• Proceedings of the KIEE Conference
• /
• 2005.07d
• /
• pp.2658-2660
• /
• 2005

This paper presents a stator winding fault diagnosis technique of induction motor on the PC - based virtual instrumentation system designed using the graphical programming language LabVIEW. This method collects the 3-phase current signals using the current probe amplifier and PXI/DAQ system then the preprocessing removes the noise using LPF, after then this method transforms the stator current to Park's vector and obtains the each Park's Vector pattern and detects stator winding fault by comparing the obtained faulted pattern with the healthy pattern. This proposed LabVIEW based diagnosis system is applied to the 3 phase 1 hp induction motor and obtained the reasonable results under no load condition. The test results give us the possibility a simple and realistic on-line winding fault diagnosis system.

• Communications of the Korean Mathematical Society
• /
• v.13 no.3
• /
• pp.465-473
• /
• 1998

A real m $\times$ n matrix A is semipositive (SP) if there is a vector x $\geq$ 0 such that Ax > 0, inequalities being entrywise. A is minimally semipositive (MSP) if A is semipositive and no column deleted submatrix of A is semipositive. We give a necessary and sufficient condition for the sign pattern matrix with n positive entries to be minimally semipositive.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2007.06a
• /
• pp.309-310
• /
• 2007

• Journal of Korea Multimedia Society
• /
• v.25 no.9
• /
• pp.1328-1337
• /
• 2022

Recently, research on various font designs has been actively conducted to deliver effective emotional information in a digital environment. In this study, we propose a Hangul font outline vector modification algorithm that effectively conveys sensitivity according to weather information and can be transformed immediately. The algorithm performs a series of transformations: sets outlines according to design pattern templates, calculates the glyph's position to reflect physical rules, splits outline segments into smaller sizes and deforms the outlines. Through this, we could create several vector font designs such as humidity, cloud, wind, and snow. The usability evaluation was close to good, so it can be used in diverse ways if we improve readability and effective design expression.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2014.10a
• /
• pp.833-834
• /
• 2014

In recent years, a pattern recognition method has been widely used by researchers for fault diagnoses of mechanical systems. A pattern recognition method determines the soundness of a mechanical system by detecting variations in the system's vibration characteristics. Hidden Markov model has recently been used as pattern recognition methods in various fields. In this study, a HMM method for the fault diagnosis of a mechanical system is introduced, and a rotating machine with mass unbalance is selected for fault diagnosis. Moreover, a diagnosis procedure to identity the size of a defect is proposed in this study.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.361-363
• /
• 2007

In this paper, an auto-diagnosis method of rotor bar fault for small induction motor is suggested. Usually FFT of stator currents are given the good results, but to detect the fault, slip is needed for calculating the feature frequency. The slip is varied as the load is changed. So in this paper, some alternative method for estimating the load is suggested. This method is based on the Park's vector pattern. The magnitudes of the feature frequency are compared with the threshhold that is predefined in the bounded range of load. The healthy rotor, single rotor bar fault and double rotor bar fault are tested with no load, 25%, 50%, 75%, and 100% rated load. From 50% to 100% rated load case, the rotor bar faults are detectable using indirect estimation of the load and the comparing the magnitudes of feature frequency. The no load case and under 40% rated load case, rotor fault are un detectable.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.1876-1877
• /
• 2011

In this paper, a winding fault diagnosis method base on MCSA(Motor Current Signature Analysis) for BLDC motor is proposed. This method is programmed by LabVIEW for winding fault diagnosis. For winding fault diagnosis, two types of winding fault(shorted turn at one pole, shorted turn at two pole in same phase) are put intentionally in on phase. The motor current is collected by hole sensor, and transformed by the Park's transform, and then the Park's Vector Pattern are obtained, Usually this pattern is formed an ellipse, so a proper threshold value of distortion ratio(the ratio of the shortest axis and longest axis of ellipse) is suggested for winding faults diagnosis.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.6
• /
• pp.774-779
• /
• 2012

Brain-computer interface based on motor imagery is a system that transforms a subject's intention into a control signal by classifying EEG signals obtained from the imagination of movement of a subject's limbs. For the new paradigm, we do not know which positions are activated or not. A simple approach is to use as many channels as possible. The problem is that using many channels causes other problems. When applying a common spatial pattern (CSP), which is an EEG extraction method, many channels cause an overfit problem, in addition there is difficulty using this technique for medical analysis. To overcome these problems, we suggest a binary particle swarm optimization with channel impact factor in order to select channels close to the most important channels as channel selection method. This paper examines whether or not channel impact factor can improve accuracy by Support Vector Machine(SVM).

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04c
• /
• pp.175-177
• /
• 2003

This paper addresses a problem of classifying human breast cancer into its subtypes. A main ingredient in our approach is kernel machines such as support vector machine (SVM). kernel principal component analysis (KPCA). and kernel partial least squares (KPLS). In the task of breast cancer classification, we employ both SVM and KPLS and compare their results. In addition to this classification. we also analyze the patterns of clinical outcomes in the feature space. In order to visualize the clinical outcomes in low-dimensional space, both KPCA and KPLS are used. It turns out that these methods are useful to identify correlations between clinical outcomes and the nonlinearly protected expression profiles in low-dimensional feature space.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.5 s.305
• /
• pp.123-136
• /
• 2005

We propose a recognition system for superimposed patterns based on selective attention model and SVM which produces better performance than artificial neural network. The proposed selective attention model includes attention layer prior to SVM which affects SVM's input parameters. It also behaves as selective filter. The philosophy behind selective attention model is to find the stopping criteria to stop training and also defines the confidence measure of the selective attention's outcome. Support vector represents the other surrounding sample vectors. The support vector closest to the initial input vector in consideration is chosen. Minimal euclidean distance between the modified input vector based on selective attention and the chosen support vector defines the stopping criteria. It is difficult to define the confidence measure of selective attention if we apply common selective attention model, A new way of doffing the confidence measure can be set under the constraint that each modified input pixel does not cross over the boundary of original input pixel, thus the range of applicable information get increased. This method uses the following information; the Euclidean distance between an input pattern and modified pattern, the output of SVM, the support vector output of hidden neuron that is the closest to the initial input pattern. For the recognition experiment, 45 different combinations of USPS digit data are used. Better recognition performance is seen when selective attention is applied along with SVM than SVM only. Also, the proposed selective attention shows better performance than common selective attention.