• Journal of international Conference on Electrical Machines and Systems
• /
• 제3권2호
• /
• pp.169-175
• /
• 2014

This paper presents an improved direct power control (DPC) strategy for grid-connected voltage source inverter (VSI) under unbalanced and harmonic grid voltage conditions. Based on the mathematic model of VSI with the negative sequence, 5th and 7th harmonic voltage components consideration, a PI controller is used in the proposed DPC strategy to achieve the average output power regulation. Furthermore, vector PI controller with the resonant frequency tuned at the two times and six times grid fundamental frequency is adopted to regulate both negative and harmonic components, and then two alternative targets of the balanced/sinusoidal current and smooth active/reactive output power can be achieved. Finally, simulation results based on MATLAB validate the availability of the proposed DPC strategy.

• Journal of international Conference on Electrical Machines and Systems
• /
• 제3권2호
• /
• pp.215-221
• /
• 2014

To satisfy the high voltage direct current (HVDC) grid connection demand for wind power generation system, a novel topology and control strategy of HVDC grid connection for open-winding permanent magnet synchronous generator (PMSG) based wind power generation system is proposed, in which two generator-side converter and two isolated DC/DC converters are used to transmit the wind energy captured by open winding PMSG to HVDC grid. By deducing the mathematic model of open winding PMSG, the vector control technique, position sensorless operation, and space vector modulation strategy is applied to implement the stable generation operation of PMSG. Finally, the simulation model based on MATLAB is built to validate the availability of the proposed control strategy.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.1513-1516
• /
• 2003

Genetic algorithm is well known as a stochastic searching method. In this paper, a modified genetic algorithm using 'Suppor Vector Machines (SVM)' is proposed. SVM is used to reduce the number of calling the objective function which in turn accelerate the searching speed compared to the conventional GA.

• Communications for Statistical Applications and Methods
• /
• 제26권6호
• /
• pp.635-644
• /
• 2019

Class probability is a fundamental target in classification that contains complete classification information. In this article, we propose a class probability estimation method when the predictor is functional. Motivated by Wang et al. (Biometrika, 95, 149-167, 2007), our estimator is obtained by training a sequence of functional weighted support vector machines (FWSVM) with different weights, which can be justified by the Fisher consistency of the hinge loss. The proposed method can be extended to multiclass classification via pairwise coupling proposed by Wu et al. (Journal of Machine Learning Research, 5, 975-1005, 2004). The use of FWSVM makes our method model-free as well as computationally efficient due to the piecewise linearity of the FWSVM solutions as functions of the weight. Numerical investigation to both synthetic and real data show the advantageous performance of the proposed method.

• 한국정밀공학회지
• /
• 제31권10호
• /
• pp.947-954
• /
• 2014

Performance of next generation susceptor is affected by temperature uniformity in order to produce reliably large-sized flat panel display. In this paper, we propose a learning estimation model of susceptor to predict and appropriately assess the temperature uniformity. Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs) are compared for the suitability of the learning estimation model. It is proved that SVMs provides more suitable verification of uniformity modeling than ANNs during each stage of temperature variations. Practical procedure for uniformity estimation of susceptor temperature was developed using the SVMs prediction algorithm.

• 한국토양비료학회지
• /
• 제42권Spc호
• /
• pp.8-13
• /
• 2009

심층토 내에서의 흐름과 이동과정을 포함하는 연구와 관리 측면에서 수학모델에 대한 관심도가 점점 증가하고 있다. 로제타는 토성이나 용적밀도 자료와 같은 대체 토양자료로부터 불포화수리특성에 대한 자료를 추정하는 프로그램이다. 이와 같은 형태의 모델은 애초 기본 토양자료를 수리특성자료로 전환하기 시작한 이래 대체 측정수단으로서 PTF라 불리워졌다. 이러한 기능은 유사-실험모델을 사용하여 예측한 자료를 근간으로 하여 직간접적으로 토양수분을 추정할 수 있다.

• 한국정보시스템학회지:정보시스템연구
• /
• 제18권3호
• /
• pp.375-399
• /
• 2009

In this study, we propose a integrated model of logistic regression, artificial neural networks, support vector machines(SVM), with case-based reasoning(CBR). To predict respondents in the direct marketing is the binary classification problem as like bankruptcy prediction, IDS, churn management and so on. To solve the binary problems, we employed logistic regression, artificial neural networks, SVM. and CBR. CBR is a problem-solving technique and shows significant promise for improving the effectiveness of complex and unstructured decision making, and we can obtain excellent results through CBR in this study. Experimental results show that the classification accuracy of integration model using CBR is superior to logistic regression, artificial neural networks and SVM. When we apply the customer response model to predict respondents in the direct marketing, we have to consider from the view point of profit/cost about the misclassification.

• 한국지진공학회:학술대회논문집
• /
• 한국지진공학회 2005년도 학술발표회 논문집
• /
• pp.331-342
• /
• 2005

This paper presents a non-destructive evaluation (NDE) technique for detecting damages on a jointed steel plate on the basis of the time of flight and wavelet coefficient, obtained from wavelet transforms of Lamb wave signals. Support vector machines (SVMs), which is a tool for pattern classification problems, was applied to the damage estimation. Two kinds of damages were artificially introduced by loosening bolts located in the path of the Lamb waves and those out of the path. The damage cases were used for the establishment of the optimal decision boundaries which divide each damage class's region from the intact class. In this study, the applicability of the SVMs was investigated for the damages in and out of the Lamb wave path. It has been found that the present methods are very efficient in detecting the damages simulated by loose bolts on the jointed steel plate.

• Geomechanics and Engineering
• /
• 제15권1호
• /
• pp.631-643
• /
• 2018

The estimation of the strength and other mechanical parameters characterizing the tensile behavior of granites can play an important role in civil engineering tasks such as design, construction, rehabilitation and repair of existing structures. The purpose of this paper is to apply data mining techniques, such as multiple regression (MR), artificial neural networks (ANN) and support vector machines (SVM) to estimate the mechanical properties of granites. In a first phase, the mechanical parameters defining the complete tensile behavior are estimated based on the tensile strength. In a second phase, the estimation of the mechanical properties is carried out from different combination of the physical properties (ultrasonic pulse velocity, porosity and density). It was observed that the estimation of the mechanical properties can be optimized by combining different physical properties. Besides, it was seen that artificial neural networks and support vector machines performed better than multiple regression model.

• Communications for Statistical Applications and Methods
• /
• 제16권6호
• /
• pp.997-1004
• /
• 2009

A standard approach is to classify all of future observations. In some cases, however, it would be desirable to defer a decision in particular for observations which are hard to classify. That is, it would be better to take more advanced tests rather than to make a decision right away. This motivates a classifier with a reject option that reports a warning for those observations that are hard to classify. In this paper, we present the method which gives efficient computation with a reject option. Some numerical results show strong potential of the propose method.