• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 춘계학술대회 논문집 전기설비전문위원
• /
• pp.166-168
• /
• 2007

The DGA (Dissolved Gases Analysis) technique has been widely using for fault diagnosis of the power transformers. This technique has a high reliability than other techniques. KEPCO (Korea Electric Power Cooperation) has been using DGA technique since KEPCO established the criteria of DGA in 1985. In this paper, we introduce the DGA criteria of KEPCO and analyze the result of DGA. Also we introduce the cases of thoroughgoing inspection of the power transformers caused by DGA and compare the judgment of DGA with the result of throughgoing inspection.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 제38회 하계학술대회
• /
• pp.95-96
• /
• 2007

Dissolved gas analysis (DGA) is one of the most widely used diagnostic tools for detecting and evaluating faults in electrical equipment. However, interpretation of DGA results is often complex and should always be done with care, involving experienced insulation maintenance personnel. KEPCO (Korea Electric Power Cooperation) has been using DGA technique since KEPCO established the criteria of DGA in 1985. In this paper, we introduce the DGA criteria of KEPCO and analyze the result of DGA. Also we sort pattern in result of DGA. Then, relation between pattern and inner inspection was studied. 67 DGA data was used for analyzing pattern. Some patterns have something to do with cause of incipient fault.

• 융합보안논문지
• /
• 제22권5호
• /
• pp.145-154
• /
• 2022

최근 봇넷의 광범위한 확산과 고도의 정교함은 기업과 사용자뿐만 아니라 국가 간 사이버전에도 심각한 결과를 초래하고 있다. 이 때문에 봇넷을 탐지하고자 하는 연구는 꾸준히 되고 있다. 하지만, DGA 기반의 봇넷은 기존의 시그니처 및 통계 기반의 기술로는 탐지율은 높지만, 오탐율 또한 높은 한계가 있다. 이에 본 논문에서는 DGA 기반의 봇넷을 탐지하고자 문자 기반의 n-gram을 활용한 탐지모델을 제안한다. 제안한 모델을 통해 기존의 탐지 기술의 한계인 탐지율을 높이고 오탐율을 최소화할 수 있다. 다양한 DGA 봇넷에서 사용하는 대규모의 도메인 데이터셋과 정상 도메인에 대한 실험을 통해 기존의 모델보다 성능이 우수함을 확인하였다. 제안된 모델의 오탐율은 2~4% 미만이며 전체 탐지 정확도와 F1 점수는 모두 97.5%임을 확인하였다. 이처럼 본 논문에서 제안한 모델을 통해 DGA 기반의 봇넷에 대한 탐지 및 대응 능력이 향상될 것을 기대한다.

• Journal of Electrical Engineering and Technology
• /
• 제9권2호
• /
• pp.615-621
• /
• 2014

Power transformer is one of the most important equipments in electrical power system. The detection of certain gases generated in transformer is the first indication of a malfunction that may lead to failure if not detected. Dissolved gas analysis (DGA) of transformer oil has been one of the most reliable techniques to detect the incipient faults. Many conventional DGA methods have been developed to interpret DGA results obtained from gas chromatography. Although these methods are widely used in the world, they sometimes fail to diagnose, especially when DGA results falls outside conventional method codes or when more than one fault exist in transformer. To overcome these limitations, fuzzy inference system (FIS) is proposed. 250 different cases are used to test the accuracy of various DGA methods in interpreting the transformer condition.

• 전기전자학회논문지
• /
• 제24권1호
• /
• pp.354-359
• /
• 2020

전력용 변압기의 결함을 검출하고, 고장을 예방하기 위해 유중가스분석 방법이 정기적으로 수행되고 있다. 유중가스분석방법에 의해 변압기 내부의 과열 또는 방전 현상의 발생은 확인할 수 있지만 결함 부위는 내부점검에 의하여 판별하여야 한다. 하지만, 권선 또는 철심 결함은 내부점검으로 확인할 수 없어 DGA만으로는 조치방안을 수립하기가 불가능하다. 본 논문에서는 변압기 내부점검 보고서를 바탕으로 내부 결함 모드를 분석하여 제시하고, DGA에 의한 판별법을 고려하여 내부 결함을 예측할 수 있도록 하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 추계학술대회 논문집 전력기술부문
• /
• pp.141-143
• /
• 2006

Dissolved gas analysis (DGA) is widely used to detect incipient faults in oil-filled electrical equipment. KEPCO make a rule of DGA in 1985. They have been diagnosing power transformer using their DGA criteria. In this paper, we analysis the result of DGA data about transformer in the substation. We try to find out what is cause of an error in DGA diagnosis considering accuracy in extracting gases from mineral oil in transformer. The carbon-monoxide was primary reason of warning in DGA data. We specially consider that aging is a cause of generating of carbon-monoxide in power transformer.

• 전기학회논문지
• /
• 제56권12호
• /
• pp.2084-2090
• /
• 2007

The DGA (Dissolved Gases Analysis) technique has been widely using for fault diagnosis of the power transformers. Some electric power utility company establishes the criteria of DGA to improve reliability, because of difference of operation environment and design of power transformer. In this paper, we introduce intelligent diagnosis system for DGA result of KEPCO (Korea Electric Power Cooperation). This system can classify patterns type of gases ratio that frequently occurs in recent result of gases analysis using Fuzzy Inference. The classification of Patterns let us know that major causes of gases generation based on type of patterns. Finally, Neural Network based on patterns diagnose transformer. NN was trained using result data of DGA of actually faulted transformers recently. Result of intelligent diagnosis system is right well in comparison with actual inner inspection of transformers.

• Journal of Acupuncture Research
• /
• 제19권3호
• /
• pp.107-114
• /
• 2002

Objective : This study was designed to find the most effective and safest way to overcome Lumbago due to blood stasis and sprain involved in a few Meridian Tendino-musculatures by evaluating the effect of two kinds of Dong-gi(Dong-qi) Acupuncture(DGA) and by reporting their side effects. Material : 97 patients of out and admission patients were selected, who were diagnosed with lumbar sprain caused by repetitive bending, heavy weight lifting, unsuitable posture, concussion and falling down and whose Lumbago due to blood stasis and sprain in the concept of oriental medicine. Methods : 97 patients were divided into three groups. One is exclusive DGA group to which DGA and the method retaining needles on the acupoints for about 20 minutes were applied, the other is DGA combined active exercise group in which patients stretched their Meridian Tendino-muscuIatures with their hips moving up and downward repeatedly during DGA, the third is DGA combined passive exercise group in which patients were made to flex or extend their bodies on the auto flexion-distraction table in a prone position, from 10 to 20 degree, during DGA. In each group, bed rest, physical therapy and herbal medicine were used according to symptoms, in addition to DGA. In DGA method, "Su(Shu)" points of the meridian related to the involved Meridian Tendino-musculature were mainly chosen, that is, Sokkol(Shugu, B65), Hugye(Houxi, SI3), ChungJo(Zhongzhu, TE3) were used, for most LBP belonged to Bladder and Gallbladder Meridian Tendino-musculature disorders. Pyong-Bo-Pyong-Sa(Ping-Bu-Ping-Xie) such as Dong-Gi and Yeom-Jeon(Nian-Zhuan) was applied as Bo-Sa method. For evaluation of effectiveness, new score system was devised by severity of pain and range of movement. the score was given twice at patients' first and last visit and the difference between first and last score was regarded as a evaluation scale, the effectiveness was classified into four grade by evaluation scale.(scale : 12-15; excellent, 8-11; good, 4-7; fair, 0-3; bad) Results : 1. Exclusive DGA, DGA combined active exercise and DGA combined passive exercise group showed 97, 87 and 89% in effectiveness. 2. Exclusive DGA, DGA combined active exercise and DGA combined passive exercise group showed no aggravation of pain, range of movement. 3. In blood test of 34 patients, only one patient showed abnormal rise of sGOT, sGPT and $\gamma$-GTP at his first visit and the others didn't show any detrimental change. DGA had no bad influence upon BUN and creatinine of patients. Conclusion : For complex theraphy combining DGA, exercise, physical therapy and Herbal medicine proved to be highly effective on treating lumbago due to blood stasis and sprain, this is expected to be available for clinical use.

• 정보보호학회논문지
• /
• 제28권5호
• /
• pp.1141-1151
• /
• 2018

APT(Advanced Persistent Threat) 공격에서 감염 호스트와 C&C(Command and Control) 서버 간 통신은 공격 대상의 내부로 침입하기 위한 핵심단계이다. 공격자는 C&C 서버를 통해 다수의 감염 호스트를 제어하고, 침입 및 공격 행위를 지시하는데, 이 단계에서 C&C 서버가 노출되면 공격은 실패할 수 있다. 따라서 최근의 경우 DGA(Domain Generation Algorithm)를 통해 C&C 서버의 DNS를 짧은 시간 간격으로 교체하여 탐지를 어렵게 하고 있다. 특히 하루에도 500만개 이상 새로 등록되는 DNS 전부를 검증하고 탐지하는 것은 매우 어렵다. 이러한 문제점을 해결하기 위해 본 논문에서는 정상 DNS와 DGA를 통해 생성된 DNS(DGA-DNS)의 형태적 유사도(similarity) 분석을 이용한 DGA-DNS 탐지와 이를 통해 APT 공격 징후로 판단하는 모델을 제시하고 유효성을 검증한다.

• 한국인공지능학회지
• /
• 제5권1호
• /
• pp.18-28
• /
• 2017

Recently, there are many companies that use systems based on artificial intelligence. The accuracy of artificial intelligence depends on the amount of learning data and the appropriate algorithm. However, it is not easy to obtain learning data with a large number of entity. Less data set have large generalization errors due to overfitting. In order to minimize this generalization error, this study proposed DGA which can expect relatively high accuracy even though data with a less data set is applied to machine learning based genetic algorithm to deep learning based dropout. The idea of this paper is to determine the active state of the nodes. Using Gradient about loss function, A new fitness function is defined. Proposed Algorithm DGA is supplementing stochastic inconsistency about Dropout. Also DGA solved problem by the complexity of the fitness function and expression range of the model about Genetic Algorithm As a result of experiments using MNIST data proposed algorithm accuracy is 75.3%. Using only Dropout algorithm accuracy is 41.4%. It is shown that DGA is better than using only dropout.