• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 제37회 하계학술대회 논문집 D
• /
• pp.1832-1833
• /
• 2006

This paper presents a design method of the wavelet neural network(WNN) controller based on a direct adaptive control scheme for the intelligent control of Autonomous Underwater Vehicle(AUV) steering systems. The neural network is constructed by the wavelet orthogonal decomposition to form a wavelet neural network that can overcome nonlinearities and uncertainty. In our control method, the control signals are directly obtained by minimizing the difference between the reference track and original signal of AUV model that is controlled through a wavelet neural network. The control process is a dynamic on-line process that uses the wavelet neural network trained by gradient-descent method. Through computer simulations, we demonstrate the effectiveness of the proposed control method.

• 에너지공학
• /
• 제14권2호
• /
• pp.112-116
• /
• 2005

본 논문에서는 높은 대역폭과 안정성을 제공하는 DCS용 통신망의 구조를 제시하고 성능을 해석한다. 본 논문에서 제시하는 DCS용 통신망은 DCS 통신망에서 널리 사용되는 리플렉티브 메모리 (Reflective Memory) 구조를 채용하며, 이에 따라 링형 토폴로지를 가진다 물리계층으로 사무용 및 산업용으로 널리 쓰이고 있는 패스트 이더넷(Fast Ethernet)물리 매체를 사용하여 100 Mbps의 대역폭을 가지고, 링형 토폴로지가 가지는 단점인 각 노드에서의 시간 지연을 줄이기 위해 RED(Ring Enhancement Device)라는 장치를 고안하여 사용한다. 본 논문에서 소개하는 DCS용 통신망을 ERCNet(Ethernet based Real-time Control Network)이라고 명명하며, ERCNet의 구조와 동작에 대해 설명한다. ERCNet의 통신 성능에 대한 수학적 해석을 수행하고 개발된 ERCNet을 이용한 실험을 통하여 해석 결과의 정확성과 통신망 성능을 검증한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권1호
• /
• pp.413-435
• /
• 2018

Although the accuracy of handwritten character recognition based on deep networks has been shown to be superior to that of the traditional method, the use of an overly deep network significantly increases time consumption during parameter training. For this reason, this paper took the training time and recognition accuracy into consideration and proposed a novel handwritten character recognition algorithm with newly designed network structure, which is based on an extended nonlinear kernel residual network. This network is a non-extremely deep network, and its main design is as follows:(1) Design of an unsupervised apriori algorithm for intra-class clustering, making the subsequent network training more pertinent; (2) presentation of an intermediate convolution model with a pre-processed width level of 2;(3) presentation of a composite residual structure that designs a multi-level quick link; and (4) addition of a Dropout layer after the parameter optimization. The algorithm shows superior results on MNIST and SVHN dataset, which are two character benchmark recognition datasets, and achieves better recognition accuracy and higher recognition efficiency than other deep structures with the same number of layers.

• Journal of Electrical Engineering and Technology
• /
• 제10권3호
• /
• pp.1221-1226
• /
• 2015

This paper proposes a multiple switch mode power supply (SMPS) system based on the wireless network which controls variable load. The system enables power supply of up to 600W using 200W SMPS as a unit module and provides a controlling function of output power based on variable load and a monitoring function based on wireless network. The controlling function for output power measures the variation of output power and facilitates efficient power supply by controlling output power based on the measured variation value. The monitoring function guarantees a stable power supply by observing the multiple SMPS system in real time via wireless network. The performance of the proposed system was examined by various experiments. In addition, it was verified through standardized test of Korea Testing Certification. The results were given and discussed.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제4권1호
• /
• pp.111-118
• /
• 2004

In this paper, we present a novel approach for the structure of Fuzzy Neural Network(FNN) based on wavelet function and apply this network structure to the solution of the tracking problem for mobile robots. Generally, the wavelet fuzzy model(WFM) has the advantage of the wavelet transform by constituting the fuzzy basis function(FBF) and the conclusion part to equalize the linear combination of FBF with the linear combination of wavelet functions. However, it is very difficult to identify the fuzzy rules and to tune the membership functions of the fuzzy reasoning mechanism. Neural networks, on the other hand, utilize their learning capability for automatic identification and tuning. Therefore, we design a wavelet based FNN structure(WFNN) that merges these advantages of neural network, fuzzy model and wavelet transform. The basic idea of our wavelet based FNN is to realize the process of fuzzy reasoning of wavelet fuzzy system by the structure of a neural network and to make the parameters of fuzzy reasoning be expressed by the connection weights of a neural network. And our network can automatically identify the fuzzy rules by modifying the connection weights of the networks via the gradient descent scheme. To verify the efficiency of our network structure, we evaluate the tracking performance for mobile robot and compare it with those of the FNN and the WFM.

• 한국컴퓨터정보학회논문지
• /
• 제25권12호
• /
• pp.195-202
• /
• 2020

객체 감지 및 환경 센서 기반의 센서네트워크 환경에서 자원 활용 효율화를 위한 제어 시스템은 센서데이터 획득 및 송수신 기능과 서버에서의 분석을 기반으로 하는 능동적 제어 기능을 필요로 한다. 본 논문은 능동규칙 기반 이동에이전트 미들웨어를 이용하여 원격 데이터 센싱과 서버와의 Zigbee 기반 통신 및 서버의 데이터 분석 방법을 구현함으로써, 센서네트워크 환경에서 중앙 센서데이터 서버의 부하를 감소시키는 새로운 분산제어 프레임워크를 제안한다. 또한, 수요자의 요구 및 환경 변수들을 적용한 능동규칙 기반의 분산제어 방법을 이용한 절전 시스템 프로토타입을 구현하고, 이동에이전트 미들웨어 환경에서 실험과 평가를 통하여 유효성을 검증하였다. 제안 시스템은 센서네트워크 환경에서 분산된 객체들을 효율적으로 자율제어할 수 있는 시스템 프레임워크이며, 향후 스마트 전력 시스템을 위한 최적 전력제어 기반의 수요 반응 서비스 개발에 효과적 적용이 가능하다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 제37회 하계학술대회 논문집 D
• /
• pp.1860-1861
• /
• 2006

In this paper, we design a robust controller of biped robot system with uncertainties, using recurrent neural network. In our proposed control system, we use the self-recurrent wavelet neural network (SRWNN). The SRWNN makes up for the weak points in wavelet neural network(WNN). While the WNN has fast convergence ability, it dose not have a memory. So the WNN cannot confront unexpected change of the system. However, the SRWNN, having advantage of WNN such as fast convergence, can easily encounter the unexpected change of the system. For stable walking control of biped robot, we use sliding mode control (SMC). Here, uncertainties are predicted by SRWNN. The weights of SRWNN are trained by adaptive laws based on Lyapunov stability theorem. Finally, we carry out computer simulations with a biped robot model to verify the effectiveness of the proposed control system,.

• 제어로봇시스템학회논문지
• /
• 제13권5호
• /
• pp.406-413
• /
• 2007

This paper proposes a self-recurrent wavelet neural network(SRWNN) based adaptive backstepping control technique for the robust steering control of autonomous underwater vehicles(AUVs) with unknown model uncertainties and external disturbance. The SRWNN, which has the properties such as fast convergence and simple structure, is used as the uncertainty observer of the steering model of AUV. The adaptation laws for the weights of SRWNN and reconstruction error compensator are induced from the Lyapunov stability theorem, which are used for the on-line control of AUV. Finally, simulation results for steering control of an AUV with unknown model uncertainties and external disturbance are included to illustrate the effectiveness of the proposed method.

• 제어로봇시스템학회논문지
• /
• 제11권12호
• /
• pp.1002-1010
• /
• 2005

We study on the implementation of reconfigurable position control system which is based on Open Control Platform(OCP) for Unmanned Expedition Vehicles(UEV) in ubiquitous environment. The control system uses hierarchical control structure and OCP structure which contains three layers such as core OCP, reconfigurable control API(Application Programmer Interface), generic hybrid control API. The goal of our research is to implement an UEV control system using advanced software technology. As a specific control problem, we study a transition management problem between PID control and neural network control depending on fault or parameter change of the plant, i.e., UEV. The concept of the OCP-based software-enabled control can provide synergy effect by the integration of software component, middleware, network communication, and control, and thus can be applied to various systems in ubiquitous environment.

• 한국시뮬레이션학회논문지
• /
• 제8권4호
• /
• pp.33-51
• /
• 1999

In this study, the system level network simulation is considered with adaptive array antenna in CDMA mobile communication system. A network simulation framework is implemented based on IS-95A/B system to consider dynamic handoff, system level network behavior, and deploying strategy into the overall CDMA mobile communication network under adaptive array algorithm. Its simulation model, such as vector channel model, adaptive beam forming antenna model, handoff model, and power control model, are described in detail with simulation block. In order to maximize SINR of received signal at antenna, Maximin algorithm is particularly considered, and it is computed at each simulation snap shot with SINR based power control and handoff algorithm. Graphic user interface in this system level network simulator is also implemented to define the simulation environments and to represent simulation results on real mapping system. This paper also shows some features of simulation framework and simulation results.