• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.941-946
• /
• 2005

In this paper an active random noise control using adaptive learning rate neural networks is presented. The adaptive learning rate strategy increases the learning rate by a small constant if the current partial derivative of the objective function with respect to the weight and the exponential average of the previous derivatives have the same sign, otherwise the learning rate is decreased by a proportion of its value. The use of an adaptive learning rate attempts to keep the learning step size as large as possible without leading to oscillation. It is expected that a cost function minimize rapidly and training time is decreased. Numerical simulations and experiments of active random noise control with the transfer function of the error path will be performed, to validate the convergence properties of the adaptive learning rate Neural Networks. Control results show that adaptive learning rate Neural Networks control structure can outperform linear controllers and conventional neural network controller for the active random noise control.

• 말소리와 음성과학
• /
• 제3권3호
• /
• pp.91-98
• /
• 2011

In this paper, a multi-channel speech enhancement method using the linearly constrained minimum variance (LCMV) algorithm and a variable learning rate control is proposed. To control the learning rate for adaptive filters of the LCMV algorithm, the direction of arrival (DOA) is measured for each short-time input signal and the likelihood function of the target speech presence is estimated to control the filter learning rate. Using the likelihood measure, the learning rate is increased during the pure noise interval and decreased during the target speech interval. To optimize the parameter of the mapping function between the likelihood value and the corresponding learning rate, an exhaustive search is performed using the Bark's scale distortion (BSD) as the performance index. Experimental results show that the proposed algorithm outperforms the conventional LCMV with fixed learning rate in the BSD by around 1.5 dB.

• 제어로봇시스템학회논문지
• /
• 제3권4호
• /
• pp.363-372
• /
• 1997

In this paper, the design and the implementation of the adaptive learning rate neural network controller for an articulate robot, which is being developed (or) has been developed in our Automatic Control Laboratory, are mainly discussed. The controller reduces software computational load via distributed processing method using multiple CPU's, and simplifies hardware structures by the time-division control with TMS32OC31 DSP chip. Proposed neural network controller with adaptive learning rate structure using expert's heuristics can improve learning speed. The proposed controller verifies its superiority by comparing response characteristics of conventional controller with those of the proposed controller that are obtained from the experiments for the 5 axis vertical articulated robot. We, also, present the generalization property of proposed controller for unlearned trajectory and the change of load through experimental data.

• 제어로봇시스템학회논문지
• /
• 제13권4호
• /
• pp.309-314
• /
• 2007

This paper presents an adaptive neural computation algorithm for multi-layered neural networks which are applied to identify the characteristic function of dynamic systems. The main feature of the proposed algorithm is that the initial learning rate for the employed neural network is assigned systematically, and also the assigned learning rate can be adjusted empirically for effective neural leaning. By employing the approach, enhanced modeling of dynamic systems is possible. The effectiveness of this approach is veri tied by simulations.

• International Journal of Control, Automation, and Systems
• /
• 제3권1호
• /
• pp.43-55
• /
• 2005

In this paper, a predictive control method using self-recurrent wavelet neural network (SRWNN) is proposed for chaotic systems. Since the SRWNN has a self-recurrent mother wavelet layer, it can well attract the complex nonlinear system though the SRWNN has less mother wavelet nodes than the wavelet neural network (WNN). Thus, the SRWNN is used as a model predictor for predicting the dynamic property of chaotic systems. The gradient descent method with the adaptive learning rates is applied to train the parameters of the SRWNN based predictor and controller. The adaptive learning rates are derived from the discrete Lyapunov stability theorem, which are used to guarantee the convergence of the predictive controller. Finally, the chaotic systems are provided to demonstrate the effectiveness of the proposed control strategy.

• 전기전자학회논문지
• /
• 제2권1호
• /
• pp.134-138
• /
• 1998

트래픽의 통계적 변동과 고도의 시변 특성 때문에, 최소의 반응시간을 가지고 고도의 동적인 기술과 적응 그리고 학습능력을 요구하는 네트워크의 자원으로 관리하도록 한다. 뉴럴 네트워크는 ATM 셀 도착율과 큐 길이를 정규화시키며, 그것은 적응 학습 알고리즘을 가지고, ATM 네트워크에서 발생되는 특주를 방지하기 위한 방법을 연구한다.

• 한국항해항만학회지
• /
• 제30권4호
• /
• pp.259-265
• /
• 2006

This paper presents an improved adaptive neural network autopilot based on our previous study for track-keeping control of ships. The proposed optimal neural network controller can automatically adapt its learning rate and number of iterations. Firstly, the track-keeping control system of ships is described For the track-keeping control task, a way-point based guidance system is applied To improve the track-keeping ability, the off-track distance caused by external disturbances is considered in learning process of neural network controller. The simulations of track-keeping performance are presented under the influence of sea current and wind as well as measurement noise. The toolbox for track-keeping simulation on Mercator chart is also introduced.

• 한국항해항만학회지
• /
• 제30권2호
• /
• pp.119-124
• /
• 2006

In Part I(theoretical study) of the paper, a new adaptive autopilot for ships based on Adaptive Neural Networks was proposed. The ANNAI autopilot was designed for course-keeping, turning and track-keeping control for ships. In this part of the paper, to show the effectiveness and feasibility of the ANNAI autopilot and automatic selection algorithm for learning rate and number of iterations, computer simulations of course-keeping and track-keeping tasks with and without the effects of measurement noise and external disturbances are presented. Additionally, the results of the previous studies using Adaptive Neural Network by backpropagation algorithm are also showed for comparison.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.640-645
• /
• 2004

This paper proposes a direct adaptive control method using self-recurrent wavelet neural network (SRWNN) for stable path tracking of mobile robots. The architecture of the SRWNN is a modified model of the wavelet neural network (WNN). Unlike the WNN, since a mother wavelet layer of the SRWNN is composed of self-feedback neurons, the SRWNN has the ability to store the past information of the wavelet. For this ability of the SRWNN, the SRWNN is used as a controller with simpler structure than the WNN in our on-line control process. The gradient-descent method with adaptive learning rates (ALR) is applied to train the parameters of the SRWNN. The ALR are derived from discrete Lyapunov stability theorem, which are used to guarantee the stable path tracking of mobile robots. Finally, through computer simulations, we demonstrate the effectiveness and stability of the proposed controller.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년 학술대회 논문집 정보 및 제어부문
• /
• pp.226-228
• /
• 2006

This paper is concerned with an Adaptive Fuzzy Sliding Mode Control(AFSMC) that the fuzzy systems are used to approximate the unknown functions of nonlinear system. In the adaptive fuzzy system, we adopt the adaptive law to approximate the dynamics of the nonlinear plant and to adjust the parameters of AFSMC. The stability of the suggested control system is proved via Lyapunov stability theorem, and convergence and robustness properties are demonstrated. The simulation results demonstrate that the performance is improved and the system also exhibits stability.