• 한국컴퓨터정보학회논문지
• /
• 제28권10호
• /
• pp.1-8
• /
• 2023

자동차의 주요 부품인 휠 베어링에 결함이 생기면 교통사고등 문제를 발생시켜 이를 해결하기 위해 빅데이터를 수집해서 예측진단 및 관리 기술을 통한 휠 베어링의 고장 유무 및 고장 유형을 조기에 알려 주는 알고리즘과 모니터링 시스템 개발이 필요하다. 본 논문에서는 이러한 지능형 휠 허브 베어링 정비 시스템 구현을 위해 신뢰성 및 건전성에 대한 모니터링용 센서 및 예측 진단하는 알고리즘이 탑재된 임베디드 시스템을 개발하였다. 사용된 알고리즘은 휠 베어링에 설치된 가속도 센서로부터 진동 신호를 취득하고 이를 신호 처리기법, 결함주파수 분석, 건전성 특징 인자정의 등의 과정을 빅데이터 기술을 통해 고장을 예측하고 진단할 수 있다. 구현된 알고리즘은 진동 주파수 성분들은 최소화하고 휠 베어링에서 발생하는 진동 성분을 극대화할 수 있는 안정 신호 추출 알고리즘을 적용하고, 필터를 활용한 노이즈 제거에서는 인공지능 기반의 건전성 추출 알고리즘을 적용하였으며, FFT를 통한 결함 주파수를 분석하여 고장 특성인자 추출을 통한 고장을 진단하였다. 본 시스템의 성능 목표는 12,800ODR 이상으로 시험 결과를 통해 목표치를 만족하였다.

• 한국항해항만학회지
• /
• 제46권6호
• /
• pp.562-569
• /
• 2022

기존 운항선박에 적용되어 있는 알람 모니터링 기술은 온도, 압력 등의 데이터 항목을 AMS(Alarm Monitoring System)으로 관리하고 해당 센싱 데이터가 정상 수준 범위를 초과할 경우만 선원에게 알람을 제공한다. 또한 기존 선박의 정비는 PMS(Planned Maintenance System)를 따른다. 이는 장비로부터 측정된 센싱 데이터가 설정범위 이상으로 측정되어 이에 따른 알람을 통해 정비하거나, 대상 기기의 고장 유무에 관계없이 일정 시간 사용 후 해당 부품을 사전에 교체하는 방식으로 운영되고 있다. 하지만 선박 기관운영의 신뢰성과 운항 안전성을 확보하기 위해서는 실시간 상태 모니터링 데이터 기반의 사전적 진단 및 예측이 가능해야 한다. 그러기 위해서 실선 데이터를 종합적으로측정하여 데이터베이스화 하고 이를 선박의 보조기기와 배관의 상태기반 예지보전을 위한 상태 진단 모니터링 시스템을 구현하고자 한다. 특히 반응형 웹 기반으로 선박의 보조기기와 배관 상태 정보를 관리할 수 있도록 하였으며, 선내 개인용 컴퓨터(Personal Computer, PC)에서 보는 용도뿐만 아니라 스마트폰 등 다양한 모바일 기기의 접근 및 활용이 가능하도록 화면과 해상도에 맞춰 최적화된 상태 관리가 가능하도록 하여 업데이트 비용이 적게 들며, 관리 방법도 쉽다. 본 논문에서는 자율운항선박 핵심 기술인 상태기반정비(Condition Based Management, CBM) 기술력을 확보하기 위해 선박의 보조기기 중 펌프와 청정기, 그리고 배관 중 해수 및 스팀 배관의 상태 진단 모니터링을 통해 이상 현상을 파악하고, 이를 통해 융합 분석할 수 있도록 선박 보조기기 및 배관의 성능 진단 및 고장 예측에 활용하여 예방정비 의사결정을 지원하고자 한다.

• Journal of Gastric Cancer
• /
• 제24권1호
• /
• pp.4-28
• /
• 2024

Liquid biopsy, a minimally invasive procedure that causes minimal pain and complication risks to patients, has been extensively studied for cancer diagnosis and treatment. Moreover, it facilitates comprehensive quantification and serial assessment of the whole-body tumor burden. Several biosources obtained through liquid biopsy have been studied as important biomarkers for establishing early diagnosis, monitoring minimal residual disease, and predicting the prognosis and response to treatment in patients with cancer. Although the clinical application of liquid biopsy in gastric cancer is not as robust as that in other cancers, biomarker studies using liquid biopsy are being actively conducted in patients with gastric cancer. Herein, we aimed to review the role of various biosources that can be obtained from patients with gastric cancer through liquid biopsies, such as blood, saliva, gastric juice, urine, stool, peritoneal lavage fluid, and ascites, by dividing them into cellular and acellular components. In addition, we reviewed previous studies on the diagnostic, prognostic, and predictive biomarkers for gastric cancer using liquid biopsy and discussed the limitations of liquid biopsy and the challenges to overcome these limitations in patients with gastric cancer.

• 한국멀티미디어학회논문지
• /
• 제20권11호
• /
• pp.1811-1819
• /
• 2017

As the induction motor is the core production equipment of the industry, it is necessary to construct a fault prediction and diagnosis system through continuous monitoring. Many researches have been conducted on motor fault diagnosis algorithm based on signal processing techniques using Fourier transform, neural networks, and fuzzy inference techniques. In this paper, we propose a fault diagnosis method of induction motor using LPC and DNN. To evaluate the performance of the proposed method, the fault diagnosis was carried out using the vibration data of the induction motor in steady state and simulated various fault conditions. Experimental results show that the learning time of our proposed method and the conventional spectrum+DNN method is 139 seconds and 974 seconds each executed on the experimental PC, and our method reduces execution time by 1/8 compared with conventional method. And the success rate of the proposed method is 98.08%, which is similar to 99.54% of the conventional method.

• Nuclear Engineering and Technology
• /
• 제50권8호
• /
• pp.1306-1313
• /
• 2018

The randomness and incipient nature of certain faults in reactor systems warrant a robust and dynamic detection mechanism. Existing models and methods for fault diagnosis using different mathematical/statistical inferences lack incipient and novel faults detection capability. To this end, we propose a fault diagnosis method that utilizes the flexibility of data-driven Support Vector Machine (SVM) for component-level fault diagnosis. The technique integrates separately-built, separately-trained, specialized SVM modules capable of component-level fault diagnosis into a coherent intelligent system, with each SVM module monitoring sub-units of the reactor coolant system. To evaluate the model, marginal faults selected from the failure mode and effect analysis (FMEA) are simulated in the steam generator and pressure boundary of the Chinese CNP300 PWR (Qinshan I NPP) reactor coolant system, using a best-estimate thermal-hydraulic code, RELAP5/SCDAP Mod4.0. Multiclass SVM model is trained with component level parameters that represent the steady state and selected faults in the components. For optimization purposes, we considered and compared the performances of different multiclass models in MATLAB, using different coding matrices, as well as different kernel functions on the representative data derived from the simulation of Qinshan I NPP. An optimum predictive model - the Error Correcting Output Code (ECOC) with TenaryComplete coding matrix - was obtained from experiments, and utilized to diagnose the incipient faults. Some of the important diagnostic results and heuristic model evaluation methods are presented in this paper.

• 한국소음진동공학회논문집
• /
• 제21권11호
• /
• pp.1020-1028
• /
• 2011

As rotating machines play an important role in industrial applications such as aeronautical, naval and automotive industries, many researchers have developed various condition monitoring system and fault diagnosis system by applying artificial neural network. Since using obtained signals without preprocessing as inputs of neural network can decrease performance of fault classification, it is very important to extract significant features of captured signals and to apply suitable features into diagnosis system according to the kinds of obtained signals. Therefore, this paper proposes a neural-network-based fault diagnosis system using AR coefficients as feature vectors by LPC(linear predictive coding) and EIV(errors-in variables) analysis. We extracted feature vectors from sound, vibration and current faulty signals and evaluated the suitability of feature vectors depending on the classification results and training error rates by changing AR order and adding noise. From experimental results, we conclude that classification results using feature vectors by EIV analysis indicate more than 90 % stably for less than 10 orders and noise effect comparing to LPC.

• 소음진동
• /
• 제6권3호
• /
• pp.325-332
• /
• 1996

One of the greatest shortcoming in today's predictive maintenance program is the ability to diagnose the mechanical and electrical problems within the machine when the vibration exceeds preset overall and spectral alarm levels. In this study, auto-diagnosis system is constructed by using A/D converter to convert analog to digital singal. With this device the system analyses input signal to diagonosis machine condition. Many plots, which display machine condition, and input values of every channel are calculated in this system. If the falut is found, the system diagnoses automatically using fuzzy algorithm and trend monitoring. Prediction is also performed by the grey system theory. Operator finds out eh machine operating condition intuitively based on with personal computer CRT in using this system.

• 한국멀티미디어학회논문지
• /
• 제18권7호
• /
• pp.864-872
• /
• 2015

The purpose of this study is to design the algorithm, Predictive Service Component - PSC, for forecasting and judging obsolescence of solar system that is implemented based on the micro-inverter. PSC proposed in this study is suitable for monitoring of distributed power generation systems. It provides a diagnosis functionality to detect failures and anomaly events. It also can determine the aging of PV systems. The conclusion of this study shows the research and development of this kind of integrated system using PSC will be needed more and varied in the near future.

• Korean Journal of Radiology
• /
• 제25권1호
• /
• pp.86-102
• /
• 2024

Early diagnosis, accurate assessment, and localization of peritoneal metastasis (PM) are essential for the selection of appropriate treatments and surgical guidance. However, available imaging modalities (computed tomography [CT], conventional magnetic resonance imaging [MRI], and 18fluorodeoxyglucose positron emission tomography [PET]/CT) have limitations. The advent of new imaging techniques and novel molecular imaging agents have revealed molecular processes in the tumor microenvironment as an application for the early diagnosis and assessment of PM as well as real-time guided surgical resection, which has changed clinical management. In contrast to clinical imaging, which is purely qualitative and subjective for interpreting macroscopic structures, radiomics and artificial intelligence (AI) capitalize on high-dimensional numerical data from images that may reflect tumor pathophysiology. A predictive model can be used to predict the occurrence, recurrence, and prognosis of PM, thereby avoiding unnecessary exploratory surgeries. This review summarizes the role and status of different imaging techniques, especially new imaging strategies such as spectral photon-counting CT, fibroblast activation protein inhibitor (FAPI) PET/CT, near-infrared fluorescence imaging, and PET/MRI, for early diagnosis, assessment of surgical indications, and recurrence monitoring in patients with PM. The clinical applications, limitations, and solutions for fluorescence imaging, radiomics, and AI are also discussed.

• 대한치과마취과학회지
• /
• 제12권1호
• /
• pp.17-23
• /
• 2012

Background: This study evaluated pulp vitality of anterior permanent teeth using pulse oximetry (PO), which is already used for monitoring of patient's $SpO_2$ and pulse rates (PR). Also we compared with ice tests and electric pulp test (EPT). Methods: 9 teeth, endodontic treated, were selected as non-vital teeth group. 17 vital teeth were selected as control group. Our aim is to compare sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) of ice test, electric pulp test and pulse oximetry, respectively. Pulse oximetry has two test results, $SpO_2$ and pulse rates. Also we calculated correlation and statistical significances by Pearson's test between EPT and pulse oximetry. Results: Sensitivity, specificity, PPV, NPV were calculated on each tests. Ice test has results of 1.00, 0.89, 0.94 and 1.00, respectively. EPT has results of 0.94, 0.78, 0.89 and 0.88 respectively. $SpO_2$ has results of 0.94, 1.00, 1.00 and 0.90, respectively. PR has results of all 1.00. Conclusions: PO showed relatively accurate, stable and objective results on both $SpO_2$ and PR. Percentage of ability of accurate diagnosis for vital teeth is 94% for ice test, 89% for EPT, 100% for $SpO_2$ and PR. Percentage of ability of accurate diagnosis for non-vital teeth is 100% for ice test, 88% for EPT, 90% for $SpO_2$ and 100% for PR. In additions, PR could be more accurate and significant tests than $SpO_2$.