• Communications for Statistical Applications and Methods
• /
• 제24권1호
• /
• pp.43-65
• /
• 2017

We propose a flexible cure rate survival model by assuming that the number of competing causes of the event of interest has the Poisson distribution and the time for the event follows the gamma-G family of distributions. The extended family of gamma-G failure-time models with long-term survivors is flexible enough to include many commonly used failure-time distributions as special cases. We consider a frequentist analysis for parameter estimation and derive appropriate matrices to assess local influence on the parameters. Further, various simulations are performed for different parameter settings, sample sizes and censoring percentages. We illustrate the performance of the proposed regression model by means of a data set from the medical area (gastric cancer).

• 한국기계가공학회지
• /
• 제19권11호
• /
• pp.94-101
• /
• 2020

In the age of industry 4.0, artificial intelligence is being widely used to realize machinery condition monitoring. Due to their excellent performance and the ability to handle large volumes of data, machine learning techniques have been applied to realize the fault diagnosis of different equipment. In this study, we performed the failure mode effect analysis (FMEA) of an aluminum electrolytic capacitor by using deep learning and big data. Several tests were performed to identify the main failure mode of the aluminum electrolytic capacitor, and it was noted that the capacitance reduced significantly over time due to overheating. To reflect the capacitance degradation behavior over time, we employed the Vanilla long short-term memory (LSTM) neural network architecture. The LSTM neural network has been demonstrated to achieve excellent long-term predictions. The prediction results and metrics of the LSTM and Vanilla LSTM models were examined and compared. The Vanilla LSTM outperformed the conventional LSTM in terms of the computational resources and time required to predict the capacitance degradation.

• 터널과지하공간
• /
• 제27권3호
• /
• pp.121-131
• /
• 2017

본 연구에서는 암석과 콘크리트의 정적 및 동적 장기강도시험을 통해 이들 재료의 시간 의존적 거동에 대해 연구했으며, 특히 장기강도시험 중 발생한 미소파괴음 신호를 분석하여 장기 안정성 평가에 활용하고자 하였다. 정적 장기강도시험의 경우 임계하 균열성장시험을 활용하여 Mode I과 Mode II에 대한 장기거동과 미소파괴음 발생특성을 분석하였으며, 동적 장기강도시험의 경우, 반복재하 4점 굴곡시험을 통한 장기강도의 한계와 미소파괴음 발생특성을 분석하였다. 미소파괴음 분석결과, 미소파괴음 히트 누적곡선 대 시간에 따른 곡선은 1차, 2차, 3차 구간이 있는 크립곡선의 모양과 유사한 모양을 보였다. 선형구간에 해당하는 미소파괴음 히트 누적곡선의 2차 구간의 기울기와 지연파괴시간과의 로그-로그 관계로부터 암석과 콘크리트의 정적 및 동적 장기 안정성을 평가하는 방안에 대한 가능성을 제시하였다.

• 한국지반환경공학회 논문집
• /
• 제23권12호
• /
• pp.25-31
• /
• 2022

해양지반에 설치된 구조물은 육상지반에 설치된 구조물과는 달리 해상에서의 파하중, 풍하중, 그리고 조류하중 등과 같은 장기 반복하중을 고려해야 된다. 이에 해양지반에 설치된 구조물을 설계하기 위해서는 장기 반복하중을 받는 지반의 거동을 분석하는 것이 중요하다. 본 논문에서는 반복단순전단시험을 수행하여 구속압에 따른 장기반복하중에 대한 지반거동을 분석하고, 구속압에 따른 파괴특성을 쉽게 확인할 수 있는 3차원 설계파괴곡선을 작성하였다. 분석결과, 동일한 반복전단응력비와 평균전단응력비 조건이어도 구속압에 따라 설계파괴곡선의 위치가 차이가 있었으며, 파괴에 도달하는 반복하중횟수가 구속압에 영향을 받는 것을 확인하였다. 작성한 구속압에 따른 3차원 설계파괴곡선은 구속압에 따른 설계파괴곡선의 경향성과 대략적인 값을 추정할 수 있다.

• 대한조선학회논문집
• /
• 제57권1호
• /
• pp.1-7
• /
• 2020

In general, an inspection schedule is established based on the long-term fatigue life during the design stage. However, in the design stage, it is difficult to clearly identify the uncertainty factors affecting long-term fatigue life. In this study, the probabilistic fatigue life assessment was conducted in accordance with the methodology of DNV-GL. Firstly, The initial crack distribution estimated through the initial crack propagation analysis was updated by reflecting the results of crack inspection. Secondly, the updated crack distribution was compared with the initial crack distribution, and the probability of failure was updated with the effect of crack inspection.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2008년도 추계학술대회A
• /
• pp.1391-1393
• /
• 2008

In this paper, the long-term reliability for 1.25G transceiver in use of high speed optical access network is investigated. High temperature storage tests and accelerated life tests are used to long-term reliability. Accelerated aging test have been during 3,000 hour of the three accelerated aging conditions by caused high temperature stress. Mean life is assumed to follow the Arrhenius relationship and analysis from the failure data obtained in the accelerated aging conditions.

• 한국기계가공학회지
• /
• 제20권12호
• /
• pp.85-91
• /
• 2021

In our daily life, artificial intelligence performs simple and complicated tasks like us, including operating mobile phones and working at homes and workplaces. Artificial intelligence is used in industrial technology for diagnosing various types of equipment using the machine learning technology. This study presents a fault mode effect analysis (FMEA) of start motors using machine learning and big data. Through multiple data collection, we observed that the primary failure of the start motor was caused by the melting of the magnetic switch inside the start motor causing it to fail. Long-short-term memory (LSTM) was used to diagnose the condition of the magnetic locations, and synthetic data were generated using the synthetic minority oversampling technique (SMOTE). This technique has the advantage of increasing the data accuracy. LSTM can also predict a start motor failure.

• 한국가스학회지
• /
• 제27권2호
• /
• pp.71-78
• /
• 2023

일반적으로 평균 수명이 1.0~1.5년인 전기식 액중형 펌프(electrical submersible pump, ESP)는 유·가스 및 저류층 특성, 운영 조건에 따라 성능 저하 및 수명 감소가 발생하며, 이에 따른 ESP의 고장은 회수 및 설치에 따른 높은 유정 개·보수(workover) 비용과 생산 중단에 따른 추가 비용이 발생한다. 이에 본 연구에서는 유·가스정에서 ESP 장기 운영에 따른 수명을 예측하고자 환형 유동 시스템(flow loop system)을 설계 및 구축하고, ESP 설치 초기 시점부터 고장 시점까지의 ESP 수명에 대한 전 주기 데이터를 취득 및 분석하였다. 구축한 시스템에서 산출되는 데이터 중 ESP의 유체유량, 흡입구 및 토출구의 온도, 압력 그리고 외측부에 설치된 진동 측정기의 데이터 분석을 통하여 ESP 장기 운영에 따른 성능 상태를 정상(normal), 권고 I (advise I), 권고 II (advise II), 유지관리(maintenance), 고장(failed)의 총 5단계로 분류하였다. 실험 결과를 통해 ESP 장기 운영시 단계별 데이터의 경향 차이를 확인하였으며, 이를 통해 운영 기간에 따른 ESP의 상태를 진단하고 펌프의 고장을 예측하였다. 본 연구를 통해 도출된 결과는 유·가스정에서 운영되는 ESP의 상태 모니터링(monitoring) 을 위한 고장 예측 프로그램 및 데이터 분석 알고리즘 개발에 활용될 수 있을 것으로 판단된다.

• 한국압력기기공학회 논문집
• /
• 제16권1호
• /
• pp.56-64
• /
• 2020

The safety related heat exchangers have been evaluated for their performance during the operation of the nuclear power plant. The evaluation program for the safety related heat exchanger was developed in 2010 and used by KHNP based on EPRI TR-10739 algorithms. The spend fuel pool heat exchanger is one of the safety related heat exchanger in the nuclear power plant and also evaluated for their performance. Recently the performance evaluation for the spend fuel pool heat exchanger was not available because of the decreased heat in the spend fuel pool due to the long term overhaul. This paper analyzes the main cause of evaluation failure in the evaluation process and suggests the criteria for the heat exchanger performance evaluation during the long term overhaul.

• 대한심미치과학회지
• /
• 제10권1호
• /
• pp.56-70
• /
• 2001

The use of resin-bonded fixed partial dentures described in the early 1980s caused an conservative way to preserve tooth structure in the restorative dental community. The treatment of patients with requires long term analysis of clinical application and basic research. Failure rates of these prosthesis ranged from 3% to 55%. These varieties were orginated by different techniques, materials, tooth preparation methods and diverse clinical situations. This article review was focused on the standard long term results and in vitro studies on bond strength between metal and teeth. From this, many useful clinical guidelines to RBFPD could be adopted to clinical dentistry. For successful results, careful case selection and good clinical skills are needed. And appropriate techniques for each situations should be adopted. Also, RBFPD using new materials like all-ceramics, FRC/Ceromer was introduced.