• 한국방재학회:학술대회논문집
• /
• 한국방재학회 2008년도 정기총회 및 학술발표대회
• /
• pp.101-104
• /
• 2008

In this study, rainfall adjust and forecasting using artificial neural network(ANN) which includes a correlation coefficient is application in Seoul region. It analyzed one-hour rainfall data which has been reported in 25 region in seoul during from 2000 to 2006 at rainfall observatory by AWS. The ANN learning algorithm apply for input data that each region using cross-correlation will use the highest correlation coefficient region. In addition, rainfall adjust analyzed the minimum error based on correlation coefficient and determination coefficient related to the input region. ANN model used back-propagation algorithm for learning algorithm. In case of the back-propagation algorithm, many attempts and efforts are required to find the optimum neural network structure as applied model. This is calculated similar to the observed rainfall that the correlation coefficient was 0.98 in missing rainfall adjust at 10 region. As a result, ANN model has been for suitable for rainfall adjust. It is considered that the result will be more accurate when it includes climate data affecting rainfall.

• 전자공학회논문지B
• /
• 제33B권4호
• /
• pp.209-216
• /
• 1996

In this paper, we propose a learning method of multi-layer perceptrons (MLPs) with 8-bit data precision. The suggested method uses the cross-entropy cost function to remove the slope term of error signal in output layer. To decrease the possibility of overflows, we use 16-bit weighted sum results into the 8-bit data with appropriate range. In the forwared propagation, the range for bit-conversion is determined using the saturation property of sigmoid function. In the backwared propagation, the range for bit-conversion is derived using the probability density function of back-propagated signal. In a simulation study to classify hadwritten digits in the CEDAR database, our method shows similar generalization performance to the error back-propagation learning with 16-bit precision.

• 한국기계가공학회지
• /
• 제15권1호
• /
• pp.95-102
• /
• 2016

Wrinkle, spring-back, and fracture are major defects frequently found in the sheet metal forming process, and the reduction of such defects is difficult as they are affected by uncontrollable factors, such as variations in properties of the incoming material and process parameters. Without any countermeasures against these issues, attempts to reduce defects through optimal design methods often lead to failure. In this research, a new multi-attribute robust design methodology, based on the Mahalanobis Taguchi System (MTS), is presented for reducing the possibilities of wrinkle, spring-back, and fracture. MTS performs experimentation, based on the orthogonal array under various noise conditions, uses the SN ratio of the Mahalanobis distance as a performance metric. The proposed method is illustrated through a robust design of the sheet metal forming process of a cross member of automotive body.

• 전기학회논문지
• /
• 제56권3호
• /
• pp.519-523
• /
• 2007

In this paper, we propose a precise parameter extraction of interior permanent magnet (IPM) motors based on finite element analysis. For the calculation of the two-axis inductances Ld and Lq, the slotting effect and cross magnetization due to torque angle are considered. It is examined that back electro-motive force (BEMF) constant is affected by the magnetic saturation in different ways dependent on motor types. Numerical analyses and some measurements are performed for a spoke type and a flux barrier type IPM motors

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1998년도 하계종합학술대회논문집
• /
• pp.534-537
• /
• 1998

In this paper, a set of novel self-timed latches are introduced and analyzed. These latches have no back-to-back connection as in conventional self-timed latch, and both inverting and noninerting outputs are evaluated simultaneously leading to thigher oepating frequencies. Power consumption of these latches ar ealso comparable to or less than that of conventional circuits. Novel type of cross-coupled inverter used in the proosed circuits implements static operatin without signal fighting with the main driver during signal transition. Proposed latches ar tested using a 0.6.mu.m triple-poly triple-metal n-well CMOS technology. The resutls indicates that proposed active-low sefl-timed latch (ALSTL) improves speed by 14-34% over conventional NAND SR latch, while in active-high self-timed latch (AHSTL) the improvements are 15-35% with less power as compared with corresponding NORA SR latch. These novel latches have been successfully implemented in a high-speed synchronous DRAM (SDRAM).

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2001년도 춘계학술대회 논문집
• /
• pp.1016-1020
• /
• 2001

The spinning is a very effective manufacturing technology for short production runs in a variety of sizes and shapes, because it can form the cross-section or tubular parts various shapes. However extensive experimental and analytical research has not been carried out. In this study, and fundamental experiment was conducted to improve productivity with process parameter such as tool path, angle of roller holder(a), feed rate(v) and corner radius of forming roller(Rr). These factors were selected as variables in the experiment because they were most likely expected to have and effect on spring back. The clearance was controlled in order to achieve the precision product which is comparable to deep drawing one. And also thickness and diameter distribution of a multistage cup obtained by shear spinning process were observed and compared with those of a commercial product produced by conventional deep drawing.

• 한국경영과학회지
• /
• 제30권1호
• /
• 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.

• Bulletin of the Korean Chemical Society
• /
• 제16권7호
• /
• pp.649-653
• /
• 1995

Solution-state structure of native F430 was determined by using NMR methods and NMR-based distance geometry (DG) computations. Structures were generated with loose NOE-derived interproton distance restraints (2.0-2.5 Å, 2.0-3.5 Å and 2.0-4.5 Å for strong, medium, and weak NOE cross-peak intensities, respectively). 2D NOESY back-calculations of structures were subsequently carried out for establishing the consistence between experimental data and DG-model structures. The back-calculated 2D NOESY spectra of resulting DG structures were well consistent with experimental 2D NOESY spectra. Superposition of 20 independent structures with macrocyclic ring atoms and all atoms of F430 afforded pairwise root mean square deviations (RMSD) of 0.025-0.125 Å and 0.64-1.3 Å, respectively. The macrocyclic rings of structures are well converged to a unique conformation with saddle-shaped deformation whereas most of side chains are not converged. The average dihedral angle (N1-N2-N3-N4, 27.78±1.50°) of 20 DG-structures exhibits that the macrocyclic ring conformation is puckered as much as 12,13-diepimeric F430 (28.75±4.07°).

• 한국지반공학회논문집
• /
• 제16권1호
• /
• pp.43-50
• /
• 2000

본 논문은 실내시험과 수치모델을 이용하여 십자형 배수재의 압밀촉진효과와 등가직경을 검토하고 판형배수재와 비교하였다. 배수재의 등가직경은 실내시험으로부터 역계산하여 문헌에 의해 제시된 공식으로부터 산정된 결과와 비교하였고, 압밀효과는 3차원 흐름해석프로그램인 MODFLOW를 사용하였다. 해석모델의 신뢰성은 현장의 침하-시간 계측자료를 이용하여 검토하였다. 실내시험결과 산정된 판형 배수재의 등가직경은 Rixner의 제안식에 유사한 경향을 보였고, 십자형 배수재의 등가직경은 $d_w\;=\; \\tarc{3}{4}.(b+t)$로 산정되었다. 실제현장을 모델링한 수치해석결과 십자형 배수재는 압밀시간이 9-10% 감소하였고, 현장자료를 이용한 수치 흐름모델로부터 산정한 등가직경은 실내시험보다 3.5배 작은 것으로 나타났다.

• 한국신재생에너지학회:학술대회논문집
• /
• 한국신재생에너지학회 2010년도 춘계학술대회 초록집
• /
• pp.101.2-101.2
• /
• 2010

태양전지에서 고효율을 얻기 위해서는 알루미늄 원자의 확산에 의한 불순물층으로서 p+층이 필수적이다. P+층은 형성전자의 재결합을 방지하고, 생성 캐리어의 수집 효율을 향상시키는 BSF(Back Surface Field) 효과의 역할을 한다. 도포된 알루미늄 페이스트가 부족할 경우 BSF효과가 나타나지 않으며 과할 경우 웨이퍼가 휨이 발생하여 최적 인쇄도포량이 중요하다. 본 연구에서는 레오미터 측정조건을 스크린 프린팅 인쇄 조건과 유사하게 진행하여 저장탄성율(G') 과 손실탄성율(G")의 관계를 살펴보았다. 회복단계에서 G'>G" 이고 Cross point가 없을 경우 도포량이 1.8g 이상이였으며, 웨이퍼의 휨(bowing)이 크게 발생하였고, 이와 반대로 회복시 20초 후에 Cross point가 나타난 경우 10% 정도 도포량 감소와 함께 휨 발생도 1 mm 이하로 양호한 특성을 확인할 수 있었다.