• Journal of the Korean Society of Safety
• /
• v.36 no.1
• /
• pp.56-63
• /
• 2021

The narrative texts of industrial accident reports help to identify accident risk factors. They relate the accident triggers to the sequence of events and the outcomes of an accident. Particularly, a set of related keywords in the context of the narrative can represent how the accident proceeded. Previous studies on text analytics for structuring accident reports have been limited to extracting individual keywords without context. We proposed a context-based analysis using a Natural Language Processing (NLP) algorithm to remedy this shortcoming. This study aims to apply Word2Vec of the NLP algorithm to extract adjacent keywords, known as word embedding, conducted by the neural network algorithm based on supervised learning. During processing, Word2Vec is conducted by adjacent keywords in narrative texts as inputs to achieve its supervised learning; keyword weights emerge as the vectors representing the degree of neighboring among keywords. Similar keyword weights mean that the keywords are closely arranged within sentences in the narrative text. Consequently, a set of keywords that have similar weights presents similar accidents. We extracted ten accident processes containing related keywords and used them to understand the risk factors determining how an accident proceeds. This information helps identify how a checklist for an accident report should be structured.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.5
• /
• pp.836-842
• /
• 2016

When an accident occurs in the nuclear power plant, the faulted information might mislead to the high possibility of aggravating the accident. At the Fukushima accident, the operators misunderstood that there was no core exposure despite in the processing of core damage, because the instrument information of the reactor water level was provided to the operators optimistically other than the actual situation. Thus, this misunderstanding actually caused to much confusions on the rapid countermeasure on the accident, and then resulted in multiplying the accident propagation. It is necessary to be equipped with the function that informs operators the status of instrument integrity in real time. If plant operators verify that the instruments are working properly during accident conditions, they are able to make a decision more safely. In this study, we have performed various tests for the fault detection sensitivity of an data-driven empirical model to review the usability of the model in the accident conditions. The test was performed by using simulation data from the compact nuclear simulator that is numerically simulated to PWR type nuclear power plant. As a result of the test, the proposed model has shown good performance for detecting the specified instrument faults during normal plant conditions. Although the instrument fault detection sensitivity during plant accident conditions is lower than that during normal condition, the data-drive empirical model can be detected an instrument fault during early stage of plant accidents.

• International Journal of Highway Engineering
• /
• v.18 no.3
• /
• pp.127-134
• /
• 2016

PURPOSES : Low visibility caused by dark surroundings at nighttime affects the likelihood of accidents, and various efforts, such as installing road safety facilities, have been made to reduce accidents at night. Despite these efforts, the nighttime severity index (SI) in Korea was higher than the daytime SI during 2011-2014. This study determined the factors affecting daytime and nighttime accident severity through a discriminant analysis. METHODS : Discriminant analysis. RESULTS : First, drowsiness, lack of attention, and lighting facilities affected both daytime and nighttime accident severity. Accidents were found to be caused by a low ability to recognize the driving conditions and a low obstacle avoidance capability. Second, road conditions and speeding affected only the daytime accident severity. Third, failure to maintain a safe distance significantly affected daytime accident severity and nonsignificantly affected nighttime accident severity. The majority of such accidents were caused by rear-end collisions of vehicles driving in the same direction; given the low relative speed difference in such cases, the shock imparted by the accidents was minimal. CONCLUSIONS : Accidents caused by a failure to maintain a safe distance has lower severity than do accidents caused by other factors.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.8 no.1
• /
• pp.41-56
• /
• 2000

In the Aircraft Incident Reporting System(AIRS), It is important to collect and gather date about aircraft incidents by means of systemic methods and make it materials for study in the view point of aircraft accident in the future. Especially, the development of such effective tools can be one of main factors determining whether the investigation of potential accident factors succeeds or fails. For such a reason and the purpose of aircraft accident prevention, the AIRS compatible to each county has been developed early and been adopting now in several countries involving USA. First this study examine the actual condition about investigation method tools of potential accident factors used in several countries and investigation and analyze them, finally present the method which can improve more acceptable forms to flight crew used at the KAIRS(Korean AIRS).

• Journal of the Ergonomics Society of Korea
• /
• v.20 no.2
• /
• pp.1-28
• /
• 2001

This paper deals with the selection of the important Influencing Factors (IFs) under accident management situations in nuclear power plants for use in the assessment of human errors. In order to achieve this goal, we collected two types of IF taxonomies, one is the full set IF list mainly developed for human error analysis. and the other is the IFs for human reliability analysis (HRA) in probabilistic safety assessment (PSA). Five sets of IF taxonomy among the full set IF list and ten sets of IF taxonomy among HRA methodologies were collected in the study. From the review and analysis of BRA IFs, we could obtain some insights for the selection of HRA IFs. By considering the situational characteristics of the accident management domain, candidate IFs are chosen. Finally, those IFs are structured hierarchically to be appropriate for the use in the assessment of human error under accident management situation. Three nuclear accidents such as TMI. Chernobyl and JCO were analysed to validate the proposed taxonomy.

• Journal of Power System Engineering
• /
• v.13 no.2
• /
• pp.56-62
• /
• 2009

The fatalities of pedestrian account for about 40.0% of all fatalities in Korea 2005. Vehicle-Pedestrian accident generates trajectory of pedestrian. In pedestrian involved accident, the most important data to inspect accident is throw distance of pedestrian. The throw distance of pedestrian can be influenced by many variables. But existing studies have been done for simple factors. The variables that influence trajectory of pedestrian can be classified into vehicular factors, pedestrian factors, and road factors. The trajectory of pedestrian, dynamic characteristics of multi-body were analyzed by PC-CRASH, a kinetic analysis program for a traffic accident. PC-CRASH enables an analyst to investigate the effect of many variables. The influence of the offset of impact point was analyzed by Working Model. Based on the results, the variables that influence trajectory of pedestrian were vehicular frontal shape, vehicular impact speed, the offset of impact point, the height of pedestrian, friction coefficients of pedestrian. However the weight of pedestrian did not affect trajectory of pedestrian considerably.

• Journal of the Korean Society of Safety
• /
• v.37 no.6
• /
• pp.40-49
• /
• 2022

Simple statistical frequency based analysis, such as Pareto analysis, are widely used in conventional accident analysis. However, due to the dynamic and complex nature of construction works, many factors can simultaneously affect or involve the occurrence of accidents in construction projects. Therefore, the identification of the complex relationship between such factors is important to establish relevant and effective safety management policies and/or programs. In this study, characteristic factors and their relationships' contribution to non-fatal accidents in construction projects are analyzed using the association rule mining (ARM) technique. To this end, a total of 59,202 construction accident data are collected from 2015 to 2019 and the ARM is performed to retrieve specific relationships -named as association rules-among classified factors in the data. Characteristics of the retrieved relationships are analyzed and compared with the results of conventional Pareto analysis. Based on the results, it is found that both fall and trip are notable accident forms having characteristic relations with other factors for non-fatal accidents in construction projects. It is also found that small-scale construction, age of 50s, less than 1 month of working period, and architectural construction are important factors for non-fatal accidents in construction projects.

• Journal of the Korean Society of Safety
• /
• v.14 no.1
• /
• pp.150-157
• /
• 1999

Developed in the study is the analysis of human factors involved in accidents of Korean Construction Projects. The 556 cases are sampled from a survey material 'Serious Accident Cases in the Construction Projects' edited by Korea Industrial Safety Corporation in 1995 through 1997. The analysis of these cases shows that existing classification system is not good for practical applications in real spots since they are difficult for engineers to understand. In this paper, human factors are classified into three groups by extracting the analysis and arrangement of the cases. Futhermore, We'll propose here a new type of accident which is subdivided. If engineers use this type of accident, they will be probably able to analyze efficiently human factors which are involved in accidents and relatied with how it happen. In the case of fall and upset accidents, personal factors seem to be critical when workers are horizontally moving in an unstable manner, and vertically moving without boarding facilities. Futhermore work environmental factors are important when workers release some materials and are performing building and dismantling tasks.

• Journal of the Korean Society of Safety
• /
• v.39 no.1
• /
• pp.104-113
• /
• 2024

Unlike in general manufacturing process, safety management in laboratory-based research area is complicated because the latter generally involves trying untested methods or handling unusual substances in small amounts. Laboratory accidents in South Korea have recently shown an increasing trend. Unfortunately, statistics on such accidents are not officially published by any domestic public agencies. In this study, multivariate analysis was performed on the relationships between variables to develop effective strategies for preventing laboratory accidents. A Cross-Tabulation Analysis of accident-related factors in 179 accident cases revealed that the laboratory type, accident type, and unsafe-act type are all statistically significant, whereas the unsafe condition and management factors differ with the statistical criteria. Furthermore, the results of a Multiple-Correspondence Analysis showed that accidents can be divided largely into three groups having different accident causes and injury types; this confirms the necessity of different strategies to prevent accidents of each type. The findings also reveal differences between the distribution of accident types mentioned in the accident case collection books and actual reported cases. This suggests that an official statistical system administered by a public institution would be necessary for effective prevention of laboratory accidents.

• Journal of Korean Society of Transportation
• /
• v.29 no.3
• /
• pp.93-101
• /
• 2011

In 2008, Korea has observed total 215,822traffic accidents Although the number has decreased since then, the crash rate is still higher than those of other advanced countries. In particular, high rate of pedestrian accidents occurred on urban streets is recognized as a serious problem. The previous studies, however, are not entirely considerate of accident factors by accident type. Inspired by the fact, this study analyzes factors affecting traffic accident by accident type. Using the accident data collected on urban streets in Seodaemun-gu, this paper classifies the accidents into two groups (i.e., vehicle-vs-vehicle and vehicle-vs-person crashes), and analyzes relationships between severity and exogenous variables. For the analysis, Structural Equation Modeling (SEM) is employed to estimate relationships among exogenous factors of traffic accident by each type on urban streets. The resulting model reveals that roadway related factors are highly correlated with the severity of vehicle-vs-vehicle crashes whereas environment factors are with vehicle-vs-person crashes.