• Journal of the Semiconductor & Display Technology
• /
• v.21 no.4
• /
• pp.65-70
• /
• 2022

In manufacturing and semiconductor industries, transfer robots increase productivity through accurate and continuous work. Due to the nature of the semiconductor process, there are environments where humans cannot intervene to maintain internal temperature and humidity in a clean room. So, transport robots take responsibility over humans. In such an environment where the manpower of the process is cutting down, the lack of maintenance and management technology of the machine may adversely affect the production, and that's why it is necessary to develop a technology for the machine failure diagnosis system. Therefore, this paper tries to identify various causes of failure of transport robots that are widely used in semiconductor automation, and the Prognostics and Health Management (PHM) method is considered for determining and predicting the process of failures. The robot mainly fails in the driving unit due to long-term repetitive motion, and the core components of the driving unit are motors and gear reducer. A simulation drive unit was manufactured and tested around this component and then applied to 6-axis vertical multi-joint robots used in actual industrial sites. Vibration data was collected for each cause of failure of the robot, and then the collected data was processed through signal processing and frequency analysis. The processed data can determine the fault of the robot by utilizing machine learning algorithms such as SVM (Support Vector Machine) and KNN (K-Nearest Neighbor). As a result, the PHM environment was built based on machine learning algorithms using SVM and KNN, confirming that failure prediction was partially possible.

• Journal of the KSME
• /
• v.57 no.3
• /
• pp.38-41
• /
• 2017

이 글에서는 인공지능을 이용한 공학시스템 고장진단 및 예지기술(PHM: Prognostics and Health Management)의 개념을 소개하고, 실제 적용 사례를 제시한다.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2017.05a
• /
• pp.1127-1134
• /
• 2017

Gas turbine engine control was originated from a single hydro-mechanical governor for fuel metering and changed to 1970s' DEEC and then today's centralized FADEC. In order to attain the goal of improvement of control performance, application of PHM technology, and reduction of system weight, it is necessary to make a transition to distributed engine control. This paper describes the concept and roadmap of distributed control, collaborative efforts of government and industry for successful development of the system, and technical challenges for the system.

• Nuclear Engineering and Technology
• /
• v.52 no.10
• /
• pp.2262-2273
• /
• 2020

Digital twin technology can provide significant value for the prognostics and health management (PHM) of critical plant components by improving insight into system design and operating conditions. Digital twinning of systems can be utilized for anomaly detection, diagnosis and the estimation of the system's remaining useful life in order to optimize operations and maintenance processes in a nuclear plant. In this regard, a conceptual framework for the application of digital twin technology for the prognosis of Control Element Drive Mechanism (CEDM), and a data-driven approach to anomaly detection using coil current profile are presented in this study. Health management of plant components can capitalize on the data and signals that are already recorded as part of the monitored parameters of the plant's instrumentation and control systems. This work is focused on the development of machine learning algorithm and workflow for the analysis of the CEDM using the recorded coil current data. The workflow involves features extraction from the coil-current profile and consequently performing both clustering and classification algorithms. This approach provides an opportunity for health monitoring in support of condition-based predictive maintenance optimization and in the development of the CEDM digital twin model for improved plant safety and availability.

• Journal of the Korean Data and Information Science Society
• /
• v.15 no.2
• /
• pp.405-411
• /
• 2004

In the analysis of cancer data, it is important to make inferences of survival function and to assess the effects of covariates. Cox's proportional hazard model(PHM) and Beran's nonparametric method are generally used to estimate the survival function with covariates. We adjusted the incomplete survival time using the Buckley and James's(1979) pseudo random variables, and then proposed the estimator for the conditional survival function. Also, we carried out the simulation studies to compare the performances of the proposed method.

• Journal of The Institute of Information and Telecommunication Facilities Engineering
• /
• v.10 no.1
• /
• pp.1-6
• /
• 2011

The Underground pipeline facility is a general but most important facility in modern world, but its maintainability has been left behind. An automated and intelligent management technology is needed to prevent the wast of social resource and security. In this paper, we introduce Pipeline Health Monitoring(PHM) with Ubiquitous Sensor Network(USN) for inexpensive structure safety monitoring system, and improve its utility by inventing the advanced impedance converter.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.31 no.1
• /
• pp.63-69
• /
• 2018

Bearing is an essential component in many rotary machineries. To prevent its unpredicted failures and undesired downtime cost, many researches have been made in the field of Prognostics and Health Management(PHM), in which the key issue is to establish a proper feature reflecting its current health state properly at the early stage. However, conventional features have shown some limitations that make them less useful for early diagnostics and prognostics because it tends to increase abruptly at the end of life. This paper proposes a new feature extraction method using the envelope analysis and weighted sum with correlation coefficient. The developed method is demonstrated using the IMS bearing data given by NASA Ames Prognostics Data Repository. Results by the proposed feature are compared with those by conventional approach.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2009.05a
• /
• pp.271-275
• /
• 2009

본 연구에서는 상수관로의 잔존수명을 통계적 기법 중 하나인 비례위험모형(PHM)에 적용하여 평가하였다. 비례위험모형을 구축하기 위한 개별관로의 생존시간은 관로의 파손율이 한계파손율에 도달하는 시간으로 정의하였다. 즉, Park and Loganathan(2002)에서 제시한 GPBM을 적용하여 시간에 따른 개별관로의 파손율을 추정하고 추정된 파손율과 한계파손율의 상등관계를 통해 생존시간을 산정하였다. 또한, 본 연구대상관로에 대한 GPBM을 구축함에 있어, 매설시점에서 누적파손횟수를 0으로 한 파손기록을 입력자료에 추가하는 방법과 가중계수(WF)의 범위를 수정함으로써 기존의 GPBM을 보완하였다. 이로써 파손사건이 최소 1회 이상 기록된 강관 및 주철관에 대한 비례위험모형을 구축하였다. 이와 같이 수정된 방법론은 관로 파손사건 등의 자료의 축적이 미비한 국내 여건에서 비례위험모형 및 GPBM과 같은 통계적 모형을 구축할 때 유용할 것으로 사료된다. 본 연구대상관로의 비례위험모형에 포함된 유의한 공변수는 관종과 관경 그리고 길이이며 관종은 비례성 가정을 위배하여 시간종속형 변수로 모형화되었다. 최종 채택된 PHM모형을 통해 생존함수를 추정하였으며 추정된 생존함수를 이용하여 개별관로의 잔존수명 및 경제적 수명 그리고 각 수명에 대한 95% 신뢰구간을 산정하였다. 또한 개별관로의 경제적 수명에 영향을 미치는 공변수의 위험비율도 분석하였다. 분석결과 강관의 평균 경제적 수명은 약 25.1년이고 주철관은 약 21년으로 산정되었다. 또한 관종에 따른 경제적 수명에 도달할 상대적인 위험률은 전반적으로 주철관이 높으나 20년 이상 매설된 관로에서는 강관의 위험률이 높을 것으로 분석되었다. 관경과 길이는 크기에 비례하여 상대적 위험률도 증가하였다.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.4
• /
• pp.2061-2066
• /
• 2016

Purpose: To determine the significance of P57KIP2 immunohistochemistry expression in the histopathological diagnosis of hydatidiform mole. Materials and Methods: Hydatidiform mole patients at King Chulalongkorn Memorial Hospital between January 1999 and December 2011 were recruited. Two gynecologic pathologists reviewed histopathologic slides to confirm diagnosis. Formalin-fixed, paraffin-embedded tissue sections were stained using a bstandard immunostaining system with monoclonal antibodies against P57KIP2 protein. Correlations among pathological features, immunohistochemical expression and clinical data were analyzed. Results: One hundred and twenty-seven hydatidiform mole patients were enrolled. After consensus review, 97 cases were diagnosed as complet (CHM) and 30 cases as partial (PHM). Discordance between the first and final H&E diagnoses was found in 19 cases (14.9%, k= 0.578). Significant pathological features to classify the type of hydatidiform mole are central cisterns, trophoblastic proliferation, trophoblastic atypia, two populations of villi, fetal vessels and scalloped borders. After performing immunohistochemistry for P57KIP2, 107 cases were P57KIP2 negative and 20 cases positive. Discordant diagnoses between final H&E diagnosis and P57KIP2 immunohistochemistry was identified in 12 cases (9.4%). Sensitivity of final H&E diagnosis for CHM was 89.7%; specificity was 95.0%. PHM sensitivity and specificity of final H&E diagnosis was 95.0% and 89.7%, respectively. Conclusions: Histopathological diagnosis alone has certain limitations in accurately defining types of hydatidiform mole; P57KIP2 immunohistochemistry is practical and can be a useful adjunct to histopathology to distinguish CHM from non-CHM.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.18 no.9
• /
• pp.29-35
• /
• 2019

The structure of the machinery industry due to the 4th industrial revolution is changing from precision and durability to intelligent and smart machinery through sensing and interconnection(IoT). There is a growing need for research on prognostics and health management(PHM) that can prevent abnormalities in processing machines and accurately predict and diagnose conditions. PHM is a technology that monitors the condition of a mechanical system, diagnoses signs of failure, and predicts the remaining life of the object. In this study, the vibration generated during machining is measured and a classification algorithm for normal and fault signals is developed. Arbitrary fault signal is collected by changing the conditions of un stable supply cutting oil and fixing jig. The signal processing is performed to apply the measured signal to the learning model. The sampling rate is changed for high speed operation and performed machine learning using raw signal without FFT. The fault classification algorithm for 1D convolution neural network composed of 2 convolution layers is developed.