• Journal of the Korean Society of Safety
• /
• v.33 no.1
• /
• pp.54-61
• /
• 2018

In this study, we developed a system for information sharing and cooperation support system among the accident response organizations to enable prompt and efficient response in responding to chemical accidents. In other words, by applying mobile messenger function, it is proposed to improve the chemical accident response system that provides information necessary for accident response promptly and accurately, and facilitates bi-directional communication between accident response organizations and field responders, thereby enabling efficient and organic response. As a result of comparing the information provision time before and after the chemical accident of chemical accident response information sharing system, the ratio of processing of substance information and chemical air diffusion information within 30 minutes was improved by 8% and 32%, respectively. As a result of this study, applying the chemical accident response information sharing system to the chemical accident response is expected to contribute to the improvement of the system and the ability to cope with the accident more effectively.

• Journal of the Korean Society of Safety
• /
• v.33 no.3
• /
• pp.58-64
• /
• 2018

Recently, a lot of accident report documents have accumulated in almost all of industries, including critical information of accidents. Accordingly, text data contained in accident report documents are considered useful information for understanding accident processes. However, there has been a lack of systematic approaches to analyzing accident report documents. In this respect, this paper aims at proposing text analytics approach to extracting critical information on accident processes. To be specific, major causes of the accident occurrence are classified based on text information contained in accident report documents by using both textmining and latent Dirichlet allocation (LDA) algorithms. The textmining algorithm is used to structure the document-term matrix and the LDA algorithm is applied to extract latent topics included in a lot of accident report documents. We extract ten topics of accidents as accident types and related keywords of accidents with respect to each accident type. The cause-and-effect diagram is then depicted as a tool for navigating processes of the accident occurrence by structuring causes extracted from LDA. Further, the trends of accidents are identified to explore patterns of accident occurrence in each of types. Three patterns of increasing to decreasing, decreasing to increasing, or only increasing are presented in the case of a chemical plant. The proposed approach helps safety managers systematically supervise the causes and processes of accidents through analysis of text information contained in accident report documents.

• Journal of the Korean Society of Safety
• /
• v.32 no.5
• /
• pp.179-185
• /
• 2017

Accident analysis is an essential process to make basic data for accident prevention. Most researches depend on survey data and accident statistics to analyze accidents, but these kinds of data are not sufficient for systematic and detailed analysis. We, in this paper, propose an accident classification model that extracts task type, original cause materials, accident type, and the number of deaths from accident reports. The classification model is a support vector machine (SVM) with word occurrence features, and these features are selected based on mutual information. Experiment shows that the proposed model can extract task type, original cause materials, accident type, and the number of deaths with almost 100% accuracy. We also develop an accident ontology to express the information extracted by the classification model. Finally, we illustrate how the proposed classification model and ontology effectively works for the accident analysis. The classification model and ontology are expected to effectively analyze various accidents.

• Nuclear Engineering and Technology
• /
• v.50 no.4
• /
• pp.562-569
• /
• 2018

Recently, human errors have very rarely occurred during power generation at nuclear power plants. For this reason, many countries are conducting research on smart support systems of nuclear power plants. Smart support systems can help with operator decisions in severe accident occurrences. In this study, a smart support system was developed by integrating accident prediction functions from previous research and enhancing their prediction capability. Through this system, operators can predict accident scenarios, accident locations, and accident information in advance. In addition, it is possible to decide on the integrity of instruments and predict the life of instruments. The data were obtained using Modular Accident Analysis Program code to simulate severe accident scenarios for the Optimized Power Reactor 1000. The prediction of the accident scenario, accident location, and accident information was conducted using artificial intelligence methods.

• Journal of the Korean Society of Safety
• /
• v.24 no.3
• /
• pp.79-87
• /
• 2009

The objective of this study is to develop accident scenario models for the risk assessment of railway casualty accidents. To develop these scenario models, hazardous events and hazardous factors were identified by gathering various accident reports and information. Then, the accident scenario models were built up. Each accident scenario model consists of an occurrence scenario model and a progress scenario model. The occurrence scenario refers to the occurrence process of the event before the hazardous event. The progress scenario means the progress process of the event after the hazardous event. To manage a large amount of accident/incident data and scenarios, a railway accident analysis information system was developed using railway accident scenario models. To test the feasibility of the developed scenario models, more than 800 domestic railway casualty accidents that occurred in 2004 and 2005 were investigated and quantitative and qualitative analyses were performed using the developed information system.

• Journal of the Society of Disaster Information
• /
• v.5 no.2
• /
• pp.140-152
• /
• 2009

Recently the occurrence ratio of mechanical accidents in industrial disaster of korea is increased, but very little accident information has been given regarding the prevention of mechanical accidents. In this study, mechanical accidents by the analysis of industrial accident case was examined. And it was proposed the risk assessment method and building database for investigation of risk factors in mechanical accident. As a result, from mechanical accidents database, it was found that the occurrence ratio of mechanical accident by constriction and falling etc. is very high and death ratio by mechanical accident is larger than that of usual accident. And we applied the quantitative risk assessment method proposed by this study in the mechanical accident analysis of a domestic manufacturer. From the results, the risk factors due to constriction, curling, falling and scattering are principal causes of mechanical accidents. These result is similar to that of the analysis of mechanical accidents for recent 12 years in korea.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.19 no.39
• /
• pp.99-116
• /
• 1996

The production activity by human is accompanied by various accidents, resulting in human and property loss. If information on these industrial accident can be collected, organized and analyzed for a period of time and be used in the decision-making process for the purpose of preventing industrial accident, we will be able to get rid of industrial accident and prevent human and property loss and creat a pleasant industrial atmosphere. In order to achieve this goal, the collected information should be accurate, and trusted in the work place or government agency the information is being utilized. This research analyzed the problem in our nation's industrial accident statistics and estimated the number of accidents that are occurring and suggested improvement measures so that the industrial accident statistics can be calculated accurately.

• Journal of the Society of Disaster Information
• /
• v.1 no.1
• /
• pp.121-136
• /
• 2005

Most human-error case of accident database is written by various description and expression because accident database is produced by two or more person. And extracted information by searching of database varies in researcher's judgment criteria and the capability. Furthermore, much time and effort are required to examine manually information related to the human error from each accident case. Accordingly, it is difficult to explore objectively the accidents relevant to the human-error from the accident data base which is accumulated enormously. In this study, to solve these problems, it was developed an searchig method which is not influenced by researcher's judgment criteria and capability. For this, human-error keywords were extracted from a Japanese-English dictionary to examine objectively the accident case related to human-error in data base. This searching method by the human-error keywords can be applicable in most accident databases, although a database will be accumulated in future. Also, using the searching technique of this research, knowledge obtained by searching result can be compared with other research's results by the same method. Although the number of accident case increasese, searching results from database have the objectivity because it is not necessary to modify the based searching method or change the human-error keywords. However, as subject of future investigation, it would be necessary that the extension and investigation on human-error keywords improve and the technique to enhance searching accuracy would be modified.

• Journal of the Society of Disaster Information
• /
• v.4 no.2
• /
• pp.124-136
• /
• 2008

The systematic information management of chemical accidents has been required as a tool for the policy making, system improvement and release of information concerning accident prevention. However, there is not yet a systematic chemical accidents tracking system in Korea, which make confusion among the related government agencies and the parties to accidents that the related statistics are different from each others. In this study, We developed the Chemical Accident Tracking System (CATS) using chemical accident classification which was made up of 12 upper classes, 70 middle classes, 272 lower classes. The CATS is mainly consist list up module, reporting module, searching and statistic module, etc. The CATS is expected to be applied to the information tracking and database system for chemical accidents and improve its manageability.

• Journal of the Ergonomics Society of Korea
• /
• v.35 no.3
• /
• pp.155-163
• /
• 2016

Objective: This study aims to draw the characteristics of occupational accidents occurred in cabling work, and assess accident severity based on occupational injury data. Background: Accident factors and accident risk are different by the place of work in cabling work. Field managers require information on accident prevention that can be easily understood by workers. However, there has been a lack of studies that focus on cabling work in Korea. Method: This study classifies 450 injured persons caused in cabling work by process, and analyzes the characteristics of occupational injuries from the aspects of age, work experience and accident type. This study also analyzes accident frequency and severity of injury. Results: Results show that preparing/finishing (33.3%) was the most common type of cabling process in injuries, followed by maintenance (28.4%), routing/income (23.1%) and wiring/installation (15.1%) process. The critical incidents in the level of risk management were falls from height in the routing/incoming process, and falls from height in the maintenance process. And, incidents ranked as 'High' level of risk management were slips and trips, fall from height and vehicle incident in the preparing/finishing process, and fall from height in the wiring/installation process. Conclusion and Application: The relative frequency of accident and its severity by working process serve as important information for accident prevention, and are critical for determining priorities in preventive measures.