• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.1477-1480
• /
• 1997

This paper is concerned with the design of a suboptimal robust Kalman filter using LMI approach for system models in the state space, which are subjected to parameter uncertainties in both the state and measurement atrices. Under the assumption that augmented system composed of the uncertain system and the state estimation error dynamics should be stable, a Lyapunov inequality is obtained. And from this inequaltiy, the filter design problem can be transformed to the gneric LMI problems i.e., linear objective minimization problem and generalized eigenvalue minimization problem. When applied to uncertain linear system modles, the proposed filter can provide the minimum upper bound of the estimation error variance for all admissible parameter uncertainties.

• 제어로봇시스템학회논문지
• /
• 제2권2호
• /
• pp.108-114
• /
• 1996

We present proofs of the stability and convergence of Self-organizing feature map (SOFM) neural network with time-invarient learning rate and binary reinforcement function. One of the major problems in Self-organizing feature map neural network concerns with learning rate-"Kalman Filter" gain in stochsatic control field which is monotone decreasing function and converges to 0 for satisfying minimum variance property. In this paper, we show that the stability and convergence of Self-organizing feature map neural network with time-invariant learning rate. The analysis of the proposed algorithm shows that the stability and convergence is guranteed with exponentially stable and weak convergence properties as well.s as well.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.413-418
• /
• 2003

In this paper, a new multirate optimal finite impulse response (FIR) filter is proposed for the signal reconstruction in the nosy filter bank systems. The multirate optimal FIR filter replaces the conventional synthesis filters and the Kalman synthesis filter. First, the generic linear model is derived from the multirate state space model for an autoregressive (AR)input signal. Second, the multirate optimal FIR filter is derived from the multirate generic linear model using the minimum variance criterion. This paper also provides numerical examples and results. The simulation results illustrate that the performance is improved compared with conventional synthesis filters and the proposed filter has advantages over the Kalman synthesis filter.

• 한국음향학회지
• /
• 제14권4호
• /
• pp.96-99
• /
• 1995

신호원 거리 부정합시 linearly constrained minimum variance (LCMV) 빔형성기는 원하는 신호를 제거해 버리는 성능 저하를 나타내게 된다. 어레이 공분산 행렬의 eigenstructure 성질을 이용하여 이 문제에 대한 원인 조사를 행한다. 이 원인 규명으로부터 신호원 거리 부정합에 로버스트한 빔형성기를 제안한다. 제안한 빔형성기는 최대 출력 신호 대 답음비를 나타낸다. 신호원이 far field에 있을 시 빔형성기의 weight vector는 bias되지 않는다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.349-351
• /
• 2004

The classical dynamic backpropagation learning algorithm has the problems of learning speed and the determine of learning parameter. The Extend Kalman Filter(EKF) is used effectively for a state estimation method for a non linear dynamic system. This paper presents a learning algorithm using Dual Extended Kalman Filter(DEKF) for Fully Recurrent Neural Network(FRNN). This DEKF learning algorithm gives the minimum variance estimate of the weights and the hidden outputs. The proposed DEKF learning algorithm is applied to the system identification of a nonlinear SISO system and compared with dynamic backpropagation learning algorithm.

• 전자공학회논문지B
• /
• 제30B권9호
• /
• pp.122-132
• /
• 1993

In this paper, a self tuning control algorithm is proposed for the high performance drive of DC servo motor, which is adequate to the servo system having frequent load variation. In order to realization of the algorithm, the control system is developed using a fixed point high speed digital signal processor. TMS320C25. Control algorithm is composed of two parts. One is estimation law part using recursive least mean square method, the other is control law part using minimum variance control method. For the purpose of easiness of applying adaptive algorithm, developed control system is based o PC-DSP structure which can develop, debug programs and monitor the dynamic behaviors,etc. Through computer simulation and experimental results, it was verified that proposed control system could estimate system parameters and was robust to the variation of the load and as a result, was adequate to the servo motor drives.

• 한국융합학회논문지
• /
• 제4권4호
• /
• pp.41-48
• /
• 2013

Observer design for system with unknown input was carried out. First, Kalman filter was considered to estimate system state with White noise. With the results of Kalman filter design, state observer, controller properties, including controllability and observability, and the Kalman filter structure and algorithm were also studied. Kalman filter algorithm was applied to Position and velocity measurement based on Kalman filter with white noise, and it was constructed and achieved by programming based on Matlab programming. Finally, observer for system with unknown input was constructed with the help of Gershgorin's disc theorem. With the designed observer, system states was constructed and applied to system with unknown input. By simulation results, estimation performance was verified. In this project, state feedback control theory, observer theory and relevant design procedure, as well as Kalman filter design were understood and used in practical application.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2001년도 정기총회 및 학술대회
• /
• pp.129-133
• /
• 2001

영상에 포함된 잡음은 화질 및 영상의 압축효율을 저하시킨다. 최근 들어, 영상의 에지 성분을 효율적으로 고려하면서 잡음을 제거하기 위하여 다양한 비정적(nonstationary) 영상 모델에 근거한 잡음제거 알고리즘이 제안되어 왔다. 하지만, 기존의 비정적 영상모델에서는 연산량의 부담을 덜기 위하여 각 화소들 사이에 상관관계(correlation)가 없다는 가정을 하고 있어 영상의 미세한 정보들이 필터링에 의하여 훼손된다. 본 논문에서는 영상의 비정적 상관관계를 고려한 적응적 잡음제거 알고리즘을 제시한다. 영상신호는 비정적 평균을 가진다고 가정되며, 또한 각기 다른 정적(stationary) 상관관계를 가지는 부분 영상으로 분리된다고 가정된다. 제안된 영상 모델에서의 공분산(co-variance) 행렬의 특수한 구조를 이용하여 계산적으로 효율적인 FFT에 기반한 선형 minimum mean square error 필터를 유도한다. 제안된 영상 모델의 정당성 및 알고리즘의 효율성을 제시한다.

• 응용통계연구
• /
• 제11권1호
• /
• pp.141-150
• /
• 1998

본 논문에서는 매우 민감한 조사에서 모집단이 양적속성을 갖는 여러 개의 집락으로 구성되어 있을 때, 집락을 추출단위로 하는 단순집락추출법에 양적속성의 무관질문모형을 적용하였다. 그리고, 일정한 비용하에서 분산을 최소로 하는 집락의 크기와 표본집락의 수의 최적값을 구하여 최소분산의 형태를 도출하였다. 또한, 제안한 단순집략추출법에 의한 무관질문모형과 단순임의 추출법에 의한 무관질문모형과의 효율성을 비교해 보았다.

• 소음진동
• /
• 제8권6호
• /
• pp.1030-1036
• /
• 1998

When the lateral dimensions of a duct is larger than or comparable to the wavelengths of Interest, higher order modes propagate in the duct. These modes will be radiated and produce noise. A number of sensors and actuators for control of radiating noise from the duct have to be incorporated with the number of modes which one wants to control. These considerations motivated the present study that considers a control system which has less microphones and control sources than required. In this work, by theoretical analysis, the control performance of such a kind of system is investigated in terms of sound-field variables and control system variables. The possible maximum and minimum value. mean and variance of residual acoustic potential energy are derived for the set of primary sound fields.