• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2007년도 춘계학술대회B
• /
• pp.2250-2254
• /
• 2007

Comprehensive analytical models focusing on the anode water loss, the cathode flooding, water equilibrium, and water management strategy are developed for polymer electrolyte fuel cells. Analytical solutions presented in this study are compared with two-dimensional computational results and shows a good agreement in predicting those critical characteristics of water. General features of water concentration profile as a function of membrane thickness and current density are presented to illustrate the net effect of the back-diffusion of water from the cathode to anode and the water production by the cathode catalytic reaction on water transport over a fuel cell domain. As one of practical applications, the required humidity level of feed streams for full saturation at the channel outlets are investigated as a function of the physical operating condition. These analytical models can provide good understanding on the characteristic water

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1988년도 한국자동제어학술회의논문집(국제학술편); 한국전력공사연수원, 서울; 21-22 Oct. 1988
• /
• pp.943-946
• /
• 1988

A simple method is proposed for determining the frequency response function G(j.omega.) of a system using a pair of characteristic M-sequences (maximum length linear feed back shift register sequence). When a characteristic M-sequence is sampled with q$_{1}$ and q$_{2}$ both of which are coprime with N, where N is the period of the M-sequence, the obtained pair of sequences have conjugate complex frequency spectrum. Making use of this fact, two charcteristic M-sequences having conjugate complex frequency spectrum are applied to a system to be measured. Since the magnitude of spectrium of M-sequence is known, the gain of G(j.omega.) is directly obtained from the Fourier transform of the system output. The phase of G(j.omega.) is obtained simply by taking the average of the two phases of output spectrum.

• 한국정보처리학회논문지
• /
• 제4권7호
• /
• pp.1749-1758
• /
• 1997

전력수요의 예측은 예측기간에 따라 중장기 전력수요 예측과 단기 부하 예측으로 구분할 수 있다. 기존의 단기 부하예측은 주로 역전파 알고리즘(back propagation algorithm)다층퍼셉트론을 이용하여 예측을 하였으나 이는 학습시간이 많이 걸릴 뿐만 아니라 학습도중에 지역최소점(local minima)에 빠져 학습이 계속되지 못한다는 문제가 있다. 본 논문은 이러한 역전파 알고리즘의 문제점을 해결할 수 있는 방법으로 Radial Basis 함수(Radial Basis Function)를 이용하여 동적 단기부하 예측 모형을 제안한다. Radial Basis 함수는 하나의 은닉층(hidden layer)을 갖고 있으며, 전방향(feed-forward)학습을 한다는 특징이 있다. 본 논문에서 제안한 단기 부하 예측모형은 학습을 하기 위하여 시간대별 부하량을 클러스터링 하고, 이 클러스터의 중심값을 Radial Basis 함수의 은닉층으로 하여 학습을 한 다음 예측하고자 하는 패턴을 한 단위로 하여 시단대별로 예측하였다. 기존의 연구에서의 클러스터링 방법으로는 통계학의 K-Means 방법이나 Kohonen의 LVQ(Learning Vector Quantization)을 주로 이용하였으나 본 논문에서는 패턴의 분류에 있어서 다른 알고리즘보다 편차가 작은 Pal, et. al.의 GLVQ(Generalized LVQ) 알고리즘을 이용하였다. 본 논문에서 이용한 데이타는 1995년 3월 1일-3일, 6월 1일-3일, 7월 1일-3일, 9월 1일-3일, 11월 1일-3일의 72시간 데이타를 입력하여 월별 4일의 24시간의 예측시간으로 예측하였다. 실험결과 월별 1일과 3일까지의 학습데이타로 1시간 후의 부하량을 24시간동안 예측한 결과 1.3795%의 평균 오차율로 예측하였다.

• Journal of Information Technology Applications and Management
• /
• 제19권1호
• /
• pp.1-12
• /
• 2012

Data mining is the process of searching and analyzing large quantities of data for finding out meaningful patterns and rules. Artificial Neural Network (ANN) is one of the tools of data mining which is becoming very popular in forecasting the future values. Some of the areas where it is used are banking, medicine, retailing and fraud detection. In finance, artificial neural network is used in various disciplines including stock market forecasting. In the stock market time series, due to high volatility, it is very important to choose a model which reads volatility and forecasts the future values considering volatility as one of the major attributes for forecasting. In this paper, an attempt is made to develop two models - one using feed forward back propagation Artificial Neural Network and the other using Autoregressive Conditional Heteroskedasticity (ARCH) technique for forecasting stock market returns. Various parameters which are considered for the design of optimal ANN model development are input and output data normalization, transfer function and neuron/s at input, hidden and output layers, number of hidden layers, values with respect to momentum, learning rate and error tolerance. Simulations have been done using prices of daily close of Sensex. Stock market returns are chosen as input data and output is the forecasted return. Simulations of the Model have been done using MATLAB$^{(R)}$ 6.1.0.450 and EViews 4.1. Convergence and performance of models have been evaluated on the basis of the simulation results. Performance evaluation is done on the basis of the errors calculated between the actual and predicted values.

• Journal of Advanced Marine Engineering and Technology
• /
• 제3권1호
• /
• pp.19-31
• /
• 1979

Recently the adaptive control system, which keeps the control system always optimal by adjusting the control parameters automatically according to the variations of the plant parameters, have become very important in the field of control engineering. The adaptive control systems are usally composed of the plant identification, the decision of the optimal control parameters, and the adjustment of the control parameters. This paper deals with a method of the adaptive control system when PI or PID controller is used in the feed back control system. Its controlled object (the plant) is assumed to be described by the transfer function of $\frac{ke^{-LS}}{1+TS}$ where k, T and L are steady state gain, time constant and pure dead time respectively, and their values are variable in accordance with the change of environmental circumstance. It has been known that a pseudo-random binary signal is quite effective for the measurement of an impulse response of a plant. In adaptive control systems, however, the impulse response itself is not appropriate to determine the control parameters. In this paper, the authors propose a method to estimate directly the parameters of the plant k, T and L by means of the correlation technique using 3 level M-sequence signal as a test signal. The authors also propose a method to determine the optimal parameters of the PI or PID controller in the sense of minimizing the square integral of the control error in the feed back control system, and the values of the optimal parameters are computed numerically for various values of T and L, and the results are examined and compared with those of the conventional methods. Finally the above-mentioned two methods are combined and an algorithm to struct an adaptive control system is suggested. The experiments for the indicial responses by means of both the model of the temperature control system using SCR actuater and the analog simulations have shown good results as expected, and the effectiveness of the proposed method is verified. The M-sequence generator and the time delay circuit, which are manufactured for the experiments, are operated in quite a good condition.

• 전기학회논문지P
• /
• 제58권3호
• /
• pp.316-322
• /
• 2009

This paper presents an analytical design method of a passive harmonic filter for a three-phase diode rectifier and uses a new transfer function approach in the analysis and design. The transfer function approach derives an analytical formulation of an utility system including passive filters with a basis of Laplace transform and provides a graphical formulation so that a visualized insight into an interaction between individual filter and system response can be attainted. Harmonic impedance, voltage division and current division transfer function are used as a design tool, which makes a calculated filter parameters to satisfy IEEE-519 distortion limits. A simple five-step design procedure is introduced in the filter design, which consists of system analysis, selection of PCC(Point of Common Coupling), filter specification calculation, appropriate filter design for system and filter implementation. Philosophy governing the design procedure is based on a numerical/graphical iterative solution, trial and error with visualization feed-back based on "algebra on the graph". Finally, performance of the designed passive harmonic filter is verified by experiment and shows that 5th, 7th, 9th, 11th and 13th harmonics are decreased within IEEE-519 distortion limits, respectively.

• 한국콘텐츠학회논문지
• /
• 제1권1호
• /
• pp.8-14
• /
• 2001

본 논문에서는 의료영상에서 특정 장기를 추출하여 질환 부위를 인식하는 알고리즘을 제안한다. 의료영상이 추출되어진 장기 부위에서 질환을 인식하기 위하여 단일 신경회로망을 이용하면 신경회로망의 학습 능력과 일반화 능력이 한정적이므로 성능개선에 많은 문제가 있다. 따라서 추출된 장기로부터 질환부위를 인식하는 것은 신경회로망을 복합적인 방법, 즉 RBF (Radial Basis Function), BP (Back Propagation)로 구성하여 단일 신경회로망의 단점을 극복하였다. 본 논문에서 제안하는 알고리즘은 입력 의료영상의 다양한 형태 변화에 적응력이 뛰어남을 실험결과로 알 수 있었다. 그리고, 전체 알고리즘의 수행시간이 장기추출 알고리즘을 포함하여 일반적으로 10초 이내에 수행됨을 실험 결과 알 수 있었다. 제안된 알고리즘은 실시간으로 의료영상의 질환부위를 인식하여 판별 자동화를 통해 원격의료에 사용 되어 질 수 있다.

• 대한기계학회논문집A
• /
• 제21권5호
• /
• pp.828-834
• /
• 1997

The knowledge of material stress-strain behavior is an essential requirement for design and analysis of deformation processes. Empirical stress-strain relationship and constitutive equations describing material behavior during deformation are being widely used, despite suffering some drawbacks in terms of ease of development, accuracy and speed. In the present study, back-propagation neural networks are used to model and predict the flow stresses of a HSLA steel under conditions of constant strain, strain rate and temperature. The performance of the network model is comparedto those of statistical models on rate equations. Well-trained network model provides fast and accurate results, making it superior to statistical models.

• 전기학회논문지
• /
• 제68권1호
• /
• pp.77-82
• /
• 2019

In this paper, a 0.6~6GHz quad-ridge horn antenna which can be used for the antenna measurement of 5.8GHz WiFi system from lowest frequency band of mobile LTE (Long Term Evolution) is designed and implemented. The quad-ridge horn antenna has quadruple ridges of exponential function, a back-short and a cavity. Based on this structure, we design the cavity size, ridge gap and feed gap to have broadband characteristics. For implementation, the plates material of aluminum and copper are used for the horn and four ridges, respectively. And the insulator supports are used to maintain the gap between ridges. By measurement, antenna has the gain of 6.2~13.35dBi with the return loss of less than -6dB (under VSWR 3 : 1) in the entire design band. The results of this study can be widely used to the antenna studies on the mobile communication including low frequency band of LTE, the EMI measurement and the standard calibration measurement.

• 소성∙가공
• /
• 제30권3호
• /
• pp.125-133
• /
• 2021

In this study, response surface method (RSM), back propagation neural network (BPNN), and genetic algorithm (GA) were used for modeling and multi-objective optimization of the parameters of AA5052-H32 in incremental sheet forming (ISF). The goal of optimization is to determine the maximum forming angle and minimum surface roughness, while varying the production process parameters, such as tool diameter, tool spindle speed, step depth, and tool feed rate. A Box-Behnken experimental design (BBD) was used to develop an RSM model and BPNN model to model the variations in the forming angle and surface roughness based on variations in process parameters. Subsequently, the RSM model was used as the fitness function for multi-objective optimization of the ISF process the GA. The results showed that RSM and BPNN can be effectively used to control the forming angle and surface roughness. The optimized Pareto front produced by the GA can be utilized as a rational design guide for practical applications of AA5052 in the ISF process