• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.5
• /
• pp.179-184
• /
• 2016

The usual way used by electric power stations to deliver high levels of generated power is via 6.6kV XLPE (or CV) cables. Depending on the manufacturing technique, installation environment, and usage conditions, the deterioration processes of the power cables start from the instant of operation. Cable junctions may break down in three years from the start of operation due to the manufacturing or construction defects. Otherwise they should be in good working order for 20-30 years. When the cable system (the cable itself and cable junctions combined) deteriorates, fire accidents happen due to the dielectric breakdowns. We have invented a device to monitor the deteriorating status of cables at Korean Western Power Co. Ltd. located in Taean, Chungcheongnam-do province. In this paper, we introduce the device hardware. Using the device, we have measured the insulation resistance and humidity in the sheath of the cables. We present, in analysed results, the effect of humidity on insulation resistance in cable sheaths.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.1
• /
• pp.45-52
• /
• 2018

In this paper, we propose smart digital door lock system using heterogeneous communication. This system has efficient function using RF communication and Internet communication, and realizes access and real image of the passengers by combining camera control technology to secure original competitiveness with existing products. It uses the Internet of things and receive images to and from your smart-phone. And senses human behavior. In the simulated results, the image transmission rate of 90 % or more and the time required to transmit 10,000 images have an average transmission speed of 3 seconds. It is expected to secure competitiveness to increase the security of door lock in the future by enabling minimum security and fire monitoring service in real time.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_1
• /
• pp.1413-1425
• /
• 2023

The increasing frequency of wildfires due to climate change is causing extreme loss of life and property. They cause loss of vegetation and affect ecosystem changes depending on their intensity and occurrence. Ecosystem changes, in turn, affect wildfire occurrence, causing secondary damage. Thus, accurate estimation of the areas affected by wildfires is fundamental. Satellite remote sensing is used for forest fire detection because it can rapidly acquire topographic and meteorological information about the affected area after forest fires. In addition, deep learning algorithms such as convolutional neural networks (CNN) and transformer models show high performance for more accurate monitoring of fire-burnt regions. To date, the application of deep learning models has been limited, and there is a scarcity of reports providing quantitative performance evaluations for practical field utilization. Hence, this study emphasizes a comparative analysis, exploring performance enhancements achieved through both model selection and data design. This study examined deep learning models for detecting wildfire-damaged areas using Landsat 8 satellite images in California. Also, we conducted a comprehensive comparison and analysis of the detection performance of multiple models, such as U-Net and High-Resolution Network-Object Contextual Representation (HRNet-OCR). Wildfire-related spectral indices such as normalized difference vegetation index (NDVI) and normalized burn ratio (NBR) were used as input channels for the deep learning models to reflect the degree of vegetation cover and surface moisture content. As a result, the mean intersection over union (mIoU) was 0.831 for U-Net and 0.848 for HRNet-OCR, showing high segmentation performance. The inclusion of spectral indices alongside the base wavelength bands resulted in increased metric values for all combinations, affirming that the augmentation of input data with spectral indices contributes to the refinement of pixels. This study can be applied to other satellite images to build a recovery strategy for fire-burnt areas.

• Journal of the Society of Disaster Information
• /
• v.14 no.2
• /
• pp.130-140
• /
• 2018

Purpose: In this paper, we propose a design technique for the safety characterization grounding in the construction of the photovoltaic power generation complex which can be useful and useful as an alternative power energy source in our society. In other words, we will introduce the application of safety grounding for each application, which can improve and optimize the reliability of the internal grid from the cell module to the electric room in the photovoltaic power generation complex. Method: We analyze the earth resistivity of the soil in the solar power plant and use the computer program (CDEGS) to analyze the contact voltage and stratospheric voltage causing the electric shock, and propose the calculation and calculation method of the safety ground. In addition, we will discuss the importance of semi-permanent ground electrode selection in consideration of soil environment. Results: We could obtain the maximum and minimum value of ground resistivity for each of the three areas of the data measured by the Wenner 4 - electrode method. The measured data was substituted into the basic equation and calculated with a MATLAB computer program. That is, it can be determined that the thickness of the minimum resistance value is the most favorable soil environment for installing the ground electrode. Conclusion: Through this study, we propose a grounding system design method that can suppress the potential rise on the ground surface in the inner grid of solar power plant according to each case. However, the development of smart devices capable of accumulating big data and a monitoring system capable of real-time monitoring of seismic changes in earth resistances and grounding systems should be further studied.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.5
• /
• pp.637-644
• /
• 2016

This paper is a follow-up to previous papers entitled, "Development of Tunnel-Environment Monitoring System and Its Installation" I [1] and II [2]. The target tunnel of these studies is the Solan Tunnel, which is a loop-type, single-track, 16.7-km-long tunnel located in mountainous terrain and passing through the Baekdudaegan mountain range. It is an ordinary railway tunnel designed for both freight and passenger trains. We analyzed the environmental conditions of the tunnel using temperature and humidity data recorded over approximately one year. The data were recorded using the Tunnel Rough Environment Measuring System (TREMS), which measures environmental data in subway and high-speed train tunnels and is installed in three locations inside the tunnel. Previous studies analyzed environmental conditions inside tunnels located in or near a city, whereas the tunnel in this study is located in a mountainous area. The tunnel conditions were compared with those measured outside the tunnel for each month. Hourly changes during summer and winter periods were also analyzed, and the environmental conditions at different locations inside the tunnel were compared. The results are widely applicable in studies on the thermal environment and air quality of tunnels, as well as for computer analysis of tunnel airflow such as tunnel ventilation and fire simulations.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.9
• /
• pp.18-23
• /
• 2017

The shipyard quay process struggles to control workers and maintain a secure working environment because of the presence of at least 1,000 people. Therefore, safety accidents such as an explosion or a fire are likely to occur. With the recent increase in safety accidents at shipyards, the requirements for safety and process monitoring have been strengthened. Major shipyards are conducting researchto monitor the process in real time and to detect the work environment for safety. In this paper, we propose a safe and accurate evacuation route based on the information of the dangerous area and the user's location based on a mobile application to reduce the casualty accidents in the presence of many personnel in a concentrated area. To do this, we analyze the trend of the fire escape system on the ground building, compare various algorithms for escape route calculation, select appropriate algorithms for this study, and perform programming. A basic experiment was conducted to confirm the results. The proposed method is expected to be used in large ship construction sites, passenger ships and large public facilities to reduce accidents in the case of a safety accident.

• Journal of the Korean Institute of Gas
• /
• v.15 no.6
• /
• pp.8-13
• /
• 2011

All over the nation, a lot of industrial complex utilize gas as their energy source. Possibilities are fire, explosion, and leakage could happen any time in these large complexes. To prevent these tragic accidents and to minimize the damage when the accident occurs, the development of diagnostic technology for these facilities is imperative. The safety check is conducted on an individual and partial basis, currently. Accordingly, the accumulation and improvement of the safety management technology is necessary in order to make all the different checking techniques and management systems compatible, since checking processes, result interpretation techniques, and subsequent prognoses are not the same. The program provides damage scenarios from gas leakage. The output enables policy makers to predict the degree of infliction. Through this program, engineers are able to design an effective gas safety program to operate and maintain ubiquitous gas facilities.

• 한국태양에너지학회:학술대회논문집
• /
• 2009.04a
• /
• pp.102-108
• /
• 2009

Fossil power plants firing lower grade coals or equipped with modified system for NOx controls are challenged with maintaining good combustion conditions while maximizing generation and minimizing emissions. In many cases significant derate, availability losses and increase in unburned carbon levels can be attributed to poor combustion conditions as a result of poorly controlled local fuel and air distribution within the boiler furnace. In order to develop a on-line combustion tuning system, field test was conducted at operating power boiler. During the field test the exhaust gases' $O_2$, NOx and CO was monitored by using a spatially distributed monitoring grid located in the boiler's high temperature vestibule and upper convective back-pass region. At these locations, the flue gas flow is still significantly stratified, and air in-leakage is minimal which enables tracing of poor combustion zones to specific burners and over-fire air ports. using these monitored information we can improving combustion at every point within the furnace, therefore the boiler can operate at reduced excess $O_2$ and gas temperature deviation, reduced furnace exit gas temperature levels while also reducing localized hot spots, corrosive gas conditions, slag or clinker formation and UBC. Benefits include improving efficiency, reducing NOx emissions, increasing output and maximizing availability. Discussion concerning the reduction of greenhouse gases is prevalent in the world. When taking a practical approach to addressing this problem, the best way and short-term solution to reduce greenhouse gases on coal-fired power plants is to improve efficiency. From this point of view the real time optimized combustion tuning approach is the most effective and implemented with minimal cost.

• Journal of the Korean Solar Energy Society
• /
• v.29 no.5
• /
• pp.45-52
• /
• 2009

Fossil power plants firing lower grade coals or equipped with modified system for $NO_x$ controls are challenged with maintaining good combustion conditions while maximizing generation and minimizing emissions. In many cases significant derate, availability losses and increase in unburned carbon levels can be attributed to poor combustion conditions as a result of poorly controlled local fuel and air distribution within the boiler furnace. In order to develop a on-line combustion tuning system, field test was conducted at operating power boiler. During the field test the exhaust gases' $O_2,\;NO_x$ and CO was monitored by using a spatially distributed monitoring grid located in the boiler's high temperature vestibule and upper convective rear pass region. At these locations, the flue gas flow is still significantly stratified, and air in-leakage is minimal which enables tracing of poor combustion zones to specific burners and over-fire air ports. using these monitored information we can improving combustion at every point within the furnace, therefore the boiler can operate at reduced excess $O_2$ and gas temperature deviation, reduced furnace exit gas temperature levels while also reducing localized hot spots, corrosive gas conditions, slag or clinker formation and UBC. Benefits include improving efficiency, reducing $NO_x$ emissions, increasing output and maximizing availability. Discussion concerning the reduction of greenhouse gases is prevalent in the world. When taking a practical approach to addressing this problem, the best way and short-term solution to reduce greenhouse gases on coal-fired power plants is to improve efficiency. From this point of view the real time optimized combustion tuning approach is the most effective and implemented with minimal cost.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.21 no.3
• /
• pp.419-432
• /
• 2019

Most of deep learning model training was proceeded by supervised learning, which is to train labeling data composed by inputs and corresponding outputs. Labeling data was directly generated manually, so labeling accuracy of data is relatively high. However, it requires heavy efforts in securing data because of cost and time. Additionally, the main goal of supervised learning is to improve detection performance for 'True Positive' data but not to reduce occurrence of 'False Positive' data. In this paper, the occurrence of unpredictable 'False Positive' appears by trained modes with labeling data and 'True Positive' data in monitoring of deep learning-based CCTV accident detection system, which is under operation at a tunnel monitoring center. Those types of 'False Positive' to 'fire' or 'person' objects were frequently taking place for lights of working vehicle, reflecting sunlight at tunnel entrance, long black feature which occurs to the part of lane or car, etc. To solve this problem, a deep learning model was developed by simultaneously training the 'False Positive' data generated in the field and the labeling data. As a result, in comparison with the model that was trained only by the existing labeling data, the re-inference performance with respect to the labeling data was improved. In addition, re-inference of the 'False Positive' data shows that the number of 'False Positive' for the persons were more reduced in case of training model including many 'False Positive' data. By training of the 'False Positive' data, the capability of field application of the deep learning model was improved automatically.