• 국제학술발표논문집
• /
• The 8th International Conference on Construction Engineering and Project Management
• /
• pp.179-187
• /
• 2020

This paper investigates the construction equipment accidents by time. Construction sites are unique with many different hazardous conditions which cause accidents. According to the Occupational Safety and Health Administration (OSHA), accidents related to construction equipment are one of the most leading causes of fatal injuries in the construction industry. While there have been many studies investigating the equipment-related accidents, few research studies provided in-depth analyses about the time that accidents frequently occurred. By using the OSHA accidents data collected between 1997 and 2012, this paper analyzed the accidents data by time, equipment type including excavator, backhoe, dozer, and crane, accident cause, and injury class. The analyses revealed that the time window with most accidents was between 13:00 and 13:59. In terms of the injury class, the time windows with the highest numbers of equipment accidents were between 13:00 and 13:59 and between 11:00 and 11:59 for fatality and hospitalization, respectively. For the accident causes, equipment operator's error was the highest number of accident causes. It is expected that findings from the analyses can be used to more strategically develop management plans and guidelines to prevent accidents related to construction equipment to practitioners.

• 한국안전학회지
• /
• 제7권2호
• /
• pp.5-13
• /
• 1992

If zero-accident movement is to be successful, the objective goal period should be surely obtainable, and much more in our country where frequency rate of injury are remarkably fluc-tuating. However In our country, as far as we know, no method to establish a reasonable zero-accident goal period is guaranteed. In thls paper, a new establishing-method of reasonable goal period for individual industry with considering recent accident trend is presented. A mathematical model for industrial accidents generation was analyzed, and a stochastic process model for the accident generation inteual was formulated. This model could tell the accident generation rate in future by understanding the accident tendency through the time-series analysis and search for the distribution of numbers of accidents and accident interval. On the basis of this, the forecasting method of goal achievement probability by the size and the establishment method of reasonable goal period were developed.

• Safety and Health at Work
• /
• 제7권1호
• /
• pp.38-42
• /
• 2016

Background: Truck driving is known as one of the occupations with the highest accident rate. This study investigates the characteristics of traffic collisions according to road types (expressway and rural road). Methods: Classifying 267 accidents into expressway and rural road, we analyzed them based on driver characteristics (age, working experience, size of employment), time characteristics (day of accident, time, weather), and accident characteristics (accident causes, accident locations, accident types, driving conditions). Results: When we compared the accidents by road conditions, no differences were found between the driver characteristics. However, from the accident characteristics, the injured person distributions were different by the road conditions. In particular, driving while drowsy is shown to be highly related with the accident characteristics. Conclusion: This study can be used as a guideline and a base line to develop a plan of action to prevent traffic accidents. It can also help to prepare formal regulations about a truck driver's vehicle maintenance and driving attitude for a precaution on road accidents.

• 한국융합학회논문지
• /
• 제10권5호
• /
• pp.111-117
• /
• 2019

본 연구는 차량 사고에서 병원 전 응급의료 대응시간을 단축시키기 위한 방안을 모색한 융합연구이다. 연구방법은 한국형 교통사고 심층조사 분석 체계(Korea In-Depth Accident Study)에서 2011년 1월 1일부터 2016년 7월 30일까지 3개의 응급의료센터에 119구급대로 내원한 차량 탑승자 353명을 대상으로 날씨, 도로유형, 사고유형, 구조대 출동 여부를 활용하여 병원 전 응급의료 대응시간에 대해 요인 분석하였다. 연구결과에서 고속도로는 병원 전 응급의료 대응시간을 가장 많이 소요하였고 전체시간에 영향을 주는 요인으로 확인되었다(${\beta}=.543$, p<.001). 따라서 고속도로에서 소요되는 시간을 단축시키기 위해 고속도로 119구급대의 운영과 비상회차로의 적극적인 사용, 개별 장치를 부착한 자동 긴급구조신호 서비스의 제공을 제시하였다.

• 대한교통학회지
• /
• 제33권5호
• /
• pp.497-507
• /
• 2015

고속도로의 비반복 혼잡은 주로 돌발상황에 의해 발생된다. 돌발상황의 주요 원인은 교통사고로 알려져 있다. 따라서 교통사고 시 사고처리시간을 정확하게 예측하는 것은 돌발상황 관리에서 매우 중요하다. 본 연구에서는 전국고속도로의 2008-2014년 총 7년치(60,473건)의 사고 자료를 이용하였다. 사고처리시간 예측모형은 과거의 교통사고 이력자료를 바탕으로 비모수모형인 KNN (K-Nearest Neighbor) 알고리즘을 활용하였다. 사고자료 현황 분석결과 사고등급별로 사고처리시간에 미치는 영향이 매우 큰 것으로 분석되었다. 따라서 사고처리시간은 사고등급별로 분류하여 모형을 구축하였다. 그리고 현재 발생한 사고의 교통상황과 도로 기하구조를 반영하기 위하여 교통량, 차로수, 시간대를 구분하여 데이터를 추출하였다. 추출된 데이터 중 현재 교통사고와 유사한 사고를 검색하기 위하여 사고처리시간에 영향을 미치는 요인들을 분석하였다. 마지막으로, 상태간 거리 산정을 위해서 세부항목별 가중치를 산정하였다. 가중치산정은 정규분포 표준화방법을 적용하였고, 이를 통해 사고처리시간을 예측하였다. 본 연구에서 개발된 모형의 예측결과는 기존의 연구들의 결과에 비해 낮은 예측오차(MAPE)를 보여 모형의 우수성을 입증할 수 있다고 판단된다. 본 연구를 통해 고속도로의 돌발상황 발생 시 효율적인 고속도로의 운영관리에 기여할 수 있고, 기존의 모형들이 갖고 있던 한계를 개선 및 보완할 수 있을 것으로 판단된다.

• Nuclear Engineering and Technology
• /
• 제47권1호
• /
• pp.74-84
• /
• 2015

If a transient occurs in a nuclear power plant (NPP), operators will try to protect the NPP by estimating the kind of abnormality and mitigating it based on recommended procedures. Similarly, operators take actions based on severe accident management guidelines when there is the possibility of a severe accident occurrence in an NPP. In any such situation, information about the occurrence time of severe accident-related events can be very important to operators to set up severe accident management strategies. Therefore, support systems that can quickly provide this kind of information will be very useful when operators try to manage severe accidents. In this research, the occurrence times of several events that could happen during a severe accident were predicted using support vector machines with short time variations of plant status variables inputs. For the preliminary step, the break location and size of a loss of coolant accident (LOCA) were identified. Training and testing data sets were obtained using the MAAP5 code. The results show that the proposed algorithm can correctly classify the break location of the LOCA and can estimate the break size of the LOCA very accurately. In addition, the occurrence times of severe accident major events were predicted under various severe accident paths, with reasonable error. With these results, it is expected that it will be possible to apply the proposed algorithm to real NPPs because the algorithm uses only the early phase data after the reactor SCRAM, which can be obtained accurately for accident simulations.

• Nuclear Engineering and Technology
• /
• 제50권4호
• /
• pp.582-588
• /
• 2018

Accident diagnosis is one of the complex tasks for nuclear power plant (NPP) operators. In abnormal or emergency situations, the diagnostic activity of the NPP states is burdensome though necessary. Numerous computer-based methods and operator support systems have been suggested to address this problem. Among them, the recurrent neural network (RNN) has performed well at analyzing time series data. This study proposes an algorithm for accident diagnosis using long short-term memory (LSTM), which is a kind of RNN, which improves the limitation for time reflection. The algorithm consists of preprocessing, the LSTM network, and postprocessing. In the LSTM-based algorithm, preprocessed input variables are calculated to output the accident diagnosis results. The outputs are also postprocessed using softmax to determine the ranking of accident diagnosis results with probabilities. This algorithm was trained using a compact nuclear simulator for several accidents: a loss of coolant accident, a steam generator tube rupture, and a main steam line break. The trained algorithm was also tested to demonstrate the feasibility of diagnosing NPP accidents.

• 산업경영시스템학회지
• /
• 제22권51호
• /
• pp.199-210
• /
• 1999

The number of car accident is Recently on the increase in Korea because of the explosive increase of cars, the poor road condition, the lack of safety facility, and others. The insurant with a accident has to decide whether receiving a insurance or not. In this paper, we represent a reasonable decision support material by calculating the approximate insurance fee based on the discount rate and premium additive rate, which is changed by the accident type and the accident expenditure. Practically, there is difference in the standard insurance rate and premium additive rate according to the accident type and the accident expenditure in Korea. The premium additive rate is assessed considering the number of accident, the pattern of accident, and the reason of accident for 3 years. In this paper, we represent a decision making method considering not only the first-time car accident but also the future car accident. For considering the repeated accident, we analyzed the real data accumulated until the year of 1996 from S Insurance Company, and estimated the probability density function between the first and the second-time accident, and executed the goodness of fit test using ARENA and STATISTICA software. Using this conditional PDF, we can calculate the insurance fee next 3 years and compare the insurance fee with the equivalent present value of cash flows. The program performing this analysis is represented, and written in VISUAL BASIC Language. We tried to suggest an accurate guideline for the insurant to decide the insurance coverage rationally, and tried to correct a wrong idea of dependence on the car insurance only by the amount of the accident expenditure. And we expect this study can generally be applied to many different accident types under the uncertain circumstances in our daily life.

• Nuclear Engineering and Technology
• /
• 제55권3호
• /
• pp.814-826
• /
• 2023

Sensor faults in nuclear power plant instrumentation have the potential to spread negative effects from wrong signals that can cause an accident misdiagnosis by plant operators. To detect sensor faults and make accurate accident diagnoses, prior studies have developed a supervised learning-based sensor fault detection model and an accident diagnosis model with faulty sensor isolation. Even though the developed neural network models demonstrated satisfactory performance, their diagnosis performance should be reevaluated considering real-time connection. When operating in real-time, the diagnosis model is expected to indiscriminately accept fault data before receiving delayed fault information transferred from the previous fault detection model. The uncertainty of neural networks can also have a significant impact following the sensor fault features. In the present work, a pilot study was conducted to connect two models and observe actual outcomes from a real-time application with an integrated system. While the initial results showed an overall successful diagnosis, some issues were observed. To recover the diagnosis performance degradations, additive logics were applied to minimize the diagnosis failures that were not observed in the previous validations of the separate models. The results of a case study were then analyzed in terms of the real-time diagnosis outputs that plant operators would actually face in an emergency situation.

• 한국안전학회지
• /
• 제33권5호
• /
• pp.28-34
• /
• 2018

Recently, various engineering approaches have been widely used in the accident investigation field to identify the cause of the accident and to predict damage by accident. Computational analysis is the most commonly used method of accident investigation technique. This technique is mainly used to identify the mechanism of the accident generation and to determine the cause when it is difficult to reproduce the situation at the time of the accident or when it is impossible to perform a reproduction experiment. In this study, The computational fluid dynamics analysis for nitrogen asphyxiation accident generated by defect of building structural between diffusion outlet and cooling tower was performed to determine the inflow path of the suffocation gas, death possibility by concentration of suffocation gas and predicted the time of death due to the accident using 3D modeling and FLACS program. We can quantify diffusion concentration of asphyxiation gas and predict mechanism of death occurrence by accident and evaluate the consequence Analysis through this study. In the future, This method can be widely used in the field of gas safety by improving the reliability and validity of the analysis.