• Proceedings of the KIEE Conference
• /
• 2001.07b
• /
• pp.1135-1137
• /
• 2001

본 연구는 자계방향 기준 벡터제어 이론에 기초하여 속도 센스리스 벡터제어를 구현한다. 벡터제어는 상태량에 기초한 MRAS (MRAS: Model Reference Adaptive System)방법은 이득정수의 결정이 어려운 결점을 가지고 있다. 여기서는 관측기 이론에 기초하여 2차자속 관측기와 전류센스에서 검출한 전류값으로 속도추정을 행하는 새로운 속도 추정법을 제안한다. 그리고 제안한 방법이 자계 방향 벡터제어 시스템의 실현에 가능성이 있음을 시뮬레이션으로 검토한다.

• Proceedings of the KIEE Conference
• /
• 2005.07d
• /
• pp.2681-2683
• /
• 2005

In this paper, we present the structure of fuzzy neural network(FNN) based on wavelet function, and apply this network structure to the identification of nonlinear systems. For adjusting the shape of membership function and the connection weights, the parameter learning method based on the gradient descent scheme is adopted. And an approach that uses adaptive learning rates is driven via a Lyapunov stability analysis to guarantee the fast convergence. Finally, to verify the efficiency of our network structure. we compare the Identification performance of proposed wavelet based fuzzy neural network(WFNN) with those of the FNN, the wavelet fuzzy model(WFM) and the wavelet neural network(WNN) through the computer simulation.

• Proceedings of the KIEE Conference
• /
• 2005.07d
• /
• pp.2579-2581
• /
• 2005

The Tidal Power Plant Management is defined to devise the optimum operating plan and control generating output automatically to obtain maximum production by using adaptive control method. The method to use tidal level observation results is suggested as two(2) kinds of manner, that is the two(2) layer design method by power model simulation and power automatic control.

• Proceedings of the KIEE Conference
• /
• 2006.07d
• /
• pp.1860-1861
• /
• 2006

In this paper, we design a robust controller of biped robot system with uncertainties, using recurrent neural network. In our proposed control system, we use the self-recurrent wavelet neural network (SRWNN). The SRWNN makes up for the weak points in wavelet neural network(WNN). While the WNN has fast convergence ability, it dose not have a memory. So the WNN cannot confront unexpected change of the system. However, the SRWNN, having advantage of WNN such as fast convergence, can easily encounter the unexpected change of the system. For stable walking control of biped robot, we use sliding mode control (SMC). Here, uncertainties are predicted by SRWNN. The weights of SRWNN are trained by adaptive laws based on Lyapunov stability theorem. Finally, we carry out computer simulations with a biped robot model to verify the effectiveness of the proposed control system,.

• Proceedings of the KIEE Conference
• /
• 2005.07d
• /
• pp.2717-2719
• /
• 2005

Generally, biped walking is difficult to control because a biped robot is a nonlinear system with various uncertainties. In this paper, we propose a hybrid control system to improve the efficiency of position tracking performance of biped locomotion. In our control system, the wavelet neural network (WNN) based on Sliding mode controller is used as a main controller which estimates a biped robot model, and the compensated controller is proposed to compensate the estimation error. A WNN is utilized to estimate uncertain and nonlinear system parameters, where the weights of WNN are trained by adaptive laws that are induced from the Lyapunov stability theorem. Finally, the effectiveness of the proposed control system is verified through computer simulations.

• Korean Journal of Cognitive Science
• /
• v.6 no.2
• /
• pp.81-95
• /
• 1995

Intelligent courseware predicts the status of student diagnosing student diagnosing student's response and performs an adaptive tutoring based on the student model.This paper designs an authoring tool that supports dyanmic sequence control of tutoring.And also it defines a lesson description language for the dynamic control sequence.Using this language we can represent a control sequence of courseware statically and dynamically.We apply the proposed tool for controlling sequence of C language courseware and show the usability of the proposed system.

• Journal of Information Processing Systems
• /
• v.7 no.3
• /
• pp.519-530
• /
• 2011

A Snake is an active contour for representing object contours. Traditional snake algorithms are often used to represent the contour of a single object. However, if there is more than one object in the image, the snake model must be adaptive to determine the corresponding contour of each object. Also, the previous initialized snake contours risk getting the wrong results when tracking multiple objects in successive frames due to the weak topology changes. To overcome this problem, in this paper, we present a new snake method for efficiently tracking contours of multiple objects. Our proposed algorithm can provide a straightforward approach for snake contour rapid splitting and connection, which usually cannot be gracefully handled by traditional snakes. Experimental results of various test sequence images with multiple objects have shown good performance, which proves that the proposed method is both effective and accurate.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.445-448
• /
• 1996

For a lightly damped system, IIR based filter can have better performance than FIR filter as an adaptive filter in ANC algorithm. IIR based filter which has an infinite impulse response can model a lightly damped acoustic system with a small number of weights compared that of FIR filter and has no nonlinearity and instability problems on weight updating process which are associated to the conventional IIR filters. There are, however, some drawbacks such as design parameters to be determined earlier to get better performance and much increased computational power especially in the presence of error path. In this study, base filter parameters are determined in systematic manner, with the knowledge of the nominal impulse response of the system which should be identified, by Prony's method. Three methods reducing the computational load are proposed and their performance and application limits are discussed. Simulation and experimental results demonstrate the feasibility of the proposed method.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.882-887
• /
• 2005

The paper describes Quasi-simultaneous recognition of plural targets and motion control of robot based on the recognition. The method searches for targets by model-based matching method using the hybrid GA, and the motion of the robot is generated based on the targets' positions on the image. The method is applied to a soccer robot, and targets are a ball, a goal, and an enemy in the experiment. The Experimental results show robustness and reliability of the proposed method.

• Proceedings of the IEEK Conference
• /
• 1998.06a
• /
• pp.781-784
• /
• 1998

An image segmentation approach based on the fuzzy worm searching and MIN-MAx clusterng algorithm is proposed in this paper. This algorithm deals with fuzzy worm value and min-max node at a gross scene level, which investigates the edge information including fuzzy worm action. But current segmentation methods based edge extraction methods generally need the mask information for the algebraic model, and take long run times at mask operation, wheras the proposed algorithm has single operation ccording to active searching of fuzzy worms. In addition, we also genetic min-max clustering using genetic algorithm to complete clustering and fuzyz searching on grey-histogram of image for the optimum solution, which can automatically determine the size of rnages and has both strong robust and speedy calculation. The simulation results showed that the proposed algorithm adaptively divided the quantized images in histogram region and performed single searching methods, significantly alleviating the increase of the computational load and the memory requirements.