• Nuclear Engineering and Technology
• /
• v.56 no.9
• /
• pp.3594-3601
• /
• 2024

It is difficult to detect a small-scale leakage in a nuclear power plant (NPP) quickly and take appropriate action. Delaying these procedures can have adverse effects on NPPs. In this paper, we propose leak flow rate prediction using the bidirectional gated recurrent unit (Bi-GRU) method to detect leakage quickly and accurately in small-scale leakage situations because large-scale leak rates are known to be predicted accurately. The data were acquired by simulating small loss-of-coolant accidents (LOCA) or small-scale leakage situations using the modular accident analysis program (MAAP) code. In addition, to improve prediction performance, data were collected by distinguishing the break sizes in more detail. In addition, the prediction accuracy was improved by performing both LOCA diagnosis and leak flow rate prediction in small LOCA situations. The prediction model developed using the Bi-GRU showed a superior prediction performance compared with other artificial intelligence methods. Accordingly, the accurate and effective prediction model for small-scale leakage situations proposed herein is expected to support operators in decision-making and taking actions.

• Journal of the Korean Society of Safety
• /
• v.32 no.5
• /
• pp.168-178
• /
• 2017

In order to prevent major and chemical accidents, some of the plants which would like to install and operate hazard chemicals handling facilities must submit Off-site Consequence Analysis due to recent arisen leak accidents since 2015. A lot of chemical industrials choose gas detectors as mitigation equipment to early detect gas vapor. The way of placement of gas detectors has two methods; Code-based Design(CBD) and Performance-based Design. The CBD has principles for gas detectors to be installed with consideration for the place that is expected to accumulate gas, and the leak locations according to legal standards and technical guidelines, and has a possibility to be unable to detect by these rules to locate gas detectors by vapor density information. The PBD has two methods; a Geographic Method and Scenario based Method. The Scenario-based Method has been suggested to make up for the Geographic Coverage Method. This Scenario-based Method draw the best optimum placement of gas detectors by considering leak locations, leak speed information, leak directions and etc. However, the domestic placement guidelines just refers to the CBD. Therefore, this study is to compare existing placement location of gas detectors by the domestic CBD with placement locations, coverages and the number of gas detectors in accordance with the Scenario-based Method. Also this study has measures for early detecting interest of Vapor Cloud and suitable placement of gas detectors to prevent chemical accidents. The Phast software was selected to simulate vapor cloud dispersion to predict the consequence. There are two cases; an accident hole size of leak(8 mm) from API which is the highst accident hole size less than 24.5 mm, and a normal leak hole size from KOSHA Guide (1.8 mm). Detect3D was also selected to locate gas detectors efficiently and compare CBD results and PBD results. Currently, domestic methods of gas detectors do not consider any risk, but just depend on domestic code methods which lead to placement of gas detectors not to make personnels recognize tolerable or intolerable risks. The results of the Scenario-based Method, however, analyze the leak estimated range by simulating leak dispersion, and then it is able to tell tolerable risks. Thus it is considered that individuals will be able to place gas detectors reasonably by making objectives and roles flexibly according to situations in a specific plant.

• Journal of the Korean Society of Safety
• /
• v.37 no.6
• /
• pp.25-31
• /
• 2022

In this study, the spill and leak system is developed to provide real-time remote monitoring of industrial complexes where chemical accidents have been occurring every year. The spill and leak monitoring system uses IR-RCD equipment mounted on a 70m-high steel tower to detect chemical substances, thereby detecting chemical accidents such as leaks, fires, and explosions in real time. If IR-RCD equipment can actually detect chemical substances at a long distance, accurate and rapid initial response can be expected. Therefore, in order to confirm that IR-RCD equipment can detect chemical leakage accidents occurring at a long distance, acetone was selected as the experimental substance and a detection experiment was designed. The experiment was conducted using the acetone pool evaporation method at the wharf which was located 1.5 km away from IR-RCD equipment, and it was confirmed whether IR-RCD equipment could detect acetone in real time through the control monitor.

• Journal of Electrical Engineering and Technology
• /
• v.7 no.2
• /
• pp.230-235
• /
• 2012

Cases of insulation breakdown damage of water-cooled generator stator windings occur frequently due to coolant leakage and water absorption worldwide. Such serious accidents may cause not only enormous economic loss but also very serious grid accidents in terms of stable supply of electric power. More than 50 % of domestic generators have been operated for more than 15 years, and leak and water absorption problem of windings are often found during the planned preventive maintenance period. Since 2005, leak and water absorption tests have been performed for total watercooled stator windings after fully drying the inside of the windings. The results are then comprehensively analyzed. The result of the test performed by GE, a foreign manufacturer, for 141 generators showed failures in 80 of them (failure rate: 57 %), whereas in the tests carried out in Korean domestic power plants, only 14 out of 50 generators showed failures (failure rate: 28 %).

• Nuclear Engineering and Technology
• /
• v.53 no.8
• /
• pp.2547-2555
• /
• 2021

The frequency of reactor coolant leakage is expected to increase over the lifetime of a nuclear power plant owing to degradation mechanisms, such as flow-acceleration corrosion and stress corrosion cracking. When loss of coolant accidents (LOCAs) occur, several parameters change rapidly depending on the size and location of the cracks. In this study, leak flow during LOCAs is predicted using a deep fuzzy neural network (DFNN) model. The DFNN model is based on fuzzy neural network (FNN) modules and has a structure where the FNN modules are sequentially connected. Because the DFNN model is based on the FNN modules, the performance factors are the number of FNN modules and the parameters of the FNN module. These parameters are determined by a least-squares method combined with a genetic algorithm; the number of FNN modules is determined automatically by cross checking a fitness function using the verification dataset output to prevent an overfitting problem. To acquire the data of LOCAs, an optimized power reactor-1000 was simulated using a modular accident analysis program code. The predicted results of the DFNN model are found to be superior to those predicted in previous works. The leak flow prediction results obtained in this study will be useful to check the core integrity in nuclear power plant during LOCAs. This information is also expected to reduce the workload of the operators.

• Journal of the Korean Institute of Gas
• /
• v.23 no.2
• /
• pp.17-27
• /
• 2019

In recent years, dangerous materials and gas leak accidents have been frequently occurred. The hazardous materials storage facility accidents are not rapidly controlled when a leak is detected, unlike other chemical plants can be controled. Externally, the human has to approach and respond to the source of leaking directly. As a result, the human and material damage are likely to larger result in the process. The current approach has been passive response after ringing the alarm. In this study, the suggested tracking system of the leak resource is designed system to track the resource actively by utilizing the mobile sensor robot platform, which can be made easily through recent rapid development technology, is verified through prototype system. Thus, a suggested system should pave the way for minimizing the spread and damage of the accident based on the exact site situation of the initial leak and quick and early measures.

• Fire Science and Engineering
• /
• v.28 no.1
• /
• pp.12-19
• /
• 2014

Workplaces handling hazardous chemicals are scattered, because of old-aging facilities are have been operating for more than 20 years, there is still has the risk of an accident. Advanced countries including the UN and strengthen regulation of chemicals, but the frequent leak accidents have become a big issue socially. In the case of subsequent domestic accidental chemical accident, the government and related departments for the overall prevention, preparedness, response system has been checked and improved. In this study, improvements of the related system and the plan of safety management for on the prevention of accidents and the initial response were suggested throughout the analysis of problems on the actual condition of safety management and such as standard of the related systems for handling, management for occurring the main cause of the leak and chemical accidents from hazardous chemicals handling in the workplace.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.5
• /
• pp.957-966
• /
• 2020

According to the recent statistics of the National Industrial Security Center, about 80% of the confidential leak are caused by former and current employees in the case of domestic confidential leak accidents. Most of the information leak incidents by these insiders are due to poor security management system and information leak detection technology. Blocking confidential leak of insiders is a very important issue in the corporate security sector, but many previous researches have focused on responding to intrusions by external threats rather than by insider threats. Therefore, in this research, we design an internal information leak scenario to effectively and efficiently detect various abnormalities occurring in the enterprise, analyze the key indicators of the leak symptoms derived from the scenarios by using data analytics and propose a model that accurately detects leak activities.

• Journal of the Society of Disaster Information
• /
• v.20 no.1
• /
• pp.213-221
• /
• 2024

Purpose: The purpose is to find the optimal way to quickly block the leak in the event of a leak accident in a tank lorry transporting hydrochloric acid aqueous solution, a hazardous chemical, and to carry out effective disaster prevention work to minimize damage caused by the leak. Method: We organized the overall characteristics of hydrochloric acid and accidents that occurred during transportation by accident type and cause, and created a small tank that can be tested assuming a leak situation in a hydrochloric acid tanker, creating an environment similar to the leak situation, and leaking in various ways. I would like to experiment and organize blocking methods. Result: Through experiments, an effective leak blocking method was confirmed. We would like to summarize measures to quickly block a leak in the event of a leak and present the optimal disaster prevention plan that can be applied at the accident site. Conclusion: It has been confirmed that using a combination of adhesive tape and magnets is more effective in blocking leaks. Rapid response is possible by repeatedly training business emergency response teams and product transporters to appropriately select and respond to leak-blocking equipment. Additional research on various leak prevention methods is needed in the future.

• Journal of the Korean Institute of Gas
• /
• v.23 no.6
• /
• pp.74-80
• /
• 2019

Hydrogen refueling stations that use compressed hydrogen at high pressure provide safety distances between facilities in order to ensure safety. Most accidents occurring in hydrogen stations are accidental leaks. When a leak occurs, various types of ignition sources generate a jet flame. Therefore, the analysis of leaked gas diffusion and jet flame due to high pressure hydrogen leakage is one of the most important factor for setting the safety distance. In this study, the leakage accidents that occur in the hydrogen refueling station operated in high pressure environment are simulated for various leakage source sizes. The results of this study will be used as a reference for the future safety standards.