• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1996년도 춘계학술대회 논문집
• /
• pp.403-413
• /
• 1996

Two-phase self-organizing neuro-modeling (SONM). the global SONM and local SONM, is designed for tracking non-stationary manufacturing processes. Radial basis function (RBF) neural network is employed, and self-tuning estimator is also developed for the determination of RBF network parameters on-line. A pattern recognition approach is presented for identifying a correct RBF neural network, which is used for identifying current manufacturing processes. Experimental results showed that the proposed approach is suitable for tracking non-stationary processes.

• 제어로봇시스템학회논문지
• /
• 제4권6호
• /
• pp.738-746
• /
• 1998

This paper presents a neural network-based adaptive controller for a single flexible-link. The control for feedback-error loaming of neural network is designed by using the re-definition approach. The neural network controllers are implemented on an single flexible-link experimental test-bed. The tip response is significantly improved and the vibrations of the flexible modes are damped very fast. Experimental and simulation results are presented of the proposed tip position tracking controllers over the conventional PD-type, passive controllers.

• Journal of Power Electronics
• /
• 제2권1호
• /
• pp.46-54
• /
• 2002

In this paper a neural network controller for achieving maximum power tracking as well as output voltage regulation, for a wind energy conversion system (WECS) employing a permanent magnet synchronous generator is proposed. The permanent magnet generator (PMG) supplies a dc load via a bridge rectifier and two buck-boost converters. Adjusting the switching frequency of the first buck-boost converter achieves maximum power tracking. Adjusting the switching frequency of the second buck-boost converter allows output voltage regulation. The on-time of the switching devices of the two converters are supplied by the developed neural network (NN). The effect of sudden changes in wind speed and/ or in reference voltage on the performance of the NN controller are explored. Simulation results showed the possibility of achieving maximum power tracking and output voltage regulation simulation with the developed neural network controllers. The results proved also the fast response and robustness of the proposed control system.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2000년도 하계학술대회 논문집
• /
• pp.165-168
• /
• 2000

This paper presents the tracking resistance and mechanical strength due to boiling absorption of epoxy resin. The single network structure specimen(E series) formed of epoxy alone and interpenetrating polymer network(IPN) structure specimen(EM series) which epoxy resin was taken as first network and methacrylic acid resin as second network were manufactured. As adding $SiO^2$ filler classified by o[phr], 50[phr] and 100[phr] to those specimens, six kinds of specimens were manufactured and boiled in water during 2, 4, 8, 16, 32 and 64[hours]. As a result, it was confirmed that the tracking breakdown time of E series showed a abrupt decrease with boiling time increasing, but that of EM series was decreasing smoothly. Also, it was verified that the degrading rates of mechanical strength was lowerd according to improvement of adhension strength in case of EM series.

• 제어로봇시스템학회논문지
• /
• 제18권5호
• /
• pp.502-508
• /
• 2012

Heliostat, as a concentrator to reflect the incident solar energy to the receiver, is the most important system in the tower-type solar thermal power plant since it determines the efficiency and ultimately the overall performance of solar thermal power plant. Thus, a good sun tracking ability as well as a good optical property of it are required. Heliostat sun tracking system uses usually an open loop control system. Thus the sun tracking error caused by heliostat's geometrical error, optical error and computational error cannot be compensated. Recently use of sun tracking error model to compensate the sun tracking error has been proposed, where the error model is obtained from the measured ones. This work is a development of heliostat sun tracking error measurement and compensation method using BCS (Beam Characterization System). We first developed an image processing system to measure the sun tracking error optically. Then the measured error is modeled in linear polynomial form and neural network form trained by the extended Kalman filter respectively. Finally error models are used to compensate the sun tracking error. We also developed the necessary image processing algorithms so that the heliostat optical properties such as maximum heat flux intensity, heat flux distribution and total reflected heat energy could be analyzed. Experimentally obtained data shows that the heliostat sun tracking accuracy could be dramatically improved using either linear polynomial type error model or neural network type error model. Neural network type error model is somewhat better in improving the sun tracking performance. Nevertheless, since the difference between two error models in compensation of sun tracking error is small, a linear error model is preferred in actual implementation due to its simplicity.

• 조명전기설비학회논문지
• /
• 제24권2호
• /
• pp.33-38
• /
• 2010

최근 태양광 발전시스템은 정부 에너지 정책에 의해서 널리 보급되고 있다. 여기에 광전지 전력생산의 효율을 높이기 위해서는 견실한 태양 추적식이 필요하다. 하지만 태양추적 식은 추적기술의 미비에 의해서 아직 널리 보급되지 못하고 있다. 이를 해결하기 위해서 본 논문에서는 태양광전지의 최대전력추적을 위해서 태양광센서 및 신경회로망 제어알고리즘을 적용하였다. 태양추적 센서는 평판위에 한 개의 사각기둥과 동, 서, 남, 북 4개의 광센서로 구성된다. 태양추적 2축 제어는 두 개의 모터에 의해서 각각 동작되며, 모터의 제어 입력은 신경회로망 제어 알고리즘에 의해서 계산된다. 제안된 제어방식의 기능은 태양추적광 발전 실험에 의해서 확인하였으며, 본 논문의 태양추적방식은 고정식 보다 32[%]효율을 증가시켰다.

• 방송공학회논문지
• /
• 제23권2호
• /
• pp.186-196
• /
• 2018

본 논문에서는 객체를 추적하기 위해 합성곱 신경망 모델을 이용한 온라인 추적 기법을 제안한다. 오프라인에 모델을 학습시키기 위해서는 많은 수의 훈련 샘플이 필요하다. 이러한 문제를 해결하기 위해, 학습되지 않은 모델을 사용하고, 실험 영상으로부터 직접 훈련 샘플을 수집하여 모델을 갱신한다. 기존의 방법들은 많은 훈련 샘플을 획득하여 모델의 학습에 사용하였지만, 본 논문에서는 적은 수의 훈련 샘플만으로도 객체의 추적이 가능함을 증명한다. 또한 컬러 정보를 활용하여 새로운 손실 함수를 정의하였고 이로부터 잘못 수집된 훈련 샘플로 인해 모델이 잘못된 방향으로 학습되는 문제를 방지한다. 실험을 통해 4가지 비교 방법과 동등하거나 개선된 추적 성능을 보임을 증명하였다.

• 한국화재소방학회논문지
• /
• 제9권1호
• /
• pp.3-9
• /
• 1995

This paper is a study to dectect the tracking owing to deterioration of indoor wiring, and to prevent the electrical fire. After analysing the harmonics of waveshapes in load current and tracking current by FFT, a method of identifying the tracking was developed by using neural network. Fluoscent lamp, witch was mostly used in indoor, was chosen as the load used in this study. When the learning number in neural network was more then 30,000 times, an excellent neural net-work which could correctly identify the tracking was established. Therefore, the result of this study can be utilized as a basic material in various measuring instruments, such as an hotline inslation tester, earth tester in vehicles, and tracking fire alarm device, witch can detect the tracking under the condition of hotline.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2016년도 추계학술대회
• /
• pp.489-492
• /
• 2016

Transportation in the logistics, many business organizations are engaged in monitoring and tracking the vehicles in order to improve logistics services, reduce expenses and secure security in cargo transportation. It is saving time and money by tracking and monitoring vehicles which transport cargo in supply chain of logistics. Therefore the main issue of delivery flow is to improve services, and ensure the safety in transportation system. This article suggests the tracking and monitoring model to keep safety transports on ICT network. It focuses on precise delivery control by monitoring and tracking vehicles to save time and costs. The status of product movement is analyzed for proper decision making. The vehicle embedded with RFID is automatically tracked in the movement process by tracking and monitoring model. The main role keeps safety tracking to reduce costs and to deliver products at proper time and location.

• 한국정보통신학회논문지
• /
• 제7권6호
• /
• pp.1304-1311
• /
• 2003

실세계환경에서 물체를 추적하는 기술은 영상의 지속적인 변화 및 영상데이터 방대함과 처리속도의 문제로 인하여 해결하기 어려운 문제이다. 특히 해상과 같은 환경에서는 더욱 어려운 현실이다. 본 논문에서는 복잡한 환경에서 물체를 추적하고 탐지하기 위한 방법으로 자기조직화 신경망을 사용하여 구성하였다. 본 논문에서의 접근 방법은 코호넨의 자기 조직화 신경망 분석 기법과 영역확장 기법 및 에너지 최소화함수를 이용하여 물체 추적시스템을 구성하였다. 자기조직화 신경망은 하나의 프레임 내에서 이동하는 물체의 중심점을 탐지할 수 있다. 그리고 연속적인 영상에서 이전에 탐지되어진 뉴런의 위치를 이용하여 물체를 추적할 수 있다. 자기조직화 신경망을 이용한 물체 추적의 실험결과 다양한 환경의 변화에서도 물체의 추적이 가능함을 알 수 있었다.