• 한국정보전자통신기술학회논문지
• /
• 제16권6호
• /
• pp.385-391
• /
• 2023

최근 탄소배출을 최소화하기 위해 전기자동차의 사용이 증가함에 따라 핵심 부품인 리튬이온 배터리의 상태 및 성능 분석의 중요성이 대두되고 있다. 따라서 배터리의 상태 및 성능에 영향을 줄 수 있는 배터리의 전압, 전류 및 온도뿐만 아니라 전기 자동차의 운행 데이터 및 충전 패턴 데이터를 활용한 종합적인 분석이 필요하다. 따라서 전기적 이동 수단에서 수집되는 배터리 데이터 수집 및 데이터 전처리, 단순 배터리 데이터에 추가적인 운전자 운전 습관에 대한 데이터 수집 및 전처리, 분석된 영향인자를 기반으로 인공지능 알고리즘 세부 설계 및 수정, 해당 알고리즘을 기반으로 하는 배터리 분석 및 평가 모델 설계하였다. 본 논문에서는 실시간 전기버스를 대상으로 운행 데이터와 배터리 데이터를 수집하여 Random Forest 알고리즘 활용하여 학습시킨 후, XAI 알고리즘을 통해 배터리 상태 중요 영향인자로 배터리의 상태, 운행 및 충전 패턴 데이터 등을 종합적으로 고려하여 운행 패턴에서 급가속, 급 감속, 급정지와 충 방전 패턴에서 일 주행횟수, 일일 누적 DOD와 셀 방전에서 셀 전압 차 , 셀 최대온도, 셀 최소온도의 요소가 배터리 상태에 많은 영향을 미치는 인자로 확인되었으며, Random Forest 알고리즘 기반으로 배터리 분석 및 평가 모델을 설계하고 평가하였다.

• Journal of the Korean Data and Information Science Society
• /
• 제17권2호
• /
• pp.269-278
• /
• 2006

This paper presents the new hybrid data mining technique using error pattern, modeling of improving classification accuracy. The proposed method improves classification accuracy by combining two different supervised learning methods. The main algorithm generates error pattern modeling between the two supervised learning methods(ex: Neural Networks, Decision Tree, Logistic Regression and so on.) The Proposed modeling method has been applied to the simulation of 10,000 data sets generated by Normal and exponential random distribution. The simulation results show that the performance of proposed method is superior to the existing methods like Logistic regression and Discriminant analysis.

• Journal of Mechanical Science and Technology
• /
• 제20권12호
• /
• pp.2079-2086
• /
• 2006

A fundamental study for developing a fault diagnosis system of a pump is performed by using neural network. Acoustic signals were obtained and converted to frequency domain for normal products and artificially deformed products. The neural network model used in this study was 3-layer type composed of input, hidden, and output layer. The normalized amplitudes at the multiples of real driving frequency were chosen as units of input layer. And the codes of pump malfunctions were selected as units of output layer. Various sets of teach signals made from original data by eliminating some random cases were used in the training. The average errors were approximately proportional to the number of untaught data. Neural network trained by acoustic signals can detect malfunction or diagnose fault of a given machine from the results.

• 한국콘텐츠학회논문지
• /
• 제5권6호
• /
• pp.172-177
• /
• 2005

히트 판정은 전투방식의 MMORPG 게임시스템의 설계에 필수적이며 다양한 형태의 게임시스템의 근간을 이룬다. 히트 판정의 모델은 최소, 최대, 치명 공격력의 공격력 구간과 실패, 일반, 치명 공격확률 구간으로 나누어지며 이를 난수 함수로 구간을 결정하고 손상값을 계산한다. 이 논문에서는 일반적인 MMORPG에서 사용할 수 있는 히트 판정 모델을 제시하고 이를 상용 MMORPG 트라비아 온라인에 적용하여 얻은 효과에 대해 자세히 설명한다.

• International Journal of Quality Innovation
• /
• 제7권3호
• /
• pp.58-69
• /
• 2006

This paper presents neural network-based recognition system for automatic light emitting diode (LED) inspection. The back-propagation neural network (BPNN) is proposed and tested. The current-voltage (I-V) characteristic data of LED from the inspection process is used for the network training and testing. This study selects 300 random samples as network training and employs 100 samples as network testing. The experimental results show that if the classification work is done well, the accuracy of recognition is 100%, and the testing speed of the proposed recognition system is almost one half faster than the traditional inspection system does. The proposed neural-network approach is successfully demonstrated by real data sets and can be effectively developed as a recognition system for a practical application purpose.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2005년도 Proceedings of ISRS 2005
• /
• pp.505-508
• /
• 2005

Wavelet scheme can be applied to the various remote sensing problems: conventional multi-resolution image analysis, compression of large image sets, fusion of heterogeneous sensor image and segmentation of features. In this study, we attempted wavelet-based filtering and its analysis. Traditionally, statistical methods and adaptive filter are used to manipulate noises in the image processing procedure. While we tried to filter random noise from optical image and radar image using Discrete Wavelet Transform (DW1) and Stationary Wavelet Transform (SW1) and compared with existing methods such as median filter and adaptive filter. In result, SWT preserved boundaries and reduced noises most effectively. If appropriate thresholds are used, wavelet filtering will be applied to detect road boundaries, buildings, cars and other complex features from high-resolution imagery in an urban environment as well as noise filtering

• 전기학회논문지P
• /
• 제58권2호
• /
• pp.164-171
• /
• 2009

This paper presents new learning algorithm of dynamic Bayesian networks (DBN) by means of constrained least square (LS) estimation algorithm and gradient descent method. First, we propose constrained LS based parameter estimation for a Markov chain (MC) model given observation data sets. Next, a gradient descent optimization is utilized for online estimation of a hidden Markov model (HMM), which is bi-linearly constructed by adding an observation variable to a MC model. We achieve numerical simulations to prove its reliability and superiority in which a series of non stationary random signal is applied for the DBN models respectively.

• 한국감성과학회:학술대회논문집
• /
• 한국감성과학회 2002년도 춘계학술대회 논문집
• /
• pp.16-19
• /
• 2002

Random and/or periodic defects occur in all spun yarns. These irregularities can often lead to defects in finished fabric. Yarn evenness tests are used to obtain statistical data about yarn properties, such as CV%, which is useful in comparing several sets of similar data that differ in mean value but may have some commonality in relative variation. Although this statistical data is helpful in determining relative yarn Quality, accurate predictions of how the yarn will appear in fabric form are still difficult to obtain. As an promising alterative, wavelet analysis has been employed to localize yam defect so as to predict the visual qualifies of the fabrics.

• 감성과학
• /
• 제5권3호
• /
• pp.35-38
• /
• 2002

Random and/or periodic defects occur in all spun yarns. These irregularities can often lead to defects in finished fabric. Yarn evenness tests are used to obtain statistical data about yarn properties, such as CV%, which is useful in comparing several sets of similar data that differ in mean value but may have some commonality in relative variation. Although this statistical data is helpful in determining relative yam quality, accurate predictions of how the yarn will appear in fabric form are still difficult to obtain. As an promising alterative, wavelet analysis has been employed to localize yarn defect so as to predict the visual qualities of the fabrics.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2003년도 추계학술대회
• /
• pp.137-142
• /
• 2003

A fundamental study for developing a system of fault diagnosis of a pump is performed by using neural network. The acoustic signals were obtained and converted to frequency domain for normal products and artificially deformed products. The signals were obtained in various driving frequencies in order to obtain many types of data from a limited number of pumps. The acoustic data in frequency domain were managed to multiples of real driving frequency with the aim of easy comparison. The neural network model used in this study was 3-layer type composed of input, hidden, and output layer. The normalized amplitudes at the multiples of real driving frequency were chosen as units of input layer, Various sets of teach signals made from original data by eliminating some random cases were used in the training. The average errors were approximately proportional to the number of untaught data. The results showed neural network trained by acoustic signals can be used as a simple method far a detection of machine malfunction or fault diagnosis.