection system for mechanical facility equipment in subway stations. It helps to predict failures and plan the maintenance of facility. Ultimately it aims to improve the quality of facility equipment. Methods: The data collected from Daejeon Metropolitan Rapid Transit Corporation was used in this experiment. The experiment was performed using Python, Scikit-learn, tensorflow 2.0 for preprocessing and machine learning. Also it was conducted in two failure states of the equipment. We compared and analyzed five unsupervised machine learning models focused on model Long Short-Term Memory Variational Autoencoder(LSTM-VAE). Results: In both experiments, change in vibration and current data was observed when there is a defect. When the rotating body failure was happened, the magnitude of vibration has increased but current has decreased. In situation of axis alignment failure, both of vibration and current have increased. In addition, model LSTM-VAE showed superior accuracy than the other four base-line models. Conclusion: According to the results, model LSTM-VAE showed outstanding performance with more than 97% of accuracy in the experiments. Thus, the quality of mechanical facility equipment will be improved if the proposed anomaly detection system is established with this model used.

• 한국산업융합학회 논문집
• /
• 제25권6_2호
• /
• pp.1103-1110
• /
• 2022

The old machine tools that have been used for a long time cause both increase in defective rate and decrease in productivity compared to new machines due to wear and failure of their components. In order to improve productivity and quality of machined components through remanufacturing, it is necessary to analyze the wear and failure of major components of old machine tools. In this study, the process for reverse engineering is designed for the remanufacture of planner millers, which belong to a very large machine tool. Also, the suitability of the designed process is verified through the analysis of the selected remanufactured components. In the first step of the process, some major components of the aging planner miller are scanned using a 3D laser scanner. In the next step, reverse engineering is performed using the data obtained through 3D scanning. Finally, wear and failure analysis is performed by comparing the reverse engineering data with the scan data. As a result, this reverse design and wear analysis can complement the insufficient design database and reduce costs in the maintenance of remanufactured products.

• 반도체디스플레이기술학회지
• /
• 제22권4호
• /
• pp.113-118
• /
• 2023

Maintenance of semiconductor equipment processes is crucial for the continuous growth of the semiconductor market. The process must always be upheld in optimal condition to ensure a smooth supply of numerous parts. Additionally, it is imperative to monitor the status of the robots that play a central role in the process. Just as many senses of organs judge a person's body condition, robots also have numerous sensors that play a role, and like human joints, they can detect the condition first in the joints, which are the driving parts of the robot. Therefore, a normal state test bed and an abnormal state test bed using an aging reducer were constructed by simulating the joint, which is the driving part of the robot. Various sensors such as vibration, torque, encoder, and temperature were attached to accurately diagnose the robot's failure, and the test bed was built with an integrated system to collect and control data simultaneously in real-time. After configuring the user screen and building a database based on the collected data, the characteristic values of normal and abnormal data were analyzed, and machine learning was performed using the KNN (K-Nearest Neighbors) machine learning algorithm. This approach yielded an impressive 94% accuracy in failure diagnosis, underscoring the reliability of both the test bed and the data it produced.

• Applied Biological Chemistry
• /
• 제50권4호
• /
• pp.245-252
• /
• 2007

FTA(fault tree analysis)는 system 오류 관리를 위한 정성적/정량적 기법으로 적용되고 있다. FTA를 적용한 PCR의 오류 관리 system의 구축을 위한 시범적 단계로서 PCR 실행의 여러 단계 중 가장 간단한 단계인 '반응액의 제조 및 PCR 기기 사용 단계'를 모델로 하여 분석하였다. PCR 실행시 발생할 수 있는 오류를 연역적 논리 방식에 의해 fault tree의 형태로 규명하였다. Fault tree는 오류 관리의 최상위 요소인 top event를 중심으로 중간 계층을 이루는 intermediate events와 최하위의 요소인 basic events로 세분하여 구성하였다. Top event는 '반응액의 제조 및 PCR 기기 사용 단계에서의 오류'; 중간계층 events는 '기기 유래 오류', '실험행위 유래 오류'; basic events는 '정전상황', 'PCR 기기 선정', '기기 사용 관리', '기기 내구성', '조작의 오류', '시료 구분의 오류'로 분석되었다. 이로부터 top event의 원인 분석 및 중요 관리점을 도출하기 위하여 정성적/정량적 분석을 실시하였다. 정성적 기법으로 minimal cut sets, structural importance, common cause vulnerability를 분석하였고, 정량적 기법으로 simulation, cut set importance, item importance, sensitivity를 분석하였다. 정성적 분석과 정량적 분석의 결과에서 '시료 구분의 오류'와 '기기 조작의 오류'가 제 1중요관리점; '기기 관리의 오류'와 '내구성에 의한 오류'는 제 2중요관리점으로 일치되게 나타났다. 그러나 '정전상황'과 '기기 선정의 오류'는 정성적 분석에서만 중요관리점으로 분석되었다. 특히 sensitivity 분석에서 '기기 관리의 오류'는 사용 시간이 경과함에 따라 가장 중요한 관리점으로 부각되었다. 결론적으로 FTA는 PCR 모델 case에 대한 오류의 원인 분석 및 그 방지를 위한 중요관리점을 제시함에 따라, 궁극적으로 미래에 PCR의 오류 관리 system을 완성할 수 있는 효과적인 방법으로 사료된다.

• 한국공작기계학회논문집
• /
• 제10권2호
• /
• pp.79-88
• /
• 2001

This paper suggests to predict the failure of helical gear extrusion die. The basic assumption that constitutes the frame-work for any combined stress failure theory is that failure is predicted to occur when the maximum value of stress becomes equal to or exceeds the value of the same modulus that produces failure in a simple uniaxial stress test using the same material. The stresses which were calculated to each critical points are applied maximum normal stress theory and distor-tion energy theory. The theroretical analysis and experimental results for Samanta process and New process dies were com-pared.