• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.27 no.6
• /
• pp.871-878
• /
• 2003

With the development of micro -technology, the demand for micro actual ing device is increasing. But, it is difficult to achieve high resolution and wide bandwidth with the conventional contact systems. So, the contact-free systems which are suspended or levitated by magnetic force or air bearing were proposed. These systems can be applied to high precision stages and alignment apparatuses. This paper describes a magnetically suspended system with four degrees of freedom which are composed of three rotations (roll, pitch, yaw), and one translation ( z). The operating principle and the structure of the system are similar to variable reluctance type electric machines. In this study, the force analysis is executed using magnetic circuit and virtual work principle, and the equations that describe the dynamics of the system are presented. The multivariable PID controller is adapted to the system and the experiment is executed.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.59 no.11
• /
• pp.1986-1989
• /
• 2010

The modification of magnetic structures for an E-core switched reluctance machine (SRM) comprising two segmented stator cores or a monolithic stator core is presented for ease of assembly, good manufacturability, mechanical robustness, and electromagnetic performance improvement. The E-core stator has four small poles with phase windings and two or four large poles (hereafter referred to as common poles), in between. The common poles are shared by both phases for positive torque generation during the entire operation. The E-core SRMs are compared to a conventional two-phase SRM. The comparison includes cost savings, torque, copper and core losses, and efficiency in order to validate the distinct features of the E-core SRMs. Magnetic equivalent circuit (MEC) technique is employed for proving the benefits of the E-core common-pole structure.

• Journal of information and communication convergence engineering
• /
• v.21 no.2
• /
• pp.159-166
• /
• 2023

The COI gene is a sequence of approximately 650 bp at the 5' terminal of the mitochondrial Cytochrome c Oxidase subunit I (COI) gene. As an effective DeoxyriboNucleic Acid (DNA) barcode, it is widely used for the taxonomic identification and evolutionary analysis of species. We created a CNN-LSTM hybrid model by combining the gene features partially extracted by the Long Short-Term Memory ( LSTM ) network with the feature maps obtained by the CNN. Compared to K-Means Clustering, Support Vector Machines (SVM), and a single CNN classification model, after training 278 samples in a training set that included 15 genera from two orders, the CNN-LSTM hybrid model achieved 94% accuracy in the test set, which contained 118 samples. We augmented the training set samples and four genera into four orders, and the classification accuracy of the test set reached 100%. This study also proposes calculating the cosine similarity between the training and test sets to initially assess the reliability of the predicted results and discover new species.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2005.11a
• /
• pp.178-181
• /
• 2005

Support vector machines is a powerful learning algorithm and attempt to separate belonging to two given sets in N-dimensional real space by a nonlinear surface, often only implicitly dened by a kernel function. We described breast tissue images analyses using texture features from Haar wavelet transformed images to classify breast lesion of ductal organ Benign, DCIS and CA. The approach for creating a classifier is composed of 2 steps: feature extraction and classification. Therefore, in the feature extraction step, we extracted texture features from wavelet transformed images with $10{\times}$ magnification. In the classification step, we created four classifiers from each image of extracted features using SVM(Support Vector Machines). In this study, we conclude that the best classifier in histological sections of breast tissue in the texture features from second-level wavelet transformed images used in Polynomial function.

• Journal of international Conference on Electrical Machines and Systems
• /
• v.2 no.4
• /
• pp.460-465
• /
• 2013

Electrical equipments of nuclear power plant are divided into class 1E and non-class 1E. Electrical equipment and systems that are essential to emergency reactor shutdown, containment isolation, reactor core cooling, and containment and reactor heat removal, are classified as class 1E. batteries of nuclear power plant are divided into four channels, which are physically and electrically separate and independent. The battery bank of class 1E DC power system of the nuclear power plant use lead-acid batteries in present. The lead acid battery, which has a high energy density, is the most popular form of energy storage. Kt factor of lead-acid battery is used to determine battery size and it is one of calculatiing coefficient for capacity. this paper analyzes Kt factor of lead-acid battery for the DC power system of nuclear power plant. In addition, correlation between Kt parameter and peukert's exponent of lead-acid battery for nuclear plant are discussed. The analytical results contribute to optimize of determining size Lead-acid battery bank.

• Journal of international Conference on Electrical Machines and Systems
• /
• v.3 no.4
• /
• pp.367-373
• /
• 2014

The most common current controller for the Switched Reluctance Motor (SRM) is the hysteresis controller. This method, however, suffers from such drawbacks as variable switching frequency, consequent audible noise and high current ripple. These disadvantages make this controlling method undesirable for many applications. The alternative solution is the PI controller. Since the fixed gain PI current controller can only be optimized for one operating point, and on the other hand, SR motor is highly nonlinear, PI controller gain should be adjusted according to incremental inductance. This paper presents a novel method for PI current controller gain adaptation which is simple and yields a good performance. The proposed controller has been implemented on a test bench using a eZdsp F28335 board. The performance of the current controller has been investigated in both simulation and experimental tests using a four-phase 8/6 4KW SRM drive system.

• Asia pacific journal of information systems
• /
• v.25 no.3
• /
• pp.579-596
• /
• 2015

Many studies have focused on the prediction of corporate credit rating using various data mining techniques. One of the most frequently used algorithms is support vector machines (SVM), and recently, novel techniques such as SVM+ and SVM+MTL have emerged. This paper intends to show the applicability of such new techniques to multi-classification and corporate credit rating and compare them with conventional SVM regarding prediction performance. We solve multi-class SVM+ and SVM+MTL problems by constructing several binary classifiers. Furthermore, to demonstrate the robustness and outstanding performance of SVM+MTL algorithm over other techniques, we utilized four typical multi-class processing methods in our experiments. The results show that SVM+MTL outperforms both conventional SVM and novel SVM+ in predicting corporate credit rating. This study contributes to the literature by showing the applicability of new techniques such as SVM+ and SVM+MTL and the outperformance of SVM+MTL over conventional techniques. Thus, this study enriches solving techniques for addressing multi-class problems such as corporate credit rating prediction.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.10
• /
• pp.1303-1310
• /
• 1999

In this paper, the Timed Petri-Nets(TPN) modeling of Modular Cell Manufacturing Systems(MCMS) was investigated to overcome the limit of batch mode operation, which has been one of the most popular manufacturing types to produce an extensive industrial output and to be able to adopt to suitable and quickly changing manufacturing environments. A model of the MCMS was developed in reference to the actual TFT-LCD manufacturing system. TFT-LCD manufacturing system is not mass-productive in batch mode, but it operates in the form of MCMS which consists of a sequence of several cells with four processes of operation, including those of color filter(C/F), TFT, cell, and module. The cell process is further regrouped in those of Front-End and Back-End. For the Back-End cell process, it is reconstructed into a virtual model, consisting of three cells. The TPN modeling encompasses those properties, such as states and operations of machines, the number of buffers, and the processing time. The performance of the modeling was further examined in terms of scheduling system. The productivity in each cells was examined with respect to the change of failure rate of the cell machines and Automatic Guided Vehicles(AGV) using simulation by TPN.

• International Journal of Railway
• /
• v.5 no.1
• /
• pp.38-47
• /
• 2012

At present among the most important problems in the field of traction systems of railway vehicles are the following: 1) the minimization of the mass-and-overall dimensions of the drive systems; 2) the increase of the drive systems reliability and obtaining their higher fault-tolerance abilities; 3) the minimization of the motion speed pulsations and its oscillations, etc. The results of the researches received by the authors of this paper show that the use of the multiphase (i.e. having the number of phases more than four) inverter-fed induction motors in these traction systems is the most effective way of solving the above mentioned problems. In this case the motion speed oscillations can be decreased only by the increase of the drive phase number without any change in the inverter control algorithm. In addition, the application of some non-traditional control methods in the multiphase asynchronous traction drive system of a railway vehicle allows to decrease the mass-and-overall dimensions of the system and to improve its reliability and some other technical-and economic characteristics.

• Journal of the Korean Society for Precision Engineering
• /
• v.28 no.3
• /
• pp.259-264
• /
• 2011

Authors are carrying out a national project which develops an accuracy simulation technology of mechanical machines to predict the stiffness and accuracy of machine components or entire machine in the design stage. Analysis methods in this technology are generalized to achieve the wide applicability and to be utilized as a web based platform type. In this paper, outline of the project such as concept, aim and configuration is introduced. Contents of the research are also introduced, which are composed of four main research fields; structural dynamics, linear motion analysis, rotary motion analysis and control and vibration analysis. Finally, a future plan is presented which is made up with three stages for the advance toward an ultimate manufacturing tools.