• 인지과학
• /
• 제21권2호
• /
• pp.309-338
• /
• 2010

본 논문에서는 사지가 마비되어 신체를 움직이지 못하지만 뇌의 기능은 살아있는 장애인들을 위하여, 생각만으로 외부의 장치를 제어할 수 있도록 하는 뇌-컴퓨터 인터페이스(BCI: Brain-Computer Interface) 기술을 연구하였다. 신경생리학 분야에서의 연구 결과에 의하면, 신체를 움직이는 상상을 할 경우, 뇌의 운동/감각 피질 영역에서는 $\beta$파(14-26 Hz)와 $\mu$파(8-12 Hz)가 억제/증가되는 ERD/ERS(Event-Related Desynchronization / Synchronization) 현상이 발생한다고 알려져 있다. 본 연구에서는 이를 기반으로 혀, 발, 왼손, 오른손의 동작 상상을 자극으로 이용하여 변화하는 뇌 신호 패턴을 실시간으로 분석하여 피험자의 생각을 읽을 수 있도록 하였으며, 상 하 좌 우의 네 방향으로 이동할 수 있도록 하는 마우스 제어 인터페이스를 구현하였다. 동작 상상 시 발생하는 뇌 신경 활동의 변화를 관측하기 위해서 뇌에 손상을 주지 않으면서도 높은 시간 해상도로 측정이 가능한 비침습적 뇌전도(EEG: ElectroEncephaloGraphy)를 이용하였다. 그러나 뇌전도 신호는 특성상 신호의 크기가 미약하고, 잡음의 영향을 많아 분석이 어렵다. 따라서 이를 극복하기 위해 통계적 방법을 기반으로 한 기계학습 기법인 CSP(Common Spatial Pattern)와 선형판별 분석(Linear Discriminant Analysis)을 이용하여 서로 다른 동작 상상에 의해 발생하는 뇌 신호들 간의 분산이 최대가 되도록 신호를 변환하여 인식 성능을 높일 수 있었다. 또한 분석된 뇌 신호의 시각화를 통해, 기존에 알려진 뇌의 해부학적, 신경생리학적 지식과 일치하는 ERD/ERS 현상이 발생하는 것을 확인할 수 있었다.

• 수산해양기술연구
• /
• 제28권2호
• /
• pp.144-150
• /
• 1992

This paper describes an application of artificial neural network to diagnose the defects of rotating machiner. Induction motor was used to the object of defect diagnosis. For defect diagnosis, the frequency spectrum of vibration was utilized. Learning method of applied neural network was back propagation. Neural network has following advantage; Once it has been learned, inference time is very short and it can provide a reasonable conclusion regardless of insufficient input data. So, this defect diagnosis system can be used superiorly to rule based expert system as quality inspection of rotating machinery in the shop.

• 조명전기설비학회논문지
• /
• 제26권10호
• /
• pp.44-51
• /
• 2012

The purpose of this study is development of the diagnosis system to preventative maintenance in the on-board measuring systems for in-cab electric inspection systems of high speed railway. The on-board measuring systems can inspect precisely whether ground signal system operate stably. In this paper, we recognize characteristics of the track circuits and confirm whether the wave of current matches the on-board measuring data through the electric modeling method for high speed railway. it is necessary to develop GUI visual programs that can simulate abnormalities of the on-board measuring data in many ways, and the visual program is designed to diagnosis in the case of track circuit equipment's function decreased in advance.

• 소음진동
• /
• 제2권4호
• /
• pp.281-292
• /
• 1992

Two types of vibration problems are encountered in industrial field: active isolation and passive isolation. In a passive type of vibration isolation, a foundation of a delicated machinery such as TEM, SEM, inspection- probe test, photolithograph, etc. is designed to have a vibration amplitude lower than an acceptable limit. In an active type, the isolation is focused on the vibration reduction caused by the machine itself(pump, motor, press, compressor, etc.). The foundation for such a machine should be so designed as to reduce the transmitted vibration below the permissible level prescribed. At any case, a transmissibility and stability must to be considered. Since an active isolation type is aimed for a vibration source, it is useful to isolate the transmitted vibrations energy from a major vibration source at the specific location. In this paper, a designed methodology of double anti-vibration system has been examined in order to have low transmissibility and reliable stability. Also experiment of scale model behavior has been conducted. Finally, the experiment output of the transfer function is compared to the analytical data.

• 한국구조물진단유지관리공학회 논문집
• /
• 제22권4호
• /
• pp.91-99
• /
• 2018

암반사면을 안전하고 효과적으로 해석하기 위해서 암반의 역학적 특성을 면밀하게 조사해야 한다. 하지만 클리노미터를 사용한 절리조사의 한계점으로 인해 이를 보완한 새로운 측정법의 연구가 필요하다. 본 연구에서는 절리방향의 특성을 분석하기 위해 절리의 방향성을 현장에 적용할 수 있는 절리조사 측정장비를 개발하였다. 개발된 측정장비는 해석 소프트웨어와 하드웨어로 구분된다. 하드웨어는 암반 절리 방향성을 측정하는 측정모듈, 측정자료를 전송하는 전송모듈로 구성되었다. 소프트웨어는 측정모듈을 통해 얻은 데이터로부터 절리의 방향성을 분석하기 위해 개발하였으며 Drone Joint Orientation Survey Measurement로 명명하였다. 개발된 측정장비는 접근이 어려운 지역 등 조사자가 측정할 수 없는 경우에 현장적용성이 양호하며 절리의 방향성에 대한 실내시험결과를 효과적으로 분석할 수 있었다.

• 산업경영시스템학회지
• /
• 제40권1호
• /
• pp.57-64
• /
• 2017

In order to reduce damages to major railroad components, which have the potential to cause interruptions to railroad services and safety accidents and to generate unnecessary maintenance costs, the development of rolling stock maintenance technology is switching from preventive maintenance based on the inspection period to predictive maintenance technology, led by advanced countries. Furthermore, to enhance trust in accordance with the speedup of system and reduce maintenances cost simultaneously, the demand for fault diagnosis and prognostic health management technology is increasing. The objective of this paper is to propose a highly reliable learning model using various machine learning algorithms that can be applied to critical rolling stock components. This paper presents a model for railway rolling stock component fault diagnosis and conducts a mechanical failure diagnosis of motor components by applying the machine learning technique in order to ensure efficient maintenance support along with a data preprocessing plan for component fault diagnosis. This paper first defines a failure diagnosis model for rolling stock components. Function-based algorithms ANFIS and SMO were used as machine learning techniques for generating the failure diagnosis model. Two tree-based algorithms, RadomForest and CART, were also employed. In order to evaluate the performance of the algorithms to be used for diagnosing failures in motors as a critical railroad component, an experiment was carried out on 2 data sets with different classes (includes 6 classes and 3 class levels). According to the results of the experiment, the random forest algorithm, a tree-based machine learning technique, showed the best performance.

• 대한임상검사과학회지
• /
• 제45권2호
• /
• pp.77-85
• /
• 2013

Intraoperative Neurophysiological Monitoring (INM) is very useful in monitoring the motorsensory pathway and vascular circulation system during intraspinal, or intracranial neurosurgery. Brainstem Auditory Evoked Potentials (BAEPs) are for detecting the problems along the auditory pathways including, the eighth cranial nerve and brainstem. Motor Evoked Potentials (MEPs) is a useful adjunct to conventional monitoring of Somato-sensory Evoked Potentials (SEPs) during surgery. Visual Evoked Potentials (VEPs) has been regarded as having limited significance for the preservation of visual function during neurosurgical procedures. In this paper, we propose that the most appropriate averaging of the number of inspections in the inspection of each used in the operative field, is good and efficient, functionally.

• 전기의세계
• /
• 제26권3호
• /
• pp.76-83
• /
• 1977

The choice of control method and circuit must be decided after a broad inspection with the characteristics of load and control elements as well as that of electric and mechanical nature. In the present study, Pulse width modulated(PWM) SCR chopper was chosen and for the electric commutation, Jones' forced method was taken bacause of its having enough reverse bias energy. Objectives of experimentation by this system are; 1) the condition of SCR as a gate trigger pulse. 2) the observation of phenomena at the time of forced commutation 3) the experimentation on characteristics of speed control by PWM chopper. Above experimentation shows good characteristics, however, in the limit of narrow gap between the ON and OFF pulses, a complete control was not possible. So, that must be the point to be studied further alone with the harmonics influence.

• Journal of electromagnetic engineering and science
• /
• 제11권4호
• /
• pp.298-303
• /
• 2011

A capsular endoscope (CE) for inspection of the large intestine requires a motor for backward navigation against the autonomous travel in the intestine. This study proposes an HF power system for generating a magnetic field and for delivering wireless power to the internal or implanted medical devices. The magnetic field is generated by a wound coil (L) around a wooden frame, and the current is driven to the coil through a resonating capacitor (C). The characteristics of the resonance frequency shifting of the L-C series circuit are analyzed. A stable magnetic field intensity in the field coil is maintained by a specially designed frequency tracking system that automatically follows the L-C resonance frequency. Testing confirmed that the oscillation system tracks well the parameter changes of the electric components caused by the operating conditions or environmental variations.

• 항공우주시스템공학회지
• /
• 제11권5호
• /
• pp.42-49
• /
• 2017

고체추진 로켓(SRM)은 모터케이스, 점화기, 추진제, 노즐, 절연체, 제어 및 구동장치 등으로 구성되어 있으며 액체로켓과 다르게 노즐을 냉각시킬 수 없어 고온 및 고속의 연소가스에 의해 침식(Erosion)이 발생한다. 이러한 침식현상은 노즐목의 형상 변화를 일으키며 로켓의 추력 성능을 감소시킨다. 로켓 노즐의 재질은 침식현상을 최소화하고 열을 차단시키는 효과가 있어야 하며 용융 상태에서 소실되지 않고 전단력이나 압력에 견딜 수 있어야 한다. 본 연구는 실험을 통하여 고체로켓 노즐의 재질에 대하여 연소시간별 침식특성을 파악한다. 그리고 Graphite와 C-C 복합재료의 각 재질별 조직검사를 통하여 침식 후의 미세특징을 비교 분석하여 침식특성을 규명한다.