• 전력전자학회:학술대회논문집
• /
• 전력전자학회 2018년도 추계학술대회
• /
• pp.175-176
• /
• 2018

This paper presents a method to estimate the parameter of permanent magnet synchronous motor using a least squares method. The approximate solution of the linear simultaneous equations is obtained by the pseudoinverse least squares method of the input current and output voltage data of the current controller. It is possible to obtain the current response of the same bandwidth to the general control target by using the Pole-zero Cancellation technique. This paper verifies the performance of the proposed method by comparing the results of estimation of parameters of different motors by simulation.

• Journal of the Korean Statistical Society
• /
• 제15권2호
• /
• pp.118-126
• /
• 1986

The relationships between combined estimators and generalized least squares estimators in block designs are reviewed. Here combined estimators mean the best linear combination of intrablock and interblock estimaters. It is well known that only for balanced incomplete block designs the combined estimators of Yates and of the generalized least squares estimators give the same result. In this paper, a general form of the combined estimators for treatment effects is derived and it can be seen that such estimators are equivalent to the generalized least squares estimators.

• Journal of the Korean Data and Information Science Society
• /
• 제25권2호
• /
• pp.423-429
• /
• 2014

본 논문은 이원고정효과모형의 분산분석에서 오차의 독립성과 등분산성이 만족되지 않는 경우를 가정하고 있다. 자료분석을 위한 모수추정방법으로 가중최소제곱법을 가정하고 있으며 모수를 추정하기 위한 방법으로 모형의 순차적 적합방식을 이용하고 있다. 또한, 모형의 행렬표현식으로부터 벡터공간에서의 사영을 이용하여 자료를 분석하는 방법을 제시하고 있다. 모형의 순차적 적합에 해당하는 제1종 제곱합을 구하기 위하여 모형행렬에 의한 부분공간으로의 사영을 다루고 있다. 이 경우에 사영에 의한 제곱합을 사영제곱합으로 취급한다.

• International Journal of Control, Automation, and Systems
• /
• 제6권5호
• /
• pp.713-721
• /
• 2008

This paper presents the robust velocity estimation of an omnidirectional mobile robot using a polygonal array of optical mice that are installed at the bottom of the mobile robot. First, the velocity kinematics from a mobile robot to an array of optical mice is derived as an overdetermined linear system. The least squares velocity estimate of a mobile robot is then obtained, which becomes the same as the simple average for a regular polygonal arrangement of optical mice. Next, several practical issues that need be addressed for the use of the least squares mobile robot velocity estimation using optical mice are investigated, which include measurement noises, partial malfunctions, and imperfect installation. Finally, experimental results with different number of optical mice and under different floor surface conditions are given to demonstrate the validity and performance of the proposed least squares mobile robot velocity estimation method.

• 한국CDE학회논문집
• /
• 제9권2호
• /
• pp.143-147
• /
• 2004

To design parts satisfying physical property in the continuous region, we do it in the discrete rectangular mesh points. Then we obtain points data from parts design and usually construct the surface using least squares method. In such case, that surface has an oscillation in the ineffective region which is inadequate for physical phenomena or NC machining. To solve both problems simultaneously, we extend the surface smoothly to have small curvature in the extended region. Up to now, we use the least squares method for the parts design in Color Picture Tube or Color Display Tube but in this paper, we use functions which is easily controllable. This surface has no error within the effective region compared to the least squares method.

• Communications for Statistical Applications and Methods
• /
• 제22권6호
• /
• pp.615-624
• /
• 2015

We consider the estimation of seasonal cointegration in the presence of conditional heteroskedasticity (CH) using a feasible generalized least squares method. We capture cointegrating relationships and time-varying volatility for long-run and short-run dynamics in the same model. This procedure can be easily implemented using common methods such as ordinary least squares and generalized least squares. The maximum likelihood (ML) estimation method is computationally difficult and may not be feasible for larger models. The simulation results indicate that the proposed method is superior to the ML method when CH exists. In order to illustrate the proposed method, an empirical example is presented to model a seasonally cointegrated times series under CH.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1993년도 한국자동제어학술회의논문집(국제학술편); Seoul National University, Seoul; 20-22 Oct. 1993
• /
• pp.7-12
• /
• 1993

This paper presents a generalized truncated least, squares adaptive algorithm and a two-stage design method. The proposed algorithm is directly derived from the normal equation of the generalized truncated least squares method (GTLSM). The special case of the GTLSM, the truncated least squares (TLS) adaptive algorithm, has a distinct features which includes the case of minimum steps estimator. This algorithm seemed to be best in the deterministic case. For real applications in the presence of disturbances, the GTLS adaptive algorithm is more effective. The two-stage design method proposed here combines the adaptive control system design with a conventional control design method and each can be treated independently. Using this method, the validity of the presented algorithms are examined by the simulation studies of an indirect adaptive control.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• 제14권2호
• /
• pp.125-140
• /
• 2010

This paper develops a least-squares approach to the solution of the optimal control problem for the Navier-Stokes equations. We recast the optimality system as a first-order system by introducing velocity-flux variables and associated curl and trace equations. We show that a least-squares principle based on $L^2$ norms applied to this system yields optimal discretization error estimates in the $H^1$ norm in each variable.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1991년도 하계학술대회 논문집
• /
• pp.691-694
• /
• 1991

In a discrete parameter estimation system, the standard least squares method shows slow convergence. On the other hand, the weighted least squares method has relatively fast convergence. However, if the input is not sufficiently rich, then gain matrix grows unboundedly. In order to solve these problems, this paper proposes a modified least squares algorithm which prevents gain matrix from growing unboundedly and has fast convergence.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 2004년도 추계학술발표대회논문집 제23권 2호
• /
• pp.527-530
• /
• 2004

We present a recursive total least squares (RTLS) algorithm for multilayer feedforward neural networks. So far, recursive least squares (RLS) has been successfully applied to training multilayer feedforward neural networks. But, when input data contain additive noise, the results from RLS could be biased. Such biased results can be avoided by using the recursive total least squares (RTLS) algorithm. The RTLS algorithm described in this paper gives better performance than RLS algorithm over a wide range of SNRs and involves approximately the same computational complexity of $O(N^{2})$.