• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.24 no.6
• /
• pp.538-544
• /
• 2012

Analysis of thermal performance is required for the economic operation of turbine cycle of power plant. We developed corrective model of main feed water flow which is the most important parameter for the precise analysis of turbine cycle performance. Classification model for the identification of feed water flow measurement status was applied to increase the suitability of the corrective model. We used neural network and support vector machine to develop estimation model of main feed water flow with more generalization capability. The estimation model can be used practically to evaluate corrective performance of turbine cycle plant.

• Proceedings of the KIEE Conference
• /
• summer
• /
• pp.896-898
• /
• 2004

The lagging reactive power should be supplied for the excitation of isolated squirrel-cage induction generators by external circuit. This paper deals with a technique to drive the equations for analysis of the excitation characteristics and performance of an isolated squirrel-cage induction generator from the conventional equivalent circuit of induction machine, transform the equations into d-q coordinates to use vector control technique, and carry out the simulation of an induction generator system with various conditions using MATLAB. The results of the simulation indicate that moderate reactive power can be controlled effectively to maintain constant voltage over a wide range of the rotor speeds and loads.

• Proceedings of the KIPE Conference
• /
• 2007.07a
• /
• pp.205-207
• /
• 2007

Position information is very important when driving the Permanent Magnet Synchronous Motor(PMSM). Generally, resolver is used to obtain exact position information. However, it generates periodic position errors due to the transformer ratio difference and excitation signal distortion. When the vector control is done with the position information that includes position error, torque ripple is periodically generated. This paper proposes the solution through analysis of above problem. Also, it’s validity is verified by simulation and experiment.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2003.06a
• /
• pp.78-81
• /
• 2003

본 논문은 SVM(support vector machine)을 이용한 음성인식기에 대해 효과적인 특징 파라메터를 제안한다. SVM은 특징 공간에서 비선형 경계를 찾아 분류하는 방법으로 적은 학습 데이터에서도 좋은 분류 성능을 나타낸다고 알려져 있으며 최적의 특징 파라메터를 선택하기 위해 본 논문에서는 SVM을 이용한 음성인식기를 사용하여 PCA(principal component analysis), ICA(independent component analysis) 알고리즘을 적용하여 MFCC(met frequency cepstrum coefficient)의 특징 공간을 변화시키면서 각각의 인식 성능을 비교 검토하였다. 실험 결과 ICA에 의한 특징 파라메터가 가장 우수한 성능을 나타내었으며 특징 공간에서 각 클래스의 분포도 또한 ICA가 가장 높은 선형 분별성을 나타내었다.

• Proceedings of the KIEE Conference
• /
• 2000.11b
• /
• pp.241-243
• /
• 2000

In this paper, we analyze three-dimensional magnetic field distribution of a convergence purity maget(C.P.M) which is used for a cathode ray tube. The magnetization vector distribution of the C.P.M is obtained from the result of magnetization process analysis using the 2D F.E.M. Then the motion of electron beam passing through the inner space of the C.P.M is determined and compared with experimental result.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2005.11a
• /
• pp.571-578
• /
• 2005

Corporate credit rating analysis has drawn a lot of research interests in previous studies, and recent studies have shown that machine learning techniques achieved better performance than traditional statistical ones. This paper applies support vector machines (SVMs) to the corporate credit rating problem in an attempt to suggest a new model with better explanatory power and stability. To serve this purpose, the researcher uses a grid-search technique using 5-fold cross-validation to find out the optimal parameter values of kernel function of SVM. In addition, to evaluate the prediction accuracy of SVM, the researcher compares its performance with those of multiple discriminant analysis (MDA), case-based reasoning (CBR), and three-layer fully connected back-propagation neural networks (BPNs). The experiment results show that SVM outperforms the other methods.

• Journal of the Korean Institute of Navigation
• /
• v.5 no.2
• /
• pp.99-108
• /
• 1981

As far as ship's cargo handling devicesareconcerned, the derrick system has been used comprehensively in the marine. Even though there are several new devices for ship's cargo gear, such as gantry crane, jib crane adn self unloader, the derrick system, with its improved rigging method, still retains its utmost reputations among ship's owners. Therefore the method of calculating the system's militating stresses in the course of cargo operation needs to be more convenient and analytical. Here the author attempts to introduce the calculating method of stresses by means of vector analysis. The calculating method is able to analyze the stresses acting in every part of the cargo gear systems, such as union purchase, slewing or its modified system.

• Proceedings of the KIEE Conference
• /
• 2005.07b
• /
• pp.1162-1164
• /
• 2005

A Linear Induction Motor that generates the direct thrust directly, is widely used for the operation system of electrified railroad, elevation system, conveyer system, and so on. There are two analysis methode of linear induction motor characteristics. One is the electrical magnetic analyzing, the other is analyzing equivalent circuit. The electrical magnetic analyzing methode has available advantages to consider the physical condition. The equivalent circuit analyzing methode has the elementary methode in the system of vector control and over shoot situation. In this paper, It is used the dynamic characteristic analyzing methode that can calculate efficiently the end effect by using equivalent circuit methode in the operating linear induction motor system modeling and doing simulation of output characteristics of vector controller.

• Proceedings of the KIEE Conference
• /
• 1998.11a
• /
• pp.159-162
• /
• 1998

In this paper, an algorithm of the automatic commissioning for vector controlled induction motor using controller characteristics is proposed. The automation of commissioning sequence is carried out using Walsh function analysis. In the proposed method, the distortion of the controller output waveform is easily detected and can be automatically tuned by using Walsh function analysis. This tuning algorithm has the advantage such as less sensitivity to the variation of other parameters and high sensitivity to parameter error. Hence, the easy tuning of high performance drive system of the induction motor is possible. Some experiments are carried out to prove the validity of the proposed automatic commissioning algorithm.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.05b
• /
• pp.314-317
• /
• 2003

기존의 침입탐지 시스템에서는 오용탐지모델이 널리 사용되고 있다. 이 모델은 낮은 오판율(False Alarm rates)을 가지고 있으나, 새로운 공격에 대해 전문가시스템(Expert Systems)에 의한 규칙추가를 필요로 한다. 그리고 그 규칙과 완전히 일치되는 시그너처만 공격으로 탐지하므로 변형된 공격을 탐지하지 못한다는 문제점을 가지고 있다 본 논문에서는 이러한 문제점을 보완하기 위해 주성분분석(Principle Component Analysis; 이하 PCA)과 서포트 벡터 머신(Support Vector Machines; 이하 SVM)을 이용한 침입탐지 시스템을 제안한다. 네트워크 상의 패킷은 PCA를 이용하여 결정된 주성분 공간에서 해석되고, 정상적인 흐름과 비정상적인 흐름에 대한 패킷이미지패턴으로 정규화 된다. 이러한 두 가지 클래스에 대한 SVM 분류기를 구현한다. 개발하는 침입탐지 시스템은 알려진 다양한 침입유형뿐만 아니라, 새로운 변종에 대해서도 분류기의 유연한 반응을 통하여 효과적으로 탐지할 수 있다.