• 조명전기설비학회논문지
• /
• 제19권8호
• /
• pp.33-39
• /
• 2005

본 논문에서는 퍼지와 신경회로망을 혼합한 FNN(Fuzzy Neural Network) 제어기를 이용한 유도전동기의 최대 토크 제어를 제시한다. 먼저 유도전동기 드라이브의 고성능 제어를 위하여 FNN 제어기를 설계한다. 다음은 유도전동기의 최대토크 제어를 위하여 주어진 부하토크에서 고정자 전류를 최소화하여 단위 전류당 발생토크를 높인다. 본 논문에서 제시한 FNN을 이용한 최대토크 제어의 특성을 분석하고 그 결과를 제시한다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1993년도 춘계학술대회 논문집
• /
• pp.92-96
• /
• 1993

Modern NC machine tools require a more and more exact monitoring and control of cutting process. A very important parameter is tool wear used to optimize cutting data and to change tools at the right time. In this study, a real-time multi-tool fracture method is proposed for measuring crater from fringe patterns generated by uni-shadow-moire. An optical technique using laser for non-contact measurement of tool fracture is presented. The technology in which the tool is illuminated by a beam of He-Ne laser and then the image of tool fracture CCD camera.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.149.5-149
• /
• 2001

The robot soccer simulation game is a dynamic multi-agent environment. In this paper we suggest a new reinforcement learning approach to each agent´s dynamic positioning in such dynamic environment. Reinforcement learning is the machine learning in which an agent learns from indirect, delayed reward an optimal policy to choose sequences of actions that produce the greatest cumulative reward. Therefore the reinforcement learning is different from supervised learning in the sense that there is no presentation of input-output pairs as training examples. Furthermore, model-free reinforcement learning algorithms like Q-learning do not require defining or learning any models of the surrounding environment. Nevertheless ...

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2003년도 춘계학술대회 논문집
• /
• pp.105-110
• /
• 2003

The hydraulic excavator has been a popular research object for automation because of its multi-workings and economic efficiency. When it works crane tasks, most of disasters happen. The objective of this paper is to design each components and to construct boom, arm, bucket circuit. These models modeled with AMESim show us change of variables and behavior of excavator. Simulation model will be used for simulator of excavator.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.496-499
• /
• 2003

Support Vector Machines (SVMs) is applied to a practical problem as one of standard tools for machine learning. The application of Reinforcement Learning (RL) and SVMs in action of mobile robot is investigated. A technique to decide the action of autonomous mobile robot in practice is explained in the paper, The proposed method is to find n basis for good action of the system under unknown environment. In multi-dimensional sensor input, the most reasonable action can be automatically decided in each state by RL. Using SVMs, not only optimal decision policy but also generalized state in unknown environment is obtained.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1999년도 제14차 학술회의논문집
• /
• pp.61-64
• /
• 1999

In this paper, a technique to expand the Input and Output (I/O) of the programmable logic controller (PLC) using remote I/O module is presented. The controller and the remote I/O module should have the same protocol and are interfaced through RS 485. Each remote I/O module consists of 16 digital input and 16 digital output, and the maximum of 32 remote I/O module can be linked to one controller. The remote I/O is programmed for interrupt request to controller independently. Therefore, there is no affect to the scan time of the controller. Using this technique, the PLC can be efficiently applied to the several hundred meters different control points such as the ON-OFF control fur the agriculture farm, the building automation system, a multi group of machine control.

• Transactions on Electrical and Electronic Materials
• /
• 제18권5호
• /
• pp.303-309
• /
• 2017

The flexible AC transmission system (FACTS) provides a new advanced technology solution to improve the flexibility, controllability, and stability of a power system. The unified power flow controller (UPFC) is outstanding for regulating power flow in the FACTS; it can control the real power, reactive power, and node voltage of distribution networks. This paper investigates the performance of the UPFC for power flow control with a series of step changes in rapid succession in a power system steady state and the response of the UPFC to distribution network faults and islanding mode. Simulation was carried out using the MATLAB's simulink sim power systems toolbox. The results, which were carried out on a 5-bus test system and a 4-bus multi-machine electric power system, show clearly the effectiveness and viability of UPFC in rapid response and independent control of the real and reactive power flows and oscillation damping [6].

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 1999년도 추계학술대회 논문집 - 한국공작기계학회
• /
• pp.263-268
• /
• 1999

The most important things to the tube the of the heat exchanger are the precision of t hole position and the quality of the drill face. Nowadays, 6 and 12 spindle multi-drilling machine controlled by CNC or used to drill holes of the tube sheet. The drilling of 12 axes can offer high speover three times as fast as the drilling of axis. However, the drilling of 12 axes h difficulty in controlling many motors to d spindles and assigning a corresponded numbe accurately to each axis. In the past, conventional method to inspect the code the drilling was machining holes on a thin plate previously which resulted in the productivity because it required a h production cost by machining and weldin time. In this thesis, there are two drilling codes different from CNC code. M code is used to control many motors and S code is used to assign a correspondent number for each axis. For increasing the productivity by removing process, this paper is intended to take simulation of the drill machining c including 6 and 12 axis on the persona computer.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2001년도 하계학술대회 논문집 A
• /
• pp.152-154
• /
• 2001

This paper presents a method for determination of UPFC control quantity in order to enhance the power system transient stability energy margin using Genetic Algorithms in multi-machine system. We use the minimization of energy margin as the object function in GA. To set critical energy, we use the potential energy boundary surface(PEBS) method. PEBS is one of the transient energy function(TEF) method. And we used the series voltage compensator as the UPFC model. The proposed method is applied to 6-bus, 7-line, 4-machine model system to show its effectiveness.

• 한국항행학회논문지
• /
• 제21권6호
• /
• pp.529-536
• /
• 2017

일반적인 지상통제 시스템은 단일 무인항공기 운용을 위한 통제 및 정보 전시 기능을 갖추고 있다. 현대에서는 단일 지상통제 시스템을 사용하여 복수 무인항공기의 운용이 요구되고 있다. 이로 인하여 무인기 운용자는 과거보다 다양한 임무 수행이 요구되며, 임무 수행 중 다양한 요인에 의하여 임무과부하를 받게 된다. 본 연구에서는 복수무인기 운용자의 임무과부하 측정을 통해 운용자의 상태를 반영한 적응형 지상통제 시스템을 제안한다. 복수무인기를 운용할 수 있는 지상통제 소프트웨어를 개발하고, 또한 시뮬레이터를 구성하여 운용자가 지상통제 시스템의 운용을 통해 시스템의 기능을 검증한다. 적응형 지상체 실험을 분석한 결과, 비적응형 지상체 실험 결과와 대비하여 운용자의 동공지름이 감소하고, 임무 성능이 증가하는 등 적응형 지상체의 효용성을 확인하였다.