• 제목/요약/키워드: Accident Prediction Models

검색결과 103건 처리시간 0.024초

THINNED PIPE MANAGEMENT PROGRAM OF KOREAN NUCLEAR POWER PLANTS

  • Lee, S.H.;Lee, Y.S.;Park, S.K.;Lee, J.G.
    • Corrosion Science and Technology
    • /
    • 제14권1호
    • /
    • pp.1-11
    • /
    • 2015
  • Local wall thinning and integrity degradation caused by several mechanisms, such as flow accelerated corrosion (FAC), cavitation, flashing and/or liquid drop impingements, are a main concern in carbon steel piping systems of nuclear power plant in terms of safety and operability. Thinned pipe management program (TPMP) had been developed and optimized to reduce the possibility of unplanned shutdown and/or power reduction due to pipe failure caused by wall thinning in the secondary side piping system. This program also consists of several technical elements such as prediction of wear rate for each component, prioritization of components for inspection, thickness measurement, calculation of actual wear and wear rate for each component. Decision making is associated with replacement or continuous service for thinned pipe components. Establishment of long-term strategy based on diagnosis of plant condition regarding overall wall thinning is also essential part of the program. Prediction models of wall thinning caused by FAC had been established for 24 operating nuclear plants. Long term strategies to manage the thinned pipe component were prepared and applied to each unit, which was reflecting plant specific design, operation, and inspection history, so that the structural integrity of piping system can be maintained. An alternative integrity assessment criterion and a computer program for thinned piping items were developed for the first time in the world, which was directly applicable to the secondary piping system of nuclear power plant. The thinned pipe management program is applied to all domestic nuclear power plants as a standard procedure form so that it contributes to preventing an accident caused by FAC.

나이브 베이즈 빅데이터 분류기를 이용한 렌터카 교통사고 심각도 예측 (Prediction of Severities of Rental Car Traffic Accidents using Naive Bayes Big Data Classifier)

  • 정하림;김홍회;박상민;한음;김경현;윤일수
    • 한국ITS학회 논문지
    • /
    • 제16권4호
    • /
    • pp.1-12
    • /
    • 2017
  • 교통사고는 인적요인, 차량요인, 환경요인이 복합적으로 작용하여 발생한다. 이 중 렌터카 교통사고는 운전자의 평소 익숙하지 않은 환경 등으로 인해 교통사고 발생 가능성과 심각도가 다른 교통사고와는 다를 것으로 예상된다. 이에 본 연구에서는 국내 대표 관광도시인 부산광역시, 강릉시, 제주시를 대상으로 최근 빅데이터 분석에 사용되는 기계학습 기법중 하나인 나이브 베이즈 분류기를 이용하여 렌터카 교통사고의 심각도를 예측하는 모형을 개발하였다. 또한, 기존 연구에 유의성이 검증된 변수와 수집 가능한 모든 변수를 이용하는 두 가지 모형에 대하여 모형의 예측 정확도를 비교하였다. 비교 결과 통계적 기법을 통해 유의성이 검증된 변수를 사용할 경우 모형이 더 높은 예측 정확도를 보이는 것으로 나타났다.

독립신호 교차로에서의 교통안전을 위한 서비스수준 결정방법의 개발 (DEVELOPMENT OF SAFETY-BASED LEVEL-OF-SERVICE CRITERIA FOR ISOLATED SIGNALIZED INTERSECTIONS)

  • Dr. Tae-Jun Ha
    • 대한교통학회:학술대회논문집
    • /
    • 대한교통학회 1995년도 제27회 학술발표회
    • /
    • pp.3-32
    • /
    • 1995
  • The Highway Capacity Manual specifies procedures for evaluating intersection performance in terms of delay per vehicle. What is lacking in the current methodology is a comparable quantitative procedure for ass~ssing the safety-based level of service provided to motorists. The objective of the research described herein was to develop a computational procedure for evaluating the safety-based level of service of signalized intersections based on the relative hazard of alternative intersection designs and signal timing plans. Conflict opportunity models were developed for those crossing, diverging, and stopping maneuvers which are associated with left-turn and rear-end accidents. Safety¬based level-of-service criteria were then developed based on the distribution of conflict opportunities computed from the developed models. A case study evaluation of the level of service analysis methodology revealed that the developed safety-based criteria were not as sensitive to changes in prevailing traffic, roadway, and signal timing conditions as the traditional delay-based measure. However, the methodology did permit a quantitative assessment of the trade-off between delay reduction and safety improvement. The Highway Capacity Manual (HCM) specifies procedures for evaluating intersection performance in terms of a wide variety of prevailing conditions such as traffic composition, intersection geometry, traffic volumes, and signal timing (1). At the present time, however, performance is only measured in terms of delay per vehicle. This is a parameter which is widely accepted as a meaningful and useful indicator of the efficiency with which an intersection is serving traffic needs. What is lacking in the current methodology is a comparable quantitative procedure for assessing the safety-based level of service provided to motorists. For example, it is well¬known that the change from permissive to protected left-turn phasing can reduce left-turn accident frequency. However, the HCM only permits a quantitative assessment of the impact of this alternative phasing arrangement on vehicle delay. It is left to the engineer or planner to subjectively judge the level of safety benefits, and to evaluate the trade-off between the efficiency and safety consequences of the alternative phasing plans. Numerous examples of other geometric design and signal timing improvements could also be given. At present, the principal methods available to the practitioner for evaluating the relative safety at signalized intersections are: a) the application of engineering judgement, b) accident analyses, and c) traffic conflicts analysis. Reliance on engineering judgement has obvious limitations, especially when placed in the context of the elaborate HCM procedures for calculating delay. Accident analyses generally require some type of before-after comparison, either for the case study intersection or for a large set of similar intersections. In e.ither situation, there are problems associated with compensating for regression-to-the-mean phenomena (2), as well as obtaining an adequate sample size. Research has also pointed to potential bias caused by the way in which exposure to accidents is measured (3, 4). Because of the problems associated with traditional accident analyses, some have promoted the use of tqe traffic conflicts technique (5). However, this procedure also has shortcomings in that it.requires extensive field data collection and trained observers to identify the different types of conflicts occurring in the field. The objective of the research described herein was to develop a computational procedure for evaluating the safety-based level of service of signalized intersections that would be compatible and consistent with that presently found in the HCM for evaluating efficiency-based level of service as measured by delay per vehicle (6). The intent was not to develop a new set of accident prediction models, but to design a methodology to quantitatively predict the relative hazard of alternative intersection designs and signal timing plans.

  • PDF

A Simple Model for Dispersion in the Stable Boundary Layer

  • Kang Sung-Dae;Kimura Fujio;Lee Hwa-Woon;Kim Yoo-Keun
    • Environmental Sciences Bulletin of The Korean Environmental Sciences Society
    • /
    • 제1권1호
    • /
    • pp.35-43
    • /
    • 1997
  • Handling the emergency problems such as Chemobyl accident require real time prediction of pollutants dispersion. One-point real time sounding at pollutant source and simple model including turbulent-radiation process are very important to predict dispersion at real time. The stability categories obtained by one-dimensional numerical model (including PBL dynamics and radiative process) are good agreement with observational data (Golder, 1972). Therefore, the meteorological parameters (thermal, moisture and momentum fluxes; sensible and latent heat; Monin-Obukhov length and bulk Richardson number; vertical diffusion coefficient and TKE; mixing height) calculated by this model will be useful to understand the structure of stable boundary layer and to handling the emergency problems such as dangerous gasses accident. Especially, this simple model has strong merit for practical dispersion models which require turbulence process but does not takes long time to real predictions. According to the results of this model, the urban area has stronger vertical dispersion and weaker horizontal dispersion than rural area during daytime in summer season. The maximum stability class of urban area and rural area are 'A' and 'B' at 14 LST, respectively. After 20 LST, both urban and rural area have weak vertical dispersion, but they have strong horizontal dispersion. Generally, the urban area have larger radius of horizontal dispersion than rural area. Considering the resolution and time consuming problems of three dimensional grid model, one-dimensional model with one-point real sounding have strong merit for practical dispersion model.

  • PDF

교통사고 잦은 곳 안전시설 개선 방안 예측 모델 개발 (Development of Prediction Model for Improvement of Safety Facilities in Frequent Traffic Accidents)

  • 권재경;김시원;황재성;이재형;이철기
    • 한국ITS학회 논문지
    • /
    • 제22권1호
    • /
    • pp.16-24
    • /
    • 2023
  • 교통사고 잦은 곳 개선사업을 통하여 사고가 크게 감소하고 있다. 이러한 결과는 안전 시설물이 큰 역할을 하고 있다. 교통사고는 여러 가지 원인과 다양한 환경적인 요소로 인하여 발생하게 되는데, 한가지 안전시설물 혹은 기준 없는 시설물 설치로는 개선효과를 얻기 어렵다. 따라서 본 연구는 두 가지 안전시설물의 조합으로 사고유형별 개선효과를 분석하였고, 도로종류, 도로형태, 교통량 등으로 환경적인 요소도 포함하여 특정 지점에 맞는 안전시설물 조합을 예측하는 방법을 제시하였다. 예측은 단순 분류가 가능한 예측 모델들을 결합하여 하나의 강한 예측 모델을 만드는 XGBoost 기법으로 선정하여 진행하였다. 이를 통해 최종적으로 현재까지 교통사고 잦은 곳 개선사업을 통해 긍정적인 효과를 가져다 준 안전시설물과 개선이 필요한 지점에 설치될 안전시설물을 같이 도출하여, 안전시설물 효과분석과 향후 설치지점에 대한 예측방법을 제시하였다.

Numerical and analytical predictions of nuclear steam generator secondary side flow field during blowdown due to a feedwater line break

  • Jo, Jong Chull;Jeong, Jae-Jun;Moody, Frederick J.
    • Nuclear Engineering and Technology
    • /
    • 제53권3호
    • /
    • pp.1029-1040
    • /
    • 2021
  • For the structural integrity evaluation of pressurized water reactor (PWR) steam generator (SG) tubes subjected to transient hydraulic loading, determination of the tube-to-tube gap velocity and static pressure distributions along the tubes is prerequisite. This paper addresses both computational fluid dynamics (CFD) and analytical approaches for predicting the tube-to-tube gap velocity and static pressure distributions during blowdown following a feedwater line break (FWLB) accident at a PWR SG. First of all, a comparative study on CFD calculations of the transient velocity and pressure distributions in the SG secondary sides for two different models having 30 or no tubes is performed. The result shows that the velocities of sub-cooled water flowing between any adjacent two tubes of a tubed SG model during blowdown can be roughly estimated by applying the specified SG secondary side porosity to those of the no-tubed SG model. Secondly, simplified analytical approximate solutions for the steady two-dimensional SG secondary flow velocity and pressure distributions under a given discharge flowrate are derived using a line sink model. The simplified analytical solutions are validated by comparing them to the CFD calculations.

Numerical prediction of a flashing flow of saturated water at high pressure

  • Jo, Jong Chull;Jeong, Jae Jun;Yun, Byong Jo;Moody, Frederick J.
    • Nuclear Engineering and Technology
    • /
    • 제50권7호
    • /
    • pp.1173-1183
    • /
    • 2018
  • Transient fluid velocity and pressure fields in a pressurized water reactor (PWR) steam generator (SG) secondary side during the blowdown period of a feedwater line break (FWLB) accident were numerically simulated employing the saturated water flashing model. This model is based on the assumption that compressed water in the SG is saturated at the beginning and decompresses into the two-phase region where saturated vapor forms, creating a mixture of steam bubbles in water by bulk boiling. The numerical calculations were performed for two cases of which the outflow boundary conditions are different from each other; one is specified as the direct blowdown discharge to the atmosphere and the other is specified as the blowdown discharge to an extended calculation domain with atmospheric pressure on its boundary. The present simulation results obtained using the two different outflow boundary conditions were discussed through a comparison with the predictions using a simple non-flashing model neglecting the effects of phase change. In addition, the applicability of each of the non-flashing water discharge and saturated water flashing models for the confirmatory assessments of new SG designs was examined.

LPG소형저장탱크 BLEVE 발생 시점 예측 툴 개발 (Development of a Tool for Predicting the Occurrence Time of BLEVE in Small LPG Storage Tanks)

  • 채충근;이재훈;채승빈;김용규;한신탁
    • 한국안전학회지
    • /
    • 제35권4호
    • /
    • pp.74-83
    • /
    • 2020
  • In Korea, about 110,000 LPG small storage tanks of less than three tons have been installed in restaurants, houses and factories, and are used as LPG supply facilities for cooking, heating and industrial use. In the case of combustible liquefied gas storage tanks, the tank may rupture due to the temperature increase of the tank steel plate (approximately 600℃) even when the safety valve is operating normally, causing large-scale damage in an instant. Therefore, in the event of a fire near the LPG small storage tank, it is necessary to accurately predict the timing of the BLEVE(Boiling Liquid Expanding Vapour Explosion) outbreak in order to secure golden time for lifesaving and safely carry out fire extinguishing activities. In this study, we have first investigated the results of a prior study on the prediction of the occurrence of BLEVE in the horizontal tanks. And we have developed thermodynamic models and simulation program on the prediction of BLEVE that can be applied to vertical tanks used in Korea, have studied the effects of the safety valve's ability to vent, heat flux strength of external fires, size of tanks, and gas remaining in tanks on the time of BLEVE occurrence and have suggested future utilization measures.

머신러닝 기반의 수도권 지역 고령운전자 차대사람 사고심각도 분류 연구 (Classifying Severity of Senior Driver Accidents In Capital Regions Based on Machine Learning Algorithms)

  • 김승훈;임영빈;김기정
    • 디지털융복합연구
    • /
    • 제19권4호
    • /
    • pp.25-31
    • /
    • 2021
  • 고령화 시대에 따라 고령운전자 역시 증가하고 있으며, 이들에 의한 교통사고 심각성에 대한 관심이 높아지고 있다. 이에 고령운전자에 의한 사고심각도 예측 모형의 필요성이 점차 요구됨에 따라, 본 연구에서는 기계학습 기법을 활용하여 고령운전자에 의한 차대사람 사고심각도 예측을 위한 모형 정립 및 분석을 수행하고자 한다. 이를 위해 4개의 기계학습 알고리즘 (Logistic Model, KNN, RF, SVM)을 활용, 예측 모형을 개발하고 각 결과를 비교하였다. 연구 결과에 따르면 Logistic과 SVM 모형이 상대적으로 높은 예측력을 보였으며, 정확도 측면에서는 RF가 높은 것으로 나타났다. 추가적으로 각 중요 변수들을 이용하여 교차분석을 수행한 후 그 결과를 제시하였다. 본 연구의 결과들은 고령화시대에 고령운전자에 의한 사고심각성을 예방하기 위한 안전정책 및 인프라 개발에 활용될 것으로 판단된다.

다중연결 해양부유체의 모형시험 구조응답 예측정확도 향상을 위한 유전알고리즘을 이용한 센서배치 최적화 (Optimal Sensor Placement for Improved Prediction Accuracy of Structural Responses in Model Test of Multi-Linked Floating Offshore Systems Using Genetic Algorithms)

  • 심기찬;이강수
    • 한국전산구조공학회논문집
    • /
    • 제37권3호
    • /
    • pp.163-171
    • /
    • 2024
  • 본 논문에서는 다목적 구조물인 다중연결 해양부유체를 대상으로 변형 기반 모드 차수축소법을 적용하고 차수축소모델의 구조응답 예측 성능을 향상시키기 위해 유전 알고리즘 기반의 센서 배치 최적화를 수행하였다. 다중연결 해양부유체의 차수축소모델 생성에 필요한 변형 기반 모드 데이터를 얻기 위해 다양한 규칙파랑하중조건에 대한 유체-구조 연성 수치해석을 수행하고 변형 기반 모드의 직교성, 자기상관계수를 이용하여 주요 변형 기반 모드를 선정하였다. 다중연결 해양부유체의 경우 차수축소모델의 구조응답 예측 성능이 계측 및 예측 구조응답 위치에 따라 민감하기 때문에 유전 알고리즘 기반의 최적화를 수행하여 최적의 센서 배치를 도출하였다. 최적화 결과, 모든 센서 배치 조합에 대한 차수축소모델 생성 및 예측 성능 평가 대비 약 8배의 계산 비용을 절감하였으며, 예측 성능 평가 지표인 평균 제곱근 오차가 초기 센서 배치보다 84% 감소하였다. 또한, 다중연결 해양부유체 모형시험 결과를 이용하여 불규칙파랑하중에 대한 최적화된 센서 배치의 차수축소모델의 구조응답 예측 성능을 평가 및 검증하였다.