http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
인공신경망을 이용한 저항 점용접 너겟 직경 예측에 관한 연구
김종규(Jongkyu Kim),구자훈(JaHun Ku),박영도(Yeongdo Park),김영창(Youngchang Kim),황영민(Youngmin Hwang),김희수(Heesoo Kim),Siva Prasad Murugan,구남국(Namkug Ku) 대한용접·접합학회 2021 대한용접·접합학회지 Vol.39 No.6
Resistance spot welding, which has the advantages of low cost and high productivity, is the most common method used in the automobile industry for joining steel sheets. However, in practice, resistance spot welds are typically tested for welding quality using destructive rather than non-destructive inspection methods because of their lower cost. However, in destructive inspection, quality defects can be found only after the completion of the process. Accordingly, several studies are currently being conducted to predict the quality of welding in real time. Welding quality is determined by the diameter of the nugget, and its size depends on several independent variables. In this study, a linear regression model and artificial neural network model were constructed to predict the nugget diameter. An electric power pattern was obtained from the results of a welding experiment, and nine types of electric power characteristic values were extracted from the obtained electric power pattern as independent variables. From the nine electric power characteristic values, six having the highest correlation with the nugget diameter were determined as final independent variables through correlation analysis. The linear regression model was constructed using multiple linear regression analysis, and the artificial neural network model was built using a deep neural network model with two hidden layers and nodes of 64 and 16. In this study, the error between the actual measured and predicted nugget diameters was taken as 0.2 ㎜ or less as a good predictive value. When the linear regression model was used to predict the nugget diameter, only approximately 36% were predicted well. By contrast, when the artificial neural network was used, approximately 86% were predicted well. Thus, the artificial neural network model yielded better results. It was determined that with more welding data and information on steel types, the proposed welding quality prediction system could be improved.
NOAA AVHRR 및 Landsat ETM+를 이용한 광양만 표층수온분포 특성
김종규(Jongkyu KIM),조성훈(Sung Hoon CHO) 전남대학교 수산과학연구소 2011 수산과학연구소논문집 Vol.19 No.-
광양만 SST의 계절별 분포특성을 NOAA AVHRR(Band 12, 15, 16), Landsat ETM+(Band 6) 및 ASTER(Band 13)를 이용하여 파악하였다. NOAA 영상에서 나타나듯이 광양만 입구인 여수해만에서는 쿠로시오해류의 지류인 대마난류의 영향을 받고 있지만, 광양만내에는 대마난류보다 저온인 남해안 연안수가 연중 존재하는 것을 확인할 수 있으나, NOAA AVHRR의 분광해상도에 따라 국지적인 만내의 SST 분포특성은 파악할 수 없었다. Landsat ETM+영상에서 SST의 분포를 살펴보면, 만 전체의 SST는 계절적 영향에 의한 변동이 주를 이루고 있었으며, 만 북쪽에서 년 중 난수역이 형성되어 있음을 알 수 있었다. 이것은 하동화력에서 배출하고 있는 온배수의 영향이며, 타 지역의 SST 보다 약 5~10℃ 높게 나타나는 것을 SST 모니터링 및 위성영상 분석에 의해 알 수 있었다. 또한, 하동화력에서 배출되는 온배수에 의해 형성된 난수역은 조류의 영향으로 남쪽으로 확산되어짐을 보였으며, 하계에는 계절의 영향에 의해 비교적 난수역의 영향범위가 작게 나타나고 있으며, 수온이 낮은 동계에 더 넓어지는 것을 보였으며, 조류에 의해 수괴가 여수해만을 통해 외해로 유출되어짐을 보였다. 또한, 만의 서쪽은 수심이 상당히 낮은 지역으로 SST의 변화가 외해수의 유ㆍ출입양이 많은 만의 중앙 보다 계절적 영향을 더 많이 받고 있으며, 만내로 유입되는 섬진강의 담수는 계절의 영향에 의해 동계에는 외해수보다 수온이 낮고, 하계에는 수온이 높은 특성을 보이고 있다. 이상의 결과를 토대로 알 수 있는 광양만의 SST 분포특성은 만내의 각 지역별 수온차가 계절적ㆍ인위적인 영향으로 크게 나타나고 있다. 연중 주된 SST의 변동은 계절적 영향이 가장 크게 작용하고 있음을 알 수 있었다. The Seomj in River and Hadong Power Station on the south coast of Korea discharges fresh and warm water affecting coastal ecology, respectively. The spatial and temporal characteristics of plume discharges of fresh and warm water are reported from a time series of real-time monitoring and thermal infrared data from Landsat ETM+ during one year(2003-2004). These data demonstrated the general pattern and expansion of the plume discharges using the image analysis of NOAA AVHRR and Landsat ETM+ in Gwangyang Bay. As a results, warm region was formed at three parts in Gwangyang Bay.
김종규(Jongkyu Kim),배태성(Taesung Bae),이동우(Dongwoo Lee),이권희(Kwonhee Lee) 한국자동차공학회 2009 한국자동차공학회 학술대회 및 전시회 Vol.2009 No.11
The basic purpose of a tire is to enable better vehicle performances such as driving performance, rolling resistance, durability, ride comfort, noise, wear resistance, etc, by providing a flexible cushion. In response to improvement of vehicle performances, the design method of a tire is developing much. This study proposes a structural design method for a tire contour by considering both the tread contour and the sidewall contour, simultaneously. However, the existing studies of tire contour optimization were interested in the tread contour and the sidewall, respectively. The durability, maneuverability and ride comfort are the commonly investigated performances in tire contour design. The durability, maneuverability and ride comfort can be measured by the value of strain energy density, tension and vertical stiffness, respectively. The optimization technique using metamodel is introduced to maximize durability satisfying the imposed constraints of tension and ride comfort. To achieve this, the responses defined in optimization formulation are expressed in mathematically explicit form with respect to the design variables by using kriging surrogate model, resulting a simple optimization problem. Then, the simulated annealing algorithm is utilized to find global optimum.