• 제어로봇시스템학회논문지
• /
• 제9권11호
• /
• pp.874-882
• /
• 2003

The condition assessment of engineering systems has increased in importance because the manpower needed to operate and supervise various plants has been reduced. Especially, induction motors are at the core of most engineering processes, and there is an indispensable need to monitor their health and performance. So detection and diagnosis of motor faults is a base to improve efficiency of the industrial plant. In this paper, a model-based fault detection system is developed for induction motors, using steady state vibration signals. Early various fault detection systems using vibration signals are a trivial method and those methods are prone to have missed fault or false alarms. The suggested motor fault detection system was developed using a model-based reference value. The stationary signal had been extracted from the non-stationary signal using a data segmentation method. The signal processing method applied in this research is FFT. A reference model with spectra signal is developed and then the residuals of the vibration signal are generated. The ratio of RMS values of vibration residuals is proposed as a fault indicator for detecting faults. The developed fault detection system is tested on 800 hp motor and it is shown to be effective for detecting faults in the air-gap eccentricities and broken rotor bars. The suggested system is shown to be effective for reducing missed faults and false alarms. Moreover, the suggested system has advantages in the automation of fault detection algorithms in a random signal system, and the reference model is not complicated.

• 한국전자통신학회논문지
• /
• 제12권2호
• /
• pp.331-336
• /
• 2017

화재 재해를 예방하기 위해 조기 화재 탐지 기술의 필요성이 증대되고 있다. 화염 및 연기를 감지하기 위해 열, 연기 및 불꽃에 대한 센서 감지 장치가 널리 사용되고 있으나, 이 시스템은 센서 주변 환경의 요소에 따라 제한된다. 이 문제들을 해결하기 위해 다수의 이미지 기반 화재 탐지 시스템이 개발되고 있다. 본 논문에서는 카메라 입력 이미지로 부터 합성곱 신경망을 이용하여 연기 이미지와 불꽃 이미지에 대한 학습을 통해 특징 맵을 추출하고, 이를 사용하여 다른 입력 이미지를 연기와 불꽃으로 분류하는 이미지 기반 화재 감지 시스템을 구현하였다. 다양한 조건의 이미지를 대상으로 실험한 결과 연기와 불꽃으로 분류하는데 우수한 성능을 보여주었다.

• 한국자동차공학회논문집
• /
• 제6권6호
• /
• pp.210-217
• /
• 1998

This paper describes the method for detection of the misfired cylinder using the pressure fluctuations occurred in the exhaust system on an MPI gasoline engine. If misfire is occurred in the cylinder of the gasoline engine, the power of engine gets lost, the fuel consumption and the exhaust emission are increased and the vibration is caused by unsteady torque. Therefore early detection and correction of misfire play a very important role in the proper performance and the exhaust emission. This paper suggests method of misfire detection which affect engine performance. The method is a comparison of average pressure index during the displacement period. Experimental results showed that the method using the pressure fluctuations in the exhaust system is proven to be effective in the detection of misfire on gasoline engine regardless loads and revolutions of the engine. In addition, this method, using the pressure fluctuations in exhaust system is easier than other methods and is not a need of additional reconstruction of engine.

• 방재기술
• /
• 통권19호
• /
• pp.17-21
• /
• 1995

This is to study installation standards of aspirating devices and detectors, which are components of ADS(aspirating fire detection system). The BFPSA(British Fire Protection System Association) code was mainly referred is studying. ADS aspirated air and smoke through the pipe and then checks if there is fire or not. It is now in the limelight because it can early alarm in case of fire and prevent false-alarming.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2005년도 추계종합학술대회
• /
• pp.1015-1018
• /
• 2005

In this paper, we introduce about a new class to analysis of partial discharge signal based on Fuzzy model. We can early diagnose life of power cable through detection of partial discharge signal. However, partial discharge signal detector is difficult because of partial discharge signal is very non-linear. Also, it is very difficult work that separate partial discharge signal from noise. We constructed partial discharge accumulation detection system that use Labview for detection of non-linear partial discharge signal. And analyzed partial discharge signal that is detected by Labview system utilizing Fuzzy model.

• Journal of Information Processing Systems
• /
• 제9권4호
• /
• pp.621-632
• /
• 2013

The most important things for a forest fire detection system are the exact extraction of the smoke from image and being able to clearly distinguish the smoke from those with similar qualities, such as clouds and fog. This research presents an intelligent forest fire detection algorithm via image processing by using the Gaussian Mixture model (GMM), which can be applied to detect smoke at the earliest time possible in a forest. GMMs are usually addressed by making the model adaptive so that its parameters can track changing illuminations and by making the model more complex so that it can represent multimodal backgrounds more accurately for smoke plume segmentation in the forest. Also, in this paper, we suggest a way to classify the smoke plumes via a feature extraction using HSL(Hue, Saturation and Lightness or Luminanace) color space analysis.

• 한국화재소방학회논문지
• /
• 제27권5호
• /
• pp.15-18
• /
• 2013

본 연구는 자연 발생적인 화재 및 방화자에 의한 화재를 탐지하는 고효율 저비용의 옥외형 화재경보시스템으로 중소문화재, 천연기념물 및 옥외 시설물 등 화재 발생 시 관리 감시가 취약한 곳을 대상으로 한 소방시스템의 옥외 적용시 성능 및 시험에 대한 것이다. 재래적 화재감지시스템으로부터 탈피하여 지능적인 이동형 무인 화재감지시스템의 도입을 위해 화재경보시스템 성능시험, 기능시험, 옥외 환경시험, 불꽃시험 및 EMI/EMS 적합시험 등을 실시하였다. 성능시험, 기능시험, 불꽃시험 및 옥외방치시험을 3개월간 실시한바 양호하였고, 온도변화 성능시험도 $-30{\sim}70^{\circ}C$에서 양호하였으며 EMI/EMS 시험도 적합하였다. 불꽃검출거리는 75 m까지 증가되었고 대기모드 전원은 4시간 증가, 운영모드 전원에서의 동작시간은 3일까지 가능하였으며 센서뿐만 아니라 영상으로 상황을 인지하는데 적합함을 확인하였다.

• 정보처리학회논문지B
• /
• 제18B권4호
• /
• pp.213-220
• /
• 2011

본 논문은 조기 화재 경보 시스템에서 예측하지 못한 위험요소들의 이벤트에 즉각 응답하는 비디오 기반의 효과적인 4단계 연기 감지 방법을 제안한다. 첫 번째 단계에서는 근사 미디언(approximate median) 방법을 사용하여 비디오의 현재 프레임에서 움직이는 영역들을 분리한다. 두 번째 단계에서는 연기의 칼라 기반 분리 기법을 사용하여 이러한 움직이는 영역들로부터 후보 연기 영역을 선택한다. 세 번째 단계에서는 특징추출 알고리즘을 사용하여 연기의 움직임이나 지역 불규칙성과 같은 후보 연기 영역들의 특징을 분석하여 연기의 다섯 가지 특징 파라미터를 추출한다. 네 번째 단계에서는 추출된 다섯 가지 특징 파라미터를 K-nearest neighbor (KNN) 알고리즘의 입력으로 사용하여 후보 연기 영역이 연기인지 아닌지를 구분한다. 모의실험 결과, 제안하는 4 단계 연기 감지 방법은 기존의 연기 감지 알고리즘들과 비교하여 연기감지의 정확도에서 우수한 성능을 보였고, 또한 오픈된 넓은 공간에서도 높은 신뢰성과 낮은 오류 경보율을 보였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권9호
• /
• pp.4342-4366
• /
• 2016

Congestion control in Cluster Wireless Sensor Networks (CWSNs) has drawn widespread attention and research interests. The increasing number of nodes and scale of networks cause more complex congestion control and management. Active Queue Management (AQM) is one of the major congestion control approaches in CWSNs, and Random Early Detection (RED) algorithm is commonly used to achieve high utilization in AQM. However, traditional RED algorithm depends exclusively on source-side control, which is insufficient to maintain efficiency and state stability. Specifically, when congestion occurs, deficiency of feedback will hinder the instability of the system. In this paper, we adopt the Additive-Increase Multiplicative-Decrease (AIMD) adjustment scheme and propose an improved RED algorithm by using neighbor feedback and scheduling scheme. The congestion control model is presented, which is a linear system with a non-linear feedback, and modeled by Lur'e type system. In the context of delayed Lur'e dynamical network, we adopt the concept of cluster synchronization and show that the congestion controlled system is able to achieve cluster synchronization. Sufficient conditions are derived by applying Lyapunov-Krasovskii functionals. Numerical examples are investigated to validate the effectiveness of the congestion control algorithm and the stability of the network.

• Clinical and Experimental Pediatrics
• /
• 제56권7호
• /
• pp.271-274
• /
• 2013

Brain insults, including neurotrauma, infection, and perinatal injuries such as hypoxic ischemic encephalopathy, generate inflammation in the brain. These inflammatory cascades induce a wide spectrum of cytokines, which can cause neuron degeneration, have neurotoxic effects on brain tissue, and lead to the development of seizures, even if they are subclinical and occur at birth. Cytokines are secreted by the glial cells of the central nervous system and they function as immune system mediators. Cytokines can be proinflammatory or anti-inflammatory. Interleukin (IL)-$1{\beta}$ and IL-8 are proinflammatory cytokines that activate additional cytokine cascades and increase seizure susceptibility and organ damage, whereas IL-1 receptor antagonist and IL-10 act as anti-inflammatory cytokines that have protective and anticonvulsant effects. Therefore, the immune system and its associated inflammatory reactions appear to play an important role in brain damage. Whether cytokine release is relevant for the processes of epileptogenesis and antiepileptogenesis, and whether epileptogenesis could be prevented by immunomodulatory treatment should be addressed in future clinical studies. Furthermore, early detection of brain damage and early intervention are essential for the prevention of disease progression and further neurological complications. Therefore, cytokines might be useful as biomarkers for earlier detection of brain damage in high-risk infants.