• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.694-697
• /
• 2003

In this paper, we propose modular network to solve difficult and complex problems that are seldom solved with Multi-Layer Neural Network(MLNN). The structure of Modular Neural Network(MNN) in researched by Jacobs and jordan is selected in this paper. Modular network consists of several Expert Networks(EN) and a Gating Network(CN) which is composed of single-layer neural network(SLNN) or multi-layer neural network. We propose modular network structure using Recurrent Neural Network(RNN), since the state of the whole network at a particular time depends on aggregate of previous states as well as on the current input. Finally, we show excellence of the proposed network compared with modular network.

• International journal of advanced smart convergence
• /
• 제2권2호
• /
• pp.10-15
• /
• 2013

An expert network administrator is not always stationed as disasters happen. In that case, it is desirable that a novice administrator is capable of taking part in network recovery operations as well. In this paper, an agent-based network management system in emergency situations is presented. We use the Active Information Resource based Network Management System (AIR-NMS) to relieve the human administrator from parts of her management tasks and present an interface that remotely can control this management system. The effectiveness of the system is demonstrated by experiments using a prototype system.

• International journal of advanced smart convergence
• /
• 제3권1호
• /
• pp.1-6
• /
• 2014

An expert network administrator is not always stationed as disasters happen. In that case, it is desirable that a novice administrator is capable of taking part in network recovery operations as well. In this paper, aknowledge-based network management system in emergency situations is presented. We use the Active Information Resource based Network Management System (AIR-NMS) to relieve the human administrator from parts of her management tasks and present an interface that remotely can control this management system. The effectiveness of the system is demonstrated by experiments using a prototype system.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 제37회 하계학술대회 논문집 B
• /
• pp.1073-1074
• /
• 2006

In this paper, we perform a simulation to verify the earth resistance values in Common Earth Network. The simulation is performed on the assumption that certain shorts are occurred in common earth network. Furthermore, from the result, we confirmed that very small earth resistance values in common earth network are given, by carrying out practical measurements in railway sections where common earth network is composed. From the effect, we could discover that the construction of common earth network is in a disadvantageous position on the financial aspect, while it is the most desirable way of construction for the purpose of Earth.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1996년도 하계학술대회 논문집 B
• /
• pp.1031-1033
• /
• 1996

Now is an automation age. Therefore it is required that machine can do work which was done by men. Artificial Neural Network was developed by the necessity of this purpose. This paper shows a Predictive Control with a Neural Network. The Neural Network learns an Inverted Pendulum in various situations. Then, it has a power to predict the next state after accept the current state. And the Neural Network directs the Bang-Bang Controller to give input to a plant. It seems like that a human expert looks the state of a plant and then controls the plant. It is used a Feedforward Neural Network and shown control state according to the learning. We could get a satisfactory results after complete learning.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 A
• /
• pp.34-36
• /
• 2000

This paper proposes the design of SVC adaptive fuzzy logic controller(AFLC) using Tabu search and neural network. We tuned the gain of input-output variables of fuzzy logic controller and weights of neural network using Tabu search. Neural network used to tune the output gain of FLC adaptively. We have weights of neural network learned using back propagation algorithm. We performed the nonlinear simulation on an single-machine infinite system to prove the efficiency of the proposed method. The proposed AFLC showed the better performance than PD controller in terms of the settling time and damping effect, for power system operation condition.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2001년도 하계학술대회 논문집 D
• /
• pp.2386-2389
• /
• 2001

This paper describes neural network steering controller for an AGV using MR sensor. The analytical magnetic fields model was compared with measured data and found to have less than 1 % difference. The neural network was also used to learn the steering behaviour of the AGV relative to the magnetic field values(Bx, By, Bz). A computer simulation of the AGV (including AGV's dynamics and steering) was used to verify the steering performance of the controller using the neural network. Good results were obtained. Also, the handmade AGV using neural network controller verified good results.

• 전기학회논문지
• /
• 제62권10호
• /
• pp.1451-1457
• /
• 2013

Recently, new concept of energy systems such as microgrid, smart grid, supergrid, and energy network has been introducing. In this paper, the concept of the centralized micro-energy network, which is an energy community of a building group without district heating system, is introduced. In addition, a mathematical model for optimal operation of the micro-energy network as a main function of an energy management system (EMS) for the micro-energy network is proposed. In order to show the validation, the proposed model is tested through the simulation and analyzed.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 I
• /
• pp.465-468
• /
• 2003

In industry areas, a lot of factories and process plants need network for processing data acquired from field and for communicating between sensors or actuators or field controllers. Most of the industry networks are based on wired solutions. But, recently, a lot of factories and process plants are moving into wireless solutions since they have some advantages compared with wired one. In this paper we first review the characteristics of wired and wireless network technologies and introduce the new technique called wireless sensor network (WSN). And then we describe the wireless sensor node system designed by us for WSN which has the ability of small size, flexibility and low-power consumption and embedded into the Bar-code scanner to communicate each other. Finally, we conclude this paper by showing that wireless industry network can be constructed with wireless sensor network without large change of traditional wired topologies through experiment using wireless sensor nodes.

• E2M - 전기 전자와 첨단 소재
• /
• 제10권7호
• /
• pp.651-658
• /
• 1997

In this paper, effect of interpenetrating polymer network(IPN) introduction on the dielectric properties, heat proof properties, internal structure and defects of the Epoxy/SiO$_2$composite materials, were investigated. we reported a relation between network structures and electrical properties, especially dielectric characteristics with variation of network structures for epoxy composite materials. According to experimental results, the specimens which have single network structures have lower dielectric constant than interpenetrating polymer network(IPN) specimens, but have relatively larger dependency to variation of temperature and frequency. It was confirmed that change of structures is attained by introducing of IPN to insulating materials. Therefore it is counted that introduction of multiple structure including IPN is necessary to improve heat proof and electrical properties.