• The Transactions of the Korean Institute of Electrical Engineers B
• /
• v.52 no.6
• /
• pp.262-270
• /
• 2003

In this paper, the characteristics of single-phase line-start permanent magnet synchronous motor driven by constant voltage are analyzed on d-q axis vector diagram and compared with that of current controlled motor. The coupled method of symmetrical coordinates and d-q axis voltage equation are applied to the analysis method like the analysis of single-phase induction motor. From the result of the analysis, it is seen that motors driven by constant voltage source have effects on not only the amplitude of current and torque but also current and current phase angle, so overall characteristics such as power factor and load angle are affected by circuit parameters. For precise analysis and design of single-phase line-start synchronous motor, its characteristics should be analyzed on d-q axis vector plan in consideration of the variation of circuit parameters.

• Asia pacific journal of information systems
• /
• v.26 no.4
• /
• pp.526-541
• /
• 2016

This research aims to examine the predictive power of multiple online stock message boards, namely, NAVER Finance and PAXNET, which are the most popular stock message boards in South Korea, in stock market activities. If predictive power exists, we then compare the predictive power of multiple online stock message boards. To accomplish the research purpose, we constructed a panel data set with close price, volatility, Spell out acronyms at first mention.PER, and number of posts in 40 companies in three months, and conducted a panel vector auto-regression analysis. The analysis results showed that the number of posts could predict stock market activities. In NAVER Finance, previous number of posts positively influenced volatility on the day. In PAXNET, previous number of posts positively influenced close price, volatility, and PER on the day. Second, we confirmed a difference in the prediction power for stock market activities between multiple online stock message boards. This research is limited by the fact that it only considered 40 companies and three stock market activities. Nevertheless, we found correlation between online stock message board and stock market activities and provided practical implications. We suggest that investors need to focus on specific online message boards to find interesting stock market activities.

• Asia pacific journal of information systems
• /
• v.15 no.2
• /
• pp.51-63
• /
• 2005

There has been substantial research into the bankruptcy prediction. Many researchers used the statistical method in the problem until the early 1980s. Since the late 1980s, Artificial Intelligence(AI) has been employed in bankruptcy prediction. And many studies have shown that artificial neural network(ANN) achieved better performance than traditional statistical methods. However, despite ANN's superior performance, it has some problems such as overfitting and poor explanatory power. To overcome these limitations, this paper suggests a relatively new machine learning technique, support vector machine(SVM), to bankruptcy prediction. SVM is simple enough to be analyzed mathematically, and leads to high performances in practical applications. The objective of this paper is to examine the feasibility of SVM in bankruptcy prediction by comparing it with ANN, logistic regression, and multivariate discriminant analysis. The experimental results show that SVM provides a promising alternative to bankruptcy prediction.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.30 no.1
• /
• pp.55-74
• /
• 2005

Bankruptcy prediction has drawn a lot of research interests in previous literature, and recent studies have shown that machine learning techniques achieved better performance than traditional statistical ones. This paper employs a relatively new machine learning technique, support vector machines (SVMs). to bankruptcy prediction problem in an attempt to suggest a new model with better explanatory power and stability. To serve this purpose, we use grid search technique using 5-fold cross-validation to find out the optimal values of the parameters of kernel function of SVM. In addition, to evaluate the prediction accuracy of SVM. we compare its performance with multiple discriminant analysis (MDA), logistic regression analysis (Logit), and three-layer fully connected back-propagation neural networks (BPNs). The experiment results show that SVM outperforms the other methods.

• Journal of Electrical Engineering and Technology
• /
• v.8 no.2
• /
• pp.304-315
• /
• 2013

In this paper, analysis of cascaded H-bridge multilevel inverter in DTC-SVM (Direct Torque Control-Space Vector Modulation) based induction motor drive for FCEV (Fuel Cell Electric Vehicle) is presented. Cascaded H-bridge multilevel inverter uses multiple series units of H-bridge power cells to achieve medium-voltage operation and low harmonic distortion. In FCEV, a fuel cell stack is used as the major source of electric power moreover the battery and/or ultra-capacitor is used to assist the fuel cell. These sources are suitable for utilizing in cascaded H-bridge multilevel inverter. The drive control strategy is based on DTC-SVM technique. In this scheme, first, stator voltage vector is calculated and then realized by SVM method. Contribution of multilevel inverter to the DTC-SVM scheme is led to achieve high performance motor drive. Simulations are carried out in Matlab-Simulink. Five-level and nine-level inverters are applied in 3hp FCEV induction motor drive for analysis the multilevel inverter. Each H-bridge is implemented using one fuel cell and battery. Good dynamic control and low ripple in the torque and the flux as well as distortion decrease in voltage and current profiles, demonstrate the great performance of multilevel inverter in DTC-SVM induction motor drive for vehicle application.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.485-487
• /
• 2003

Independent Component Analysis (ICA) is used to generate ICA filter for computing feature vector for image window. Filters that have high discrimination power are selected to classify image from these ICA filters. Proposed classification algorithm is based on probability distribution of feature vector.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.52 no.6
• /
• pp.333-341
• /
• 2003

In induction motor control systems driven by the indirect vector control scheme, the rotor speed is measured to determine the flux angle which is a key variable in the control algorithm. The most popular way to measure the angular velocity is the use of rotary encoder. Since the errorneous measurement of rotor speed results in incorrect flux angle estimate, the control input generated based on the faulty information should be far from the desired (correct) value and deteriorates the overall control performance. In this paper the effects of encoder fault on motor variables and control performance are analyzed by both theoretical approach and experimental study. A parity equation based on the Power is suggested and applied to detect the incipient fault of encoder.

• Journal of Power Electronics
• /
• v.12 no.3
• /
• pp.477-486
• /
• 2012

This paper proposes a novel current control scheme for vector-controlled induction machine (IM) drives in the overmodulation (OVM) range, with which the voltage utilization of the voltage-source inverter (VSI) can be maximized. In the OVM region, the original voltage reference is modified by changing its magnitude and angle, which causes the motor current to be distorted, resulting in a deterioration of the current control performance. To meet with this situation, the harmonic components in the feedback currents should be eliminated before being input to the PI current controllers. For this, a composite observer is applied to extract the fundamental and harmonic components from the distorted currents, which gives a good performance without a delay and the effect of a fundamental frequency variation. In addition, through a detailed analysis of the response of the PI current controllers in the OVM range, the effectiveness of using the composite observer is demonstrated. Simulation and experimental results for a 3-kW induction motor drive are shown to verify the validity of the proposed method.

• Journal of Power Electronics
• /
• v.13 no.4
• /
• pp.647-655
• /
• 2013

In this paper, an approach to reduce the common-mode voltage and to eliminate narrow pulse for implemented AC-DC matrix converters is presented. An improved space vector modulation (SVM) strategy is developed by replacing the zero space vectors with suitable pairs of active ones. Further, while considering the commutation time, the probability of narrow pulse in the conventional and proposed SVM methods are derived and compared. The advantages of the proposed scheme include: a 50% reduction in the peak value of the common-mode voltage; improved input and output performances; a reduction in the switching loss by a reduced number of switching commutations and a simplified implementation via software. Experimental results are presented to demonstrate the correctness of the theoretical analysis, as well as the feasibility of the proposed strategy.

• Journal of Power Electronics
• /
• v.14 no.5
• /
• pp.989-999
• /
• 2014

High-performance Current Source Inverter (CSI)-fed, variable speed alternating current drives are prepared for various industrial applications. CSI-fed Induction Motor (IM) drives are managed by using different control methods. Noteworthy methods include scalar Control (V/f), Input-Output Linearization (IOL) control, Field-Oriented Control (FOC), and Direct Torque Control (DTC). The objective of this work is to compare the dynamic performance of the aforementioned drive control methods for CSI-fed IM drives. The dynamic performance results of the proposed drives are individually analyzed through sensitivity tests. The tests selected for the comparison are step changes in the reference speed and torque of the motor drive. The operation and performance of different vector control methods are verified through simulations with MATLAB/Simulink and experimental results.