• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.5
• /
• pp.845-850
• /
• 2021

In this study, the energy conversion characteristics and design of electric vehicle (EV: Electric Vehicle) powertrain were performed. An interior permanent magnet synchronous motor (IPMSM) was targeted as a power source for the EV powertrain, and control was performed. In order to drive the IPMSM, two regions are considered: a constant torque and a constant output (field-weakening) region. The design of the control system for IPMSM was constructed based on the d-q reference frame (vector control). To determine the static characteristics of motor torque appearing in two areas of IPMSM, a torque control system and a d axis current control system of IPMSM were implemented and proposed. Matlab-Simulink software was used for characteristic analysis. Finally, by applying IPMSM to the powertrain model under the actual EV vehicle level conditions, simulation results of the proposed control system were performed and characteristics were analyzed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.12
• /
• pp.2885-2890
• /
• 2014

Localization of a sensor network node using machine learning has been recently studied. It is easy for Support vector machines algorithm to implement in high level language enabling parallelism. Raspberrypi is a linux system which can be used as a sensor node. Pi can be used to construct IP based Hadoop clusters. In this paper, we realized Support vector machine using python language and built a sensor network cluster with 5 Pi's. We also established a Hadoop software framework to employ MapReduce mechanism. In our experiment, we implemented the test sensor network with a variety of parameters and examined based on proficiency, resource evaluation, and processing time. The experimentation showed that with more execution power and memory volume, Pi could be appropriate for a member node of the cluster, accomplishing precise classification for sensor localization using machine learning.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.12
• /
• pp.187-196
• /
• 2011

Induction motors play a vital role in aeronautical and automotive industries so that many researchers have studied on developing a fault detection and classification system of an induction motor to minimize economical damage caused by its fault. With this reason, this paper extracts robust feature vectors from the normal/abnormal vibration signals of the induction motor in noise circumstance: partial autocorrelation (PARCOR) coefficient, log spectrum powers (LSP), cepstrum coefficients mean (CCM), and mel-frequency cepstrum coefficient (MFCC). Then, we classified different types of faults of the induction motor by using the extracted feature vectors as inputs of a neural network. To find optimal feature vectors, this paper evaluated classification performance with 2 to 20 different feature vectors. Experimental results showed that five to six features were good enough to give almost 100% classification accuracy except features by CCM. Furthermore, we considered that vibration signals could include noise components caused by surroundings. Thus, we added white Gaussian noise to original vibration signals, and then evaluated classification performance. The evaluation results yielded that LSP was the most robust in noise circumstance, then PARCOR and MFCC followed by LSP, respectively.

• Journal of IKEEE
• /
• v.5 no.2 s.9
• /
• pp.190-200
• /
• 2001

This paper is addressed to welding defect feature vector selection and implementation method of welding defect classifier using fuzzy techniques. We compare IAV, zero-crossing number as time domain analysis, power spectrum coefficient as frequency domain, histogram as both domain for welding defect feature selection. We choose histogram as feature vector by graph analysis and find out that maximum frequent occurrence number and section of corresponding signal scale in relative histogram show obvious difference between normal welding and voiding with penetration depth defect. We implement a fuzzy welding defect classifier using these feature vector, test it to verify its effectiveness for 695 welding data frame which consist of 4000 sampled data. As result of test, correct classification rate is 92.96%. Lab experimental results show a effectiveness of fuzzy welding defect classifier using relative histogram for practical Laser welding monitoring system in industry.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.2
• /
• pp.9-16
• /
• 2011

GPU computing is emerging in high performance application area since it can easily exploit massive parallelism in a way of cost-effective computing. The power method which finds the eigen vector of a given matrix is widely used in various applications such as PageRank for calculating importance of web pages. In this research we made the power method efficiently parallelized on GPU and also suggested how it can be improved to enhance its performance. The power method mainly consists of matrix-vector product and it can be easily parallelized. However, it should decide the convergence of the eigen vector and need scaling of the vector subsequently. Such operations incur several calls to GPU kernels and data movement between host and GPU memories. We improved the performance of the power method by means of reduced calls to GPU kernels, optimized thread allocation and enhanced decision operation for the convergence.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.8 no.1
• /
• pp.41-46
• /
• 2014

In this paper, we propose a novel voice activity detection (VAD) algorithm using feature vectors based on TE (teager energy). Specifically, power spectral deviation (PSD), which is used as the feature for the VAD in the IS-127 noise suppression algorithm, is obtained after the input signal is transfomed by Teager energy operator. In addition, the TE-based likelihhod ratio are derived in each frame to modifiy the PSD for further VAD. The performance of our proposed VAD algorithm are evaluated by objective testing (total error rate, receiver operating characteristics, perceptual evaluation of speech quality) under various environments, and it is found that the proposed method yields better results than conventional VAD algorithms in the non-stationary noise environments under 5 dB SNR (total error rate = 2.6% decrease, PESQ score = 0.053 improvement).

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.1
• /
• pp.59-64
• /
• 2005

To achieve a goal of minimum output power, the beamformer tends to cancel the desired signal if there exists correlated interference sources such as multipaths of the desired signal. In this paper, we propose a new method which overcomes the signal cancellation problem for correlated interferences. Instead of decorrelating the correlated interferences, the proposed bramformer regards them as replicas of the desired signal and coherently combines them with desired signal. This method uses an eigenvector constraint that suppresses a noise and uncorrelated interferences but keeps the desired signal and correlated interferences. Indisputably, the beamformer does not require any preliminary information on correlated interferences. Simulation results show that the proposed beamformer overcomes the signal cancellation problem and improves signal-to-noise ratio (SNR) of the array output when the correlated interferences exist.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.2
• /
• pp.180-186
• /
• 2004

The presence of noise in speech signals degrades the performance of recognition systems in which there are mismatches between the training and test environments. To make a speech recognizer robust, it is necessary to compensate these mismatches. In this paper, we studied about an improvement of stochastic feature extraction based on band-SNR for robust speech recognition. At first, we proposed a modified version of the multi-band spectral subtraction (MSS) method which adjusts the subtraction level of noise spectrum according to band-SNR. In the proposed method referred as M-MSS, a noise normalization factor was newly introduced to finely control the over-estimation factor depending on the band-SNR. Also, we modified the architecture of the stochastic feature extraction (SFE) method. We could get a better performance when the spectral subtraction was applied in the power spectrum domain than in the mel-scale domain. This method is denoted as M-SFE. Last, we applied the M-MSS method to the modified stochastic feature extraction structure, which is denoted as the MMSS-MSFE method. The proposed methods were evaluated on isolated word recognition under various noise environments. The average error rates of the M-MSS, M-SFE, and MMSS-MSFE methods over the ordinary spectral subtraction (SS) method were reduced by 18.6%, 15.1%, and 33.9%, respectively. From these results, we can conclude that the proposed methods provide good candidates for robust feature extraction in the noisy speech recognition.

• Proceedings of the KIPE Conference
• /
• 2003.07a
• /
• pp.341-344
• /
• 2003

직렬연결형 다중레벨 컨버터(cascade multilevel converter)는 각기 절연된 DC전압원과 H-bridge 인버터가 한 단위를 이루고, 각 단위 인버터의 출력을 직렬 연결한 구조로서, 부하(전동기)에 정현파에 가까운 전압을 인가할 수 있는 시스템이다 각 H-bridge인버터의 DC전압원으로는 배터리 또는 커패시터등이 사용되는데, 일반적인 경우 각 H-bridge 컨버터의 입출력 파워가 틀려지게 되며, 따라서 DC전압간 불균형이 발생하게 된다. DC전압간 불균형이 발생하면 원하는 전압벡터를 정확하게 발생시킬 수 없게 되고, 고조파 하모닉이 만들어질뿐 아니라, 경우에 따라서는 DC전압원측에과 전압 또는 저전압 폴트가 발생할 수 있다. 본 논문은 N개의 H-bridge 인버터의 DC전압을 측정하지 않고, 전체 상출력 전압만을 측정하여 각 DC전압을 추정하고, 스위칭 패턴을 변경하여 DC전압을 평형화하는 방법을 제안한다. 모의실험을 통해서 알고리즘의 동작여부를 검증하였다.

• Proceedings of the KIPE Conference
• /
• 2004.07a
• /
• pp.11-14
• /
• 2004

This paper presents an implementation of compact vector control system for induction motor using a digital signal processor (DSP) and a smart power module (SPM). The DSP TMS320F2812 has most necessary functions for ac motor control in a single chip and SPM provides a compact power stage. The indirect vector control algorithm is implemented in the drive system using these devices. The developed system is applied by 0.8kW induction servo motor and the all functions are verified through the experiments.