• 한국화재소방학회논문지
• /
• 제29권4호
• /
• pp.39-48
• /
• 2015

본 논문은 화재위험성이 높은 산업용 덕트 내부의 화재를 예방하고 화재로 인한 피해를 최소화하기 위한 덕트전용 지능형 화재감지시스템 개발에 관한 연구이다. 덕트 화재위험성을 파악하기 위해 산업용 덕트가 많이 사용되는 대구섬유공단으로 중심으로 화재위험성을 분석하였고, 이를 바탕으로 덕트 화재를 예방하고 피해를 최소화 할 수 있는 전용 화재감지기 및 화재수신기를 설계 제작하여 그 성능을 확인하였다. 성능실험결과 덕트전용 지능형 화재감지시스템의 경우 적응성 및 온도정확도가 우수한 것으로 나타났다. 덕트내부의 실시간 온도모니터링을 통해 화재발생시 설정온도에 따른 연동설비의 단계별 제어로 덕트내부화재를 효율적으로 진압할 수 있는 것을 확인할 수 있었다.

• 플랜트 저널
• /
• 제4권3호
• /
• pp.66-72
• /
• 2008

The vibration of steam turbine is caused by Mass unbalance, Shaft misalignment, Oil whip and rubbing etc. But in turbine which is normally operated and maintained, the Mass unbalance component possesses the greatest portion. Our power plant has two steam turbines in capacity of 200 MW and 135 MW respectively and each turbine is supported by 6 journal bearings. However, we had many difficulties because the vibration amplitude of #3 and #4 Bearings was high during the start-up and operation mode change of steam turbine. But, with this study, we completely solved the vibration problem caused by the mass unbalance of #1 steam turbine. Until a recent date, #3 and #4 bearings which support high pressure turbine for #1 steam turbine had shown about $135{\mu}m$ in vibration amplitude (sometimes it increased to $221{\mu}m$ maximum. alarm: 6 mils, trip: 9 mils) at base load. After applying the study, they decreased to about $45{\mu}m$ maximum. It is a result from that we did not change the setting value of bearing alignment and only changed the assembly position of internal parts in Synchro clutch coupling rachet wheel which links between high pressure turbine and low pressure turbine, and increased the internal gap and machining of the Pawl cage surface. In the operation of steam turbine, if the vibration value increases by 1X, we should reduce the vibration of bearing by weight balancing. However, unless the vibration of bearing is declined by the balancing, we will have to disassemble and check the component and find the cause. In this study, we researched the way to lower mass unbalance that is 1X vibration component which has the greatest portion of vibration generated by steam turbine and we got good result by applying the findings of this study.

• 한국전산유체공학회:학술대회논문집
• /
• 한국전산유체공학회 2008년도 춘계학술대회논문집
• /
• pp.232-235
• /
• 2008

The vibration of steam turbine is caused by Mass Unbalance, Shaft Misalignment, Oil Whip and Rubbing etc. but in turbine which is normally operated and maintained, the Mass Unbalance component possesses the greatest portion. Our power plant has two steam turbines in capacity of 200MW and 135MW respectively and each turbine is supported by 6 journal bearings. However, we had many difficulties because the vibration amplitude of No 3 and 4 Bearings was high during the start-up and operation mode change of steam turbine. But, with this study, we completely solved the vibration problem caused by the mass unbalance of No 1 steam turbine. Until a recent date, No 3 and 4 bearings which support high pressure turbine for No 1 steam turbine had shown about 135${\mu}$m in vibration amplitude (sometimes it increased to 221${\mu}$m maximum. alarm: 6mils, trip: 9mils) at base load. After applying the study, they decreased to about 40${\mu}$m maximum. It is a result from that we did not change the setting value of Bearing Alignment and only changed the assembly position of internal parts in Synchro Clutch Coupling Rachet Wheel which links between high pressure turbine and low pressure turbine, and increased the internal gap and machining of the Pawl stopper surface. In the operation of steam turbine, if the vibration value increases by 1X, we should reduce the vibration of bearing by weight balancing. However, unless the vibration of bearing is declined by the balancing, we will have to disassemble and check the component and find the cause. In this study, We researched the way to lower mass unbalance that is 1X vibration component which has the greatest portion of vibration generated by steam turbine and We got good result by applying the findings of this study.

• 한국정보통신학회논문지
• /
• 제21권9호
• /
• pp.1718-1724
• /
• 2017

최근 IoT기반으로 가전제품을 실시간 모니터링을 하는 스마트 플러그가 활성화 되고 있다. 이를 통해 상시 실시간 에너지 소비 모니터링을 통한 소비자의 에너지 절약 유도를 하고, 소비자 설정 기반의 알람 기능을 통해 소비전력을 절감하는 효과를 보고 있다. 본 논문에서는 이러한 실시간 모니터링을 위해 벽 전원 콘센트에서 나오는 교류 전류를 측정한다. 이때, 가전제품마다의 전류 패턴을 분류하고 어떤 제품이 동작하는지 판단을 위해 딥러닝(Deep learning)으로 실험하였다. 전류 패턴의 학습으로 제품의 종류에 따른 인식 성능을 검증하기 위하여, 교차 검증 방법과 붓스트랩(Bootstrap) 검증 방법을 이용하였다. 또한 Cost function과 학습 성공률(Accuracy)이 Train 데이터와 Test 데이터가 동일함을 확인하였다.

• Healthcare Informatics Research
• /
• 제24권4호
• /
• pp.381-386
• /
• 2018

Objectives: This study aimed to describe the process of utilizing a mobile application for ecological momentary assessment (EMA) to collect data on stress and mood in daily life setting. Methods: A mobile application for the Android operating system was developed and installed with a set of questions regarding momentary mood and stress into a smartphone of a participant. The application sets alarms at semi-random intervals in 60-minute blocks, four times a day for 7 days. After obtaining all momentary affect and stress, the questions to assess the usability of the mobile EMA application were also administered. Results: The data were collected from 97 police officers working in Gyeonggi Province of South Korea. The mean completion rate was 60.0% ranging from 3.5% to 100%. The means of positive and negative affect were 18.34 of 28 and 19.09 of 63. The mean stress was 17.92 of 40. Participants responded that the mobile application correctly measured their affect ($4.34{\pm}0.83$) and stress ($4.48{\pm}0.62$) of 5-point Likert scale. Conclusions: Our study investigated the process of utilizing a mobile application to assess momentary affect and stress at repeated times. We found challenges regarding adherence to the research protocol, such as completion and delay of answering after alarm notification. Despite this inherent issue of adherence to the research protocol, the EMA still has advantages of reducing recall bias and assessing the actual moment of interest at multiple time points that improves ecological validity.

• 한국안전학회지
• /
• 제38권3호
• /
• pp.35-42
• /
• 2023

This study analyzed the current and temperature characteristics of major components of an induction motor during normal and abnormal operations as functions of the difference in the rated capacities of medium and large-sized motors widely used in industrial settings. The temperature rise equation of the induction motor winding was derived through locked-rotor operation experiments and linear regression analysis. When the ambient temperature is 40 ℃, the time to reach 155 ℃, the temperature limit of the insulation class (F class) of the winding of the induction motor, was confirmed to be 48 seconds for the 2.2 kW induction motor and 39 seconds for the 3.7 kW induction motor. This means that when the rated capacity is large or the installation environment is high temperature, the time to reach the temperature limit of the insulation class during locked-rotor operation is short, and the risk of insulation deterioration and fire is high. In addition, even if the EOCR (Electronic Over Current Relay) is installed, if the setting time is excessively set, the EOCR does not operate even if the normal and locked-rotor operation of the induction motor is repeated, and the temperature limit of the insulation grade of the winding of the induction motor is exceeded. The results of this study can be used for preventive measures such as the promotion of electrical and mechanical measures for the failure of induction motors and fire prevention in industrial sites, or the installation of fire alarm systems.

• 한국항행학회논문지
• /
• 제27권6호
• /
• pp.865-870
• /
• 2023

본 논문은 LiDAR (light detection and ranging) 센서를 활용하여 블랙아이스를 검출하는 새로운 방법을 제안합니다. 센서는 작고 비용이 저렴하면서도 높은 정확성을 가진 거리 측정 센서로 온도와 경사각을 다르게 하여 아스팔트와 블랙아이스의 각도를 구별하는 데 사용됩니다. 이 센서의 거리 측정 오차율은 대략 ±1 cm로 블랙아이스와 아스팔트을 구별하는 데에는 일부 오차가 발생할 수 있습니다. 본 논문에서는 정확성을 높이기 위한 추가적인 연구와 개선이 필요함을 지적하며 이를 통해 더욱 정확한 블랙아이스 검출 방법을 제안합니다.

• 한국빅데이터학회지
• /
• 제7권1호
• /
• pp.125-137
• /
• 2022

운송 산업은 우리나라의 3면이 바다로 둘러싸여 있는 지리적 요건과 자원 소비량의 대부분을 수입에 의존하는 자원 빈곤 문제로 인해 중요한 산업 중 하나이다. 그 중에서도 해운업의 비중은 운송 산업의 대부분을 차지할 정도로 크며, 해운업에서의 유지보수는 선박의 운영 효율성 개선 및 비용 감소에 있어서도 중요하다. 그러나 현재 선박이 유지보수를 위해 일정기간 주기로 검사가 시행되고, 이에 따라 시간과 비용이 발생하며 원인규명도 제대로 되지 않고 있다. 따라서 본 연구에서는 제안 방법론인 LSTM-AutoEncoder를 활용해 실제 선박 운항 데이터에 대해 시점을 고려하여 선박 고장의 원인이 될 수 있는 이상 탐지를 수행한다. 또한 클러스터링을 통해 군집화를 수행하고 이상치에 대해 요인별로 그룹화를 통해 선박 메인엔진 고장의 잠재 원인을 규명한다. 이는 선박의 다양한 정보에 대해 보다 빠르게 모니터링이 가능하고, 이상 정도를 식별할 수 있다. 또한 현재 선박의 고장 감시시스템에 있어서도 구체화된 경보 점 설정과 고장 진단 체계를 갖추고, 유지보수시점을 찾는 데 도움을 줄 수 있을 것이다.