• 한국정밀공학회지
• /
• 제15권5호
• /
• pp.43-49
• /
• 1998

Adaptive neural network approach is presented for determining Electrical Discharge Machining (EDM) parameters. Electrical Discharge Machining has been widely used with its capability of machining hard metals and tough shapes. In the past few years, EDM has been established in tool-room and large-scale production. However. in spite of it's wide application, an universal selection method of EDM parameters has not been established yet. No attempt has been tried before to suggest a logical method in determining essential machine parameters considering the machining rate and resulting surface roughness integrity. The paper presents a method, which is focusing on determining appropriate machining parameters. Depending on the electrode wear and surface roughness, an adaptive neural network is designed for providing suitable machining guideline.

• 대한전자공학회논문지
• /
• 제20권1호
• /
• pp.37-44
• /
• 1983

본 논문에서는 MRAC 방식을 이용하여 이산 시간이고 잡음이 없는 단일한 입출력을 갖는 선형계에 직접제어 방식으로 적응 제어 알고리즘을 원용하였다. 직접 제어 방식에서 제어기는 매개변수형으로 구성되고 그리고 매개변수 조정을 위한 검증 알고리즘은 일련의 축차방정식으로 주어지는데 이는 가중 최소 자승법에 따라 유도되었다. 가중 최소 자승법으로 제어기 매개변수를 검증했을 때 출력 추적오차가 영에 수검하는 속도가 경도법 또는 최소 자승법을 사용했을 때보다 빠르다는 것이 컴퓨터 시뮬레이견으로 확인되었으며 또한 λ를 변화시키는 제안된 가중 최소 자승법은 규범형 모델 입력의 동파수 성분에 관계언이 사용될 수 있음을 보였다. 또한 이런 경우에 있어서 수험성과 안정도에 관해서도 고찰했다.

• 한국정보통신학회논문지
• /
• 제9권3호
• /
• pp.522-527
• /
• 2005

이동 통신단말의 급속한 보급에 따라 고품질이며 대용량인 정보의 전송이 요구된다. 또한 고속 전송 시 발생하는 다중로 페이딩을 해결하기 위해 적응 배열 안테나의 연구가 활발히 진행되고 있으며, 그 중 DOA(Direction of Arrival) 추정은 적응배열 안테나의 중요한 부분이다. 본 논문에서는, 2차 통계량을 이용한 시공간 블라인드 시스템 식별을 제안하고, 블라인드 시공간 적응 배열 안테나를 이용하여 제안 방법의 효율성을 입증한다.

• KSBB Journal
• /
• 제6권1호
• /
• pp.15-25
• /
• 1991

The optimal glucose concentration for the high-density culture of recombinant yeasts was obtained using dynamic simulation. An adaptive and predictive algoritilm complimented by the rule base was proposed for the control of the fed-batch fermentation process. The measurement of process variables has relatively long sampling period and relatively long time delay characteristics. As one of the solution on these problems, prediction techniques and rule bases were added to a classical recursive identification and control algorithm. Rule bases were used in the determination of control input considering the difference between the predicted value and the measured value. A mathelnatical model was used in the estimation and interpretation of the changes of state variables and parameters. Better performances were obtained by employing the control algorithm proposed in the present study compared to the conventional adaptive control method.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1995년도 하계학술대회 논문집 B
• /
• pp.953-955
• /
• 1995

Studied on identification of nonlinear system with unknown variables and adaptive control were successful. We need a mathmatical model when control a dynamic system using adaptive control technique, but it is very difficult due to its nonlinearity. In this paper, we described about performance improvement of error back-propagation algorithm and learning algorithm of non-linear dynamic system. We examined the proposed back-propagation learn algorithm for through an experiment.

• Journal of Electrical Engineering and information Science
• /
• 제2권6호
• /
• pp.82-89
• /
• 1997

In this paper, an adaptive speed controller with an FNN(Feedforward Neural Network) is proposed for servo motor drives. Generally, the motor system has nonlinearities in friction, load disturbance and magnetic saturation. It is necessary to treat the nonlinearities for improving performance in servo control. The FNN can be applied to control and identify a nonlinear dynamical system by learning capability. In this study, at first, a robust speed controller is developed by Lyapunov stability theory. However, the control input has discontinuity which generates an inherent chattering. To solve the problem and to improve the performances, the FNN is introduced to convert the discontinuous input to continuous one in error boundary. The FNN is applied to identify the inverse dynamics of the motor and to control the motor using coordination of feedforward control combined with inverse motor dynamics identification. The proposed controller is developed for an SR motor which has highly nonlinear characteristics and it is compared with an MRAC(Model Reference Adaptive Controller). Experiments on an SR motor illustrate te validity of the proposed controller.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1998년도 추계학술대회 논문집 학회본부 B
• /
• pp.537-539
• /
• 1998

In this paper, we construct the on-line model structure for the nonlinear process systems using the adaptive fuzzy-neural network. Adaptive fuzzy-neural network usually consists of two distinct modifiable structure, with both, the premise and the consequent part. These two parts can be adapted by different optimization methods, which are the hybrid learning procedure combining gradient descent method and least square method. To achieve the on-line model structure, we use the recursive least square method for the consequent parameter identification of nonlinear process. We design the interface between PLC and main computer, and construct the monitoring and control simulator for the nonlinear process. The proposed on-line modeling to real process is carried out to obtain the effective and accurate results.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1996년도 하계학술대회 논문집 B
• /
• pp.1155-1157
• /
• 1996

In this paper, the direct adaptive control using neural networks is presented for the control of chaotic nonlinear systems. The direct adaptive control method has an advantage that the additional system identification procedure is not necessary. Two direct adaptive control methods are applied to a Duffing's equation and the simulation results show the effectiveness of the controllers.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1996년도 하계학술대회 논문집 B
• /
• pp.1037-1041
• /
• 1996

Input-output linearization technique in nonlinear control does not guarantee the robustness in the presence of parameter uncertainty or unmodeled dynamics, etc. However, it has been used as an important preliminary step in achieving additional control objectives, for instance, robustness to parameter uncertainty and disturbance attenuation. An indirect adaptive control scheme based on input-output linearization is proposed in this paper. The scheme consists of a Hopfield network for process parameter identification and an adaptive sliding mode controller based on input-output linearization, which steers the system response into a desired configuration. A numerical example is presented for the trajectory tracking of uncertain nonlinear dynamic systems with slowly time-varying parameters.

• International Journal of Aeronautical and Space Sciences
• /
• 제3권1호
• /
• pp.86-94
• /
• 2002

The initial alignment of inertial platform for navigation system was considered. An adaptive filtering technique is developed for the system with unknown and varying sway disturbance. It is assumed that the random sway motion is the second order ARMA(Auto Regressive Moving Average) model and performed parameter identification for unknown parameters. Designed adaptive filter contain both a Kalman filter and a self-tuning filter. This filtering system can automatically adapt to varying environmental conditions. To verify the robustness of the filtering system, the computer simulation was performed with unknown and varying sway disturbance.