• 한국원자력학회:학술대회논문집
• /
• 한국원자력학회 1998년도 춘계학술발표회논문집(1)
• /
• pp.264-270
• /
• 1998

This research broadens the prime concern of nuclear power plant operations from safe performance to both economic and safe performance. First emergency diesel generator is identified as one of main contributors for the lost plant availability through the review of plants forced outage records. The framework of an integrated architecture for performing modern on-line condition for operational availability improvement is configured in this work. For the development of the comprehensive sensor networks for complex target systems, an integrated methodology incorporating a structural hierarchy, a functional hierarchy, and a fault-system matrix is formulated. The second part of our research is development of intelligent diagnosis and maintenance advisory system, which employs Bayesian Belief networks (BBNs) as a high level reasoning tool incorporating inherent uncertainty use in probabilistic inference. Our prototype diagnosis algorithms are represented explicitly through topological symbols and links between them in a causal direction. As new evidence from sensor network development is entered into the model especially, our advisory of system provides operational advice concerning both availability and safety, so that the operator is able to determine the likely modes, diagnose the system state, locate root causes, and take the most advantageous action. Thereby, this advice improves operational availability

• 디지털콘텐츠학회 논문지
• /
• 제15권5호
• /
• pp.579-586
• /
• 2014

본 논문은 문맥-자유 문법 (context-free grammar)를 이용하여, 차선변경 상황에서의 운전자의 행동패턴 인식을 하는 방법을 제안하는 것을 목표로 한다. 문맥-자유-문법은 기존 패턴인식 방식과는 대조적으로 유한적 기호로는 쉽게 표현될 수 없는 특징들을 비교적 손쉽게 표현할 수 있다. 이 방식을 적용하여, 동시에 여러 특징을 각각 고려해야 하는 좌표기반 데이터 처리 대신 심볼 시퀀스 방식 (symbolic sequence)을 패턴화하기 위해 구문론적 방식을 적용한다. 이 방법은 운전자와 안전 운전 분야 연구자들에게 효율적이고 보다 직관적인 방법으로 보다 더 효과적인 수행에 도움이 된다. 본 연구의 향후과제로 보다 안정적인 인식률을 획득하기 위해 확률적 구문분석 방법을 적용할 계획이다.

• Journal of Magnetics
• /
• 제22권1호
• /
• pp.34-42
• /
• 2017

Material defects in the Steam Generator Tubes (SGT) of sodium cooled fast breeder reactor (PFBR) can lead to leakage of water into sodium. The water and sodium reaction will lead to major accidents. Therefore, the examination of steam generator tubes for the early detection of defects is an important requirement for safety and economic considerations. In this work, the Magnetic Flux Leakage (MFL) based Non Destructive Testing (NDT) technique is used to perform the defect detection process. The rectangular notch defects on the outer surface of steam generator tubes are modeled using COMSOL multiphysics 4.3a software. The obtained MFL images are de-noised to improve the integrity of flaw related information. Grey Level Co-occurrence Matrix (GLCM) features are extracted from MFL images and taken as input parameter to train the neural network. A comparative study on characterization have been carried out using feed-forward back propagation (FFBP) and cascade-forward back propagation (CFBP) algorithms. The results of both algorithms are evaluated with Mean Square Error (MSE) as a prediction performance measure. The average percentage error for length, depth and width are also computed. The result shows that the feed-forward back propagation network model performs better in characterizing the defects.

• Nuclear Engineering and Technology
• /
• 제52권10호
• /
• 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.

• 한국건설관리학회논문집
• /
• 제5권5호
• /
• pp.163-171
• /
• 2004

This research investigates a Modeling Spell Checker that, similarly to Word Spell Checker for word processing software, would conform as-built 3D models to standard construction rules. The work is focused on the study of pipe-spools. Specifically pipe diameters and coplanarity are checked and corrected by the Modeling Spell Checker, and elbows are deduced and modeled to complete models. Experiments have been conducted by scanning scenes of increasing levels of complexity regarding the number of pipes, the types of elbows and the number of planes constituting pipe-spools. For building models of pipes from sensed data, a modeling method, developed at the University of Texas at Austin, that is based on the acquisition of sparse point clouds and the human ability to recognize geometric shapes has been used Results show that primitive-based models obtained after scanning construction sites can be corrected and even improved automatically, and, since such models are expected to be used as feedback control models for equipment operators, the higher modeling accuracy achieved with the Modeling Spell Checker could potentially increase the level of safety in construction. Result also show that some improvements are still needed especially regarding the co-planarity of pipes. In addition, results show that the modeling accuracy significantly depends on the primitive modeling method, and improvement of that method would positively impact the modeling spell checker.

• 해양환경안전학회:학술대회논문집
• /
• 해양환경안전학회 2017년도 추계학술발표회
• /
• pp.69-69
• /
• 2017

Flame arrestor as end of line flame arrester for endurance burning prevents a light-back at deflagration and stabilized burning (during and after endurance burning) of potentially explosive vapor-air and gas-air mixtures at the end of vent pipes. In a flame arrestor, spring is an important part. The spring load as well as the spring's elasticity determine when the hood is opened. In addition, the spring have to work in high temperature condition due to gas burning. Therefore, it is necessary to analyze mechanical load and elasticity of spring when gas is burned. Based on the dynamic calculation on working process of a specific flame arrestor, analysis of spring is taken. A three dimensional model for spring burned in flame arrestor by using CFD simulation. Results of the CFD analysis are input in FEM simulation to analyze structure of the spring. The simulation results can predict and estimate the spring's load and elasticity at variation of the spring's deflection. Moreover, the obtained result can provide makers with references to optimize design of spring as well as flame arrestor.

• 대한교통학회지
• /
• 제21권3호
• /
• pp.23-35
• /
• 2003

본 연구는 항공기 운항에 있어 주요 구성원들인 항공정비사와 조종사들 사이에 내재하고 있는 공유가치나, 양자간의 갈등정도, 영향력이 그들간의 신뢰나 업무만족, 운항성과에 어떠한 영향을 미치는지를 살펴보았다. 분석 결과, 항공정비사와 조종사의 공유가치가 높을수록 신뢰가 높아지며 업무만족도 높아졌다. 또한 그들간의 갈등이 적을수록 신뢰가 높아지며, 업무만족이 높아졌다. 항공정비사와 조종사들간의 영향력이 균형을 이룰수록 신뢰수준과 업무만족 또한 높아졌다. 그리고 신뢰수준과 업무만족의 정도에 따라 운항성과도 달라진 것으로 파악되었다. 이상의 연구결과는 상호업무의존성이 많은 운항업무에서 항공정비사와 조종사가 지각하는 상대방에 대한 태도가 운항성과와 관련이 있음을 제시한다.

• Steel and Composite Structures
• /
• 제18권2호
• /
• pp.375-394
• /
• 2015

This paper presents the results of four long-term experiments carried out to investigate the time-dependent behaviour of composite floor slabs with particular attention devoted to the development of non-uniform shrinkage through the slab thickness. This is produced by the presence of the steel deck which prevents moisture egress to occur from the underside of the slab. To observe the influence of different drying conditions on the development of shrinkage, the four 3.3 m long specimens consisted of two composite slabs cast on Stramit Condeck $HP^{(R)}$ steel deck and two reinforced concrete slabs, with the latter ones having both faces exposed for drying. During the long-term tests, the samples were maintained in a simply-supported configuration subjected to their own self-weight, creep and shrinkage for four months. Separate concrete samples were prepared and used to measure the development of shrinkage through the slab thickness over time for different drying conditions. A theoretical model was used to predict the time-dependent behaviour of the composite and reinforced concrete slabs. This approach was able to account for the occurrence of non-uniform shrinkage and comparisons between numerical results and experimental measurements showed good agreement. This work highlights the importance of considering the shrinkage gradient in predicting shrinkage deformations of composite slabs. Further comparisons with experimental results are required to properly validate the adequacy of the proposed approach for its use in routine design.

• 한국BIM학회 논문집
• /
• 제11권2호
• /
• pp.24-32
• /
• 2021

Recently, starting with smart construction research, interest in technology that automates construction site management using artificial intelligence technology is increasing. In order to automate construction site management, it is necessary to recognize objects such as construction equipment or workers, and automatically analyze the relationship between them. For example, if the relationship between workers and construction equipment at a construction site can be known, various use cases of site management such as work productivity, equipment operation status monitoring, and safety management can be implemented. This study derives a real-time object detection platform architecture that is required when performing construction site management using deep learning technology, which has recently been increasingly used. To this end, deep learning models that support real-time object detection are investigated and analyzed. Based on this, a deep learning model development process required for real-time construction site object detection is defined. Based on the defined process, a prototype that learns and detects construction site objects is developed, and then platform development considerations and architecture are derived from the results.

• 반도체디스플레이기술학회지
• /
• 제21권2호
• /
• pp.117-122
• /
• 2022

This paper proposes a method for evaluating the work of manufacturing workers using MediaPipe as a risk factor for musculoskeletal diseases. Recently, musculoskeletal disorders (MSDs) caused by repeated working attitudes in industrial sites have emerged as one of the biggest problems in the industrial health field while increasing public interest. The Korea Occupational Safety and Health Agency presents tools such as NIOSH Lifting Equations (NIOSH), OWAS (Ovako Working-posture Analysis System), Rapid Upper Limb Assessment (RULA), and Rapid Entertainment Assessment (REBA) as ways to quantitatively calculate the risk of musculoskeletal diseases that can occur due to workers' repeated working attitudes. To compensate for these shortcomings, the system proposed in this study obtains the position of the joint by estimating the posture of the worker using the posture estimation learning model of MediaPipe. The position of the joint is calculated using inverse kinetics to obtain an angle and substitute it into the REBA equation to calculate the load level of the working posture. The calculated result was compared to the expert's image-based REBA evaluation result, and if there was a result with a large error, feedback was conducted with the expert again.