• 한국컴퓨터정보학회논문지
• /
• 제16권1호
• /
• pp.31-38
• /
• 2011

RAM 기반 3-D 신경망은 2진 신경망(Binary Neural Network, BNN)에 복수개의 정보 저장 비트를 두어 교육의 반복 횟수를 누적하도록 구성된 가중치를 가지지 않는 신경회로망으로서 한 번의 교육만으로 학습이 이루어지는 효율성이 뛰어난 신경회로망이다. MRD(Maximum Response Detector) 기법을 이용한 3-D 신경망의 인식 방법은 지도 학습에 기반을 둔 것으로서 학습을 통해 신경망 스스로가 범주를 구분할 수 없으며 잘 구분된 범주의 학습 데이터를 통해서만 성능을 발휘할 수 있다. 본 논문에서는 기존 3-D 신경 회로망에 학습 데이터의 구분 없이 신경망 자체가 입력 패턴에 따라 학습하여 범주를 구분하는 비지도 학습 알고리즘을 제안한다. 제안된 비지도 학습 알고리즘에 의해 신경회로망은 판별자의 수를 스스로 조절할 수 있는 구조를 가지게 되며 이는 망의 유연한 확장성을 보장한다. 0에서 9까지의 다중 패턴으로 구성된 오프라인 필기체 숫자를 무작위로 추출하여 학습 패턴으로 인식 실험을 수행하였으며 실험을 통해 신경망이 스스로 비지도 학습에 의해 판별자의 수를 결정하게 되며 이것은 신경망이 각각의 필기체 숫자에 대한 개념을 가지게 되는 것으로 해석할 수 있다.

• Journal of Power Electronics
• /
• 제6권4호
• /
• pp.279-289
• /
• 2006

This paper presents a neural network based adaptive dead-time compensation strategy for an inverter fed permanent magnet synchronous motor drive. The neural network is used for identifying the dead-time compensation time (DTCT) that includes an equivalent dead-time, turn-on/off time and on-state voltage components of the voltage source inverter. In order to train the neural network, desired DTCTs for eight operating points are prepared as training data. The trained neural network can identify a desired DTCT for any operating point because it has the capability of the interpolation. The accuracy of the identified DTCT is experimentally confirmed by comparing the calculated active power with a measured one.

• 제어로봇시스템학회논문지
• /
• 제10권12호
• /
• pp.1241-1248
• /
• 2004

A controller of wheeled mobile robot(WMR) based on Lyapunov theory is designed and a Fuzzy-Neural Network algorithm is applied to this system to adjust controller gain. In conventional controller of WMR that adopts fixed controller gain, controller can not pursuit trajectory perfectly when initial condition of system is changed. Moreover, acquisition of optimal value of controller gain due to variation of initial condition is not easy because it can be get through lots of try and error process. To solve such problem, a Fuzzy-Neural Network algorithm is proposed. The Fuzzy logic adjusts gains to act up to position error and position error rate. And, the Neural Network algorithm optimizes gains according to initial position and initial direction. Computer simulation shows that the proposed Fuzzy-Neural Network controller is effective.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 학술회의 논문집 정보 및 제어부문 A
• /
• pp.255-258
• /
• 2003

It is hard to centrol the wheeled mobile robot because of uncertainty of modeling, non-holonomic constraint and so on. To solve the problems, we design the controller of wheeled mobile robot based on fuzzy-neural network algorithm. In this paper, we should research the problem of classical controller for path-tracking algorithm and design of Fuzzy-Neural Network algorithm controller. Classical controller acquired different control value according to change of initial position and direction. In this control value having very difficult and having acquired a lot of trial and error Fuzzy is implemented to adaptive adjust control value by error and change of error and neural network is implemented to adaptive adjust the control gain during the optimization. The computer simulation shows that the proposed fuzzy-neural network controller is effective.

• 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.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1998년도 하계종합학술대회논문집
• /
• pp.897-900
• /
• 1998

Through fuzzy logic controller is very useful to many areas, it is difficult to build up the rule-base by experience and trial-error. So, effective self-tuning fuzzy controller for the position control of ball and beam is designed. In this paper, we developed the neural network control system with fuzzy-neuron which conducts the adjustment process for the parameters to satisfy have nonlinear property of the ball and beam system. The proposed algorithm is based on a fuzzy logic control system using a neural network learinign algorithm which is a back-propagation algorithm. This system learn membership functions with input variables. The purpose of the design is to control the position of the ball along the track by manipulating the angualr position of the serve. As a result, it is concluded that the neural network control system with fuzzy-neuron is more effective than the conventional fuzzy system.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2000년도 가을 학술발표회 논문집
• /
• pp.673-680
• /
• 2000

Artificial neural networks are efficient computing techniques that are widely used to solve complex problems in many fields. In this study, a back-propagation neural network model for estimating a consolidation behavior of clay from soil parameter, site investigation data and the first settlement curve is proposed. The training and testing of the network were based on a database of 63 settlement curve from two different sites. Five different network models were used to study the ability of the neural network to predict the desired output to increasing degree of accuracy. The study showed that the neural network model predicted a consolidation behavior of clay reasonably well.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2009년도 정보 및 제어 심포지움 논문집
• /
• pp.261-263
• /
• 2009

본 연구에서는 복잡한 비선형 모델링 방법인 RBF 뉴럴 네트워크(Radial Basis Function Neural Network)와 PNN(Polynomial Neural Network)을 접목한 새로운 형태의 Radial Basis Function Polynomial Neural Network(RPNN)를 제안한다. RBF 뉴럴 네트워크는 빠른 학습 시간, 일반화 그리고 단순화의 특징으로 비선형 시스템 모델링 등에 적용되고 있으며, PNN은 생성된 노드들 중에서 우수한 결과값을 가진 노드들을 선택함으로써 모델의 근사화 및 일반화에 탁월한 효과를 가진 비선형 모델링 방법이다. 제안된 RPNN모델의 기본적인 구조는 PNN의 형태를 이루고 있으며, 각각의 노드는 RBF 뉴럴 네트워크로 구성하였다. 사용된 RBF 뉴럴 네트워크에서의 커널 함수로는 FCM 클러스터링을 사용하였으며, 각 노드의 후반부는 다항식 구조로 표현하였다. 또한 각 노드의 후반부 파라미터들은 최소자승법을 이용하여 최적화 하였다. 제안한 모델의 적용 및 유용성을 비교 평가하기 위하여 비선형 데이터를 이용하여 그 우수성을 보인다.

• 제어로봇시스템학회논문지
• /
• 제18권6호
• /
• pp.540-545
• /
• 2012

In this paper, we propose a fault diagnosis method using artificial neural network and SVM (Support Vector Machine) to detect and isolate faults in the nonlinear systems. The proposed algorithm consists of two main parts: fault detection through threshold testing using a artificial neural network and fault isolation by SVM fault classifier. In the proposed method a fault is detected when the errors between the actual system output and the artificial neural network nominal system output cross a predetermined threshold. Once a fault in the nonlinear system is detected the SVM fault classifier isolates the fault. The computer simulation results demonstrate the effectiveness of the proposed SVM and artificial neural network based fault diagnosis method.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 2003년도 봄 학술발표회 논문집
• /
• pp.357-365
• /
• 2003

The major problems with the conventional neural network, especially Back Propagation Neural Network, arise from the necessity of many training data for neural network learning and ambiguity in the relation of neural network structure to the convergence of solution. In this paper, the PNN is used as a pattern classifier to detect the damage of structure to avoid those drawbacks of the conventional neural network. In the PNN-based pattern classification problems, the probability density function for patterns is usually assumed by Gaussian distribution. But, in this paper, several probability density functions are investigated in order to select the most approriate one for structural damage assessment.