• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.159.1-159
• /
• 2001

A new time-domain FIR parameter estimation called the receding horizon least square estimation (RHLSE) is suggested for stochastic systems by combining the well known least square estimation with the receding horizon strategy. It can be always obtained without the requirement of any \textit{a priori} information about the horizon initial parameter. A fast algorithm for the suggested estimation is also presented which is remarkable in the view of computational advantage and simple implementation. It is shown that the proposed estimation is robust against temporary modeling uncertainties due to their FIR structure through simulation studies.

• The Korean Journal of Applied Statistics
• /
• v.22 no.3
• /
• pp.531-539
• /
• 2009

Logistic regression is widely used as a datamining technique for the customer relationship management. The maximum likelihood estimator has highly inflated variance when multicollinearity exists among the regressors, and it is not robust against outliers. Thus we propose the robust principal components logistic regression to deal with both multicollinearity and outlier problem. A procedure is suggested for the selection of principal components, which is based on the condition index. When a condition index is larger than the cutoff value obtained from the model constructed on the basis of the conjoint analysis, the corresponding principal component is removed from the logistic model. In addition, we employ an algorithm for the robust estimation, which strives to dampen the effect of outliers by applying the appropriate weights and factors to the leverage points and vertical outliers identified by the V-mask type criterion. The Monte Carlo simulation results indicate that the proposed procedure yields higher rate of correct classification than the existing method.

• The Transactions of the Korean Institute of Electrical Engineers B
• /
• v.53 no.1
• /
• pp.37-46
• /
• 2004

A novel rotor speed estimation method using model reference adaptive control(MRAC) is proposed to improve the performance of a sensorless vector controller. In the proposed method, the stator current is used as the model variable for estimating the speed. In conventional MRAC methods, the relation between the two model errors and the speed estimation error is unclear. In the proposed method, the stator current error is represented as a function of the first degree for the error value in the speed estimation. Therefore, the proposed method can produce a fast speed estimation. The robustness of the rotor flux-based MRAC, back EMF-based MRAC, and proposed MRAC is compared based on a sensitivity function about each error of stator resistance, rotor time constant, mutual inductance. Consequently, the proposed method is much more robust than the conventional methods as regards errors in the mutual inductance, stator resistance. Therefore, the proposed method offers a considerable improvement in the performance of a sensorless vector controller at a low speed. In addition, the superiority of the proposed method and the validity of sensitivity functions were verified by simulation and experiment.

• International Journal of Control, Automation, and Systems
• /
• v.3 no.4
• /
• pp.612-619
• /
• 2005

A robust adaptive speed sensorless induction motor direct torque control (DTC) using a neural network (NN) is presented in this paper. The inherent lumped uncertainties of the induction motor DTC system such as parametric uncertainty, external load disturbance and unmodeled dynamics are approximated by the NN. An additional robust control term is introduced to compensate for the reconstruction error. A control law and adaptive laws for the weights in the NN, as well as the bounding constant of the lumped uncertainties are established so that the whole closed-loop system is stable in the sense of Lyapunov. The effect of the speed estimation error is analyzed, and the stability proof of the control system is also proved. Experimental results as well as computer simulations are presented to show the validity and efficiency of the proposed system.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• 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.

• The Pure and Applied Mathematics
• /
• v.9 no.1
• /
• pp.81-90
• /
• 2002

The least informative (favorable) distributions, minimizing Fisher information for a multivariate location parameter, are derived in the parametric class of the exponential-power spherically symmetric distributions under the following characterizing restrictions; (i) a bounded variance, (ii) a bounded value of a density at the center of symmetry, and (iii) the intersection of these restrictions. In the first two cases, (i) and (ii) respectively, the least informative distributions are the Gaussian and Laplace, respectively. In the latter case (iii) the optimal solution has three branches, with relatively small variances it is the Gaussian, them with intermediate variances. The corresponding robust minimax M-estimators of location are given by the $L_2$-norm, the $L_1$-norm and the $L_{p}$ -norm methods. The properties of the proposed estimators and their adaptive versions ar studied in asymptotics and on finite samples by Monte Carlo.

• Proceedings of the KIEE Conference
• /
• 1994.07a
• /
• pp.468-471
• /
• 1994

This paper presents the digital implementation of an optimal and robust VSS controller with sliding observer. Firstly, a discrete-time VSS control law which enables the system state to move into a sliding sector where the closed-loop system is stable is designed. Then optimal control theory is used to design an optimal sliding sector. Secondly, a sliding observer which provide robust state estimation against model-plant mismatches due to parameter uncertainties is designed for the sampled-data multivariable systems. Finally, modified sliding observer which effectively reduce chattering of state variables in state estimation was proposed. The proposed scheme was applied 10 a two degree of freedom inverted pendulum with passive joint to verify robust motion control. Computer simulation results confirm the viability of the proposed observer-based controller.

• Proceedings of the KIEE Conference
• /
• 2005.07d
• /
• pp.2477-2479
• /
• 2005

A robust bending frequency tracker is proposed to design the adaptive notch filter which removes the time-varying missile structural modes from the sensor measurements. To do this, the state-space form of a bending frequency model is derived under the assumption that the bending signal could be described as the lightly damped sinusoid. Since the resultant bending frequency model contains the parametric uncertainties in the measurement matrix, the design problem of bending frequency tracker is tackled by applying the robust Kalman filter to the model. This technique could be easily expanded to the multiple frequencies case because it newly illuminates the bending frequency tracking problem in view of general state estimation.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.759-762
• /
• 1996

In previous work Kwon and Yoo [5] have shown that the FIR tracking algorithm using the input estimation technique. However, it has not solved the problem of systems with parameter uncertainties. Therefore, in this paper we propose a new robust $H_{\infty}$ FIR tracking filter to solve the target tracking problems under systems with parameter uncertainties. Also, we use here the input estimation approach to account for the possibility of maneuver. Simulation results show that the robust $H_{\infty}$ FIR tracking filter proposed here still has good tracking performance for a maneuvering target tracking problem even under all system parameter uncertainties.

• Journal of Institute of Control, Robotics and Systems
• /
• v.8 no.11
• /
• pp.935-940
• /
• 2002

For robot navigation and visual reconstruction, structure from motion (SFM) is an active issue in computer vision community and its properties arc also becoming well understood. In this paper, when using stereo image sequence and direct method as a tool for SFM, we present a new method for overcoming bas-relief ambiguity. We first show that the direct methods, based on optical flow constraint equation, are also intrinsically exposed to such ambiguity although they introduce robust methods. Therefore, regarding the motion and depth estimation by the robust and direct method as approximated ones. we suggest a method that refines both stereo displacement and motion displacement with sub-pixel accuracy, which is the central process f3r improving its ambiguity. Experiments with real image sequences have been executed and we show that the proposed algorithm has improved the estimation accuracy.