• Journal of Biosystems Engineering
• /
• v.15 no.3
• /
• pp.186-198
• /
• 1990

인간 소뇌의 구조와 기능을 간략하게 수학적으로 모델링하여 입력에 따른 시스템의 적정 출력을 학습에 의한 적응 제어 방식으로 추출해 내는 소뇌모델 대수제어기(CMAC : Cerebellar Model Arithmetic Controller)가 제안되었다. 본 논문에서는 연구개발된 기존 신경회로망과의 비교 분석에 의거하여, 소뇌모델 대수제어기 대신 네트의 특성에 따라 소뇌모델 선형조합 신경망(CMLAN : Cerebellum Model Linear Associator Network)이라 하였다. 소뇌모델 선형조합 신경망은 시스템의 제어 함수치를 결정하는 데 있어, 기존의 제어방식이 시스템의 모델링을 기초로 하여 알고리즘에 의한 수치해석적 또는 분석적 기법으로 모델 해를 산출하는 것과 달리, 학습을 통하여 저장되는 분산기억 소자들의 함수치를 선형적으로 조합함으로써 시스템의 입출력을 결정한다. 분산기억 소자로의 함수치 산정 및 저장은 소뇌모델 선형조합 신경망이 갖는 고유의 구조적 상태공간 매핑(State Space Mapping)과 델타규칙(Delta Rule)에 의거한 시스템의 입출력 상태함수의 학습으로써 수행된다. 본 논문을 통하여 소뇌모델 선형조합신경망의 구조적 특성, 학습 성질과 상태공간 설정 및 시스템의 수렴성을 규명하였다. 또한 기존의 최대 편차수정 학습 알고리즘이 갖는 비능률성 및 적용 제한성을 극복한 효율적 학습 알고리즘들을 제시하였다. 언급한 신경망의 특성 및 제안된 학습 알고리즘들의 능률성을 다양한 학습이득(Learning Gain)하에서 비선형 함수를 컴퓨터로 모의 시험하여 예시하였다.

• Proceedings of the KIEE Conference
• /
• 2005.07d
• /
• pp.2720-2722
• /
• 2005

본 논문에서는 웨이블릿 신경 회로망에 기반을 둔 능동 큐 관리(Active Queue Management) 제어 시스템을 설계하는 것을 제안한다. 제안한 제어 시스템에서 웨이블릿 신경 회로망은 능동 큐 관리를 위한 제어기로 사용한다 TCP 동적 모델의 실제 출력, 큐의 길이와 웨이블릿 신경 회로망을 이용한 출력의 오차가 최소화가 되도록 웨이블릿 신경 회로망의 파라미터 값들을 변화시키며 각각의 파라미터 값들은 경사 하강법을 통해 학습시킨다. 마지막으로 제안한 방법은 모의실험을 통해 패킷 손실률과 큐의 길이의 관점에서 제안한 방법의 향상성을 보이고자 한다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.4
• /
• pp.449-455
• /
• 2011

In this paper, a time-delay problem of a tele-operated control system is investigated and compensated by neural network. The smith predictor requires an exact system model to deal with a time-delay in the system. To compensate for modeling errors in the configuration of the Smith predictor, a neural network approach is presented. Based on forming the Smith predictor structure, the radial basis function(RBF) neural network estimator is used. Simulation and experimental studies are conducted to show the functionality of the proposed method.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.8
• /
• pp.2070-2079
• /
• 1997

In this paper, we proposed the FNCAC (fuzzy neural call admission control) scheme of the ATM networks which used the benefits of fuzzy logic controller and the learning abilities of the neural network to solve the call admission control problems. The new call in ATM networks is connected if QoS(quality of service) of the current calls is not affected due to the connection of a new call. The neural network CAC(call admission control) system is predictable system because the neural network is able to learn by the input/output pattern. We applied the fuzzy inference on the learning rate and momentum constant for improving the learning speed of the fuzzy neural network. The excellence of the proposed algorithm was verified using measurement of learning numbers in the traditional neural network method and fuzzy neural network method by simulation. We found that the learning speed of the FNCAC based on the fuzzy learning rules is 5 times faster than that of the CAC method based on the traditional neural network theory.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.6
• /
• pp.720-729
• /
• 2005

In this paper, we design the indirect adaptive controller using Wavelet Neural Network(WNN) for unknown nonlinear systems. The proposed indirect adaptive controller using WNN consists of identification model and controller. Here, the WNN is used in both Identification model and controller The WNN has advantage of indicating the location in both time and frequency simultaneously, and has faster convergence than MLPN and RBFN. There are several training methods for WNN, such as GD, GA, DNA, etc. In this paper, we present the Extended Kalman Filter(EKF) based training method. Although it is computationally complex, this algorithm updates parameters consistent with previous data and usually converges in a few iterations. Finally, ore illustrate the effectiveness of our method through computer simulations for the Buffing system and the one-link rigid robot manipulator. From the simulation results, we show that the indirect adaptive controller using the EKF method has better performance than the GD method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.4B
• /
• pp.683-691
• /
• 2000

In this paper, we proposed the cell multiplexer using Hopfield neural network and the bandwidth predictor using the backpropagation neural network in order to make an accurate call setup decision. The cell multiplexer controls heterogeneous traffic and the bandwidth predictor estimates minimum bandwidth which satisfies traffic's QoS and maximizes throughput in network. Also, a novel connection admission controller decides on connection setup using the predicted bandwidth from bandwidth predictor and available bandwidth in networks. And then, we proposed a fuzzy traffic policer, when traffic sources violate the contract, takes an appropriate action and aim proved traffic shaper, which controls burstness which is one of key characteristics in multimedia traffic. We simulated the proposed controller. Simulation results show that the proposed controller outperforms existing controller.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.31 no.3
• /
• pp.50-57
• /
• 2003

In the paper, the design and evaluation of a helicopter trajectory tracking controller are presented. The control algorithm is implemented using the feedback linearization technique and the two time-scale separation architecture. In addition, and on-line adaptive architecture that employs a neural network compensating the model inversion error caused by the deficiency of full knowledge of helicopter dynamic is applied to augment the attitude control system. Trajectory tracking performance of the control system in evaluated using modified TMAN simulation program representing as Apache helicopter. It is show that the on-line neural network in an adaptive control architecture is very effective in dealing with the performance depreciation problem of the trajectory tracking control caused by insufficient information of dynamics.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.6 no.4
• /
• pp.49-60
• /
• 1996

The objective of this paper is to develop an adaptive learning method for fuzzy hypercubes using a neural network. An intelligent control system is proposed by exploiting only the merits of a fuzzy logic controller and a neural network, assuming that we can modify in real time the consequential parts of the rulebase with adaptive learning, and that initial fuzzy control rules are established in a temporarily stable region. We choose the structure of fuzzy hypercubes for the fuzzy controller, and utilize the Perceptron learning rule in order to upda1.e the fuzzy control ru1c:s on-line with the output errors. As a result, the effectiveness and the robustness of this intelligent controller are shown with application of the proposed adaptive fuzzy-neuro controller to control of the cart-pole system.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.7 no.5
• /
• pp.46-50
• /
• 1997

In fuzzy logic control, static fuzzy rules cannot cope with significant changes of parameters of plants or environment. To solve this prohlem, self-organizing fuzzy control. neural-network-hased fuzzy logic control and so on have heen introduced so far. However, dynamically changed fuzzy rules of these schemes may make a fuzzy logic controller Fall into dangerous situations because the changed fuzzy rules may he incomplete or inconsistent. This paper proposes a new adaptive filzzy logic control scheme using a predictivc neural network. Although some parameters of a controlled plant or environment are changed, proposed fuzzy logic controller changes its decision outputs adaptively and robustly using unchanged initial fuzzy rules and the predictive errors generated hy the predictive neural network by on-line learning. Experimental results with a D<' servo-motor position control problem show that propnsed cnntrol scheme is very useful in the viewpoint of adaptability.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.5
• /
• pp.29-38
• /
• 1998

This paper proposes the neural network self-tuning PID controller for the load frequency control of 2- areas power system, namely, the prompt convergence of frequency and tie-line power flow deviation. The neural network applied to computer simulation consists of neurons of two inputs, ten hiddens and tliree outputs layer. Neurons of two inputs layer receive the error and its change rate of the system and cutputs layer consists of three neurons for the parameters of the PID controller. The simulation results shows that the proposed neural network self-tuning PID controller is superior to conventional control t~:chniques(Optimal, PID) in dynamic response and control performance.