목적 : 인공지능의 기계학습 또는 심층학습을 이용한 연구가 다양한 분야에서 시도되고 있다. 본 연구는 공공 시력데이터를 자동화 수집하고, 수집한 데이터를 기계학습에 적용 및 예측하였다. 다양한 학습모델간 성능을 비교 함으로써, 시과학분야에서 적용 가능한 기계학습 최적화모델을 제시함에 있다. 방법 : 국민건강보험(NHISS) 및 통계포털(KOSIS)에 발표된 국민 시력분포 현황관련 자료를 특정 색인을 포함하 는 자료검색기법인 크롤링(crawling)을 사용하여 검색 및 수집을 자동화하였다. 2011년부터 2018년까지 보고된 모든 자료를 수집하였으며, 데이터 학습을 위해 Linear Regression, LASSO, Ridge, Elastic Net, Huber Regression, LASSO/LARS, Passive Aggressive Regressor 그리고 Pansacregressor 총 8개 모델을 사용하여 각각 데이터 학습 하였다. 결과 : 수집한 데이터를 기반으로 기계학습 모델을 통해 2018년을 예측하였다. 각 모델간 2018년도 실제-예측데 이터 차이를 MAE(Mean Absolute Error)와 RMSE(Root Mean Square Error) 점수로 각각 나타냈다. 학습모델 별 차이 중 MAE 평가결과 모델간 우/좌 Linear Regression(0.22/0.22), LASSO(0.83/0.81), RIDGE(0.31/0.31), Elastic Net(0.86/0.84), Huber Regression(0.14/0.07), LASSO/LARS(0.15/0.14), Passive Aggressive Regressor (0.29/0.18) 그리고 RANSA Regressor(0.22/0.22)를 보였다. RMSE에서 Linear Regression(0.40/0.40), LASSO (1.08/1.06), Ridge(0.54/0.54), Elastic Net(1.19/1.17), Huber Regression(0.20/0.20), LASSO/LARS(0.24/0.23), Passive Aggressive Regressor(0.21/0.58) 그리고 RANSA Regressor(0.40/0.40) 각각 나타냈다. 결론 : 본 연구는 자동화 자료검색 및 수집을 위한 크롤링 기법을 이용하여 데이터를 수집하였다. 이를 기반으 로 고전 선형모델을 기계학습에 적용할 수 있도록 하고, 데이터 학습을 위한 8개 학습모델들 간 성능을 비교하였다.

Hydro-electric power is a method of generating electricity from the rotational force of turbine blades by using the potential energy of a river or reservoir water. Recently, the necessity of small hydropower development is expanding due to the development and support of renewable energy, and because of the difficulty and environmental problems of huge dams. The purpose of this paper is to deal with a method of increasing the efficiency of small water turbine that can be adopt in low head condition. In order to improve the turbine efficiency, channel shape is optimized in order to minimize head loss using computational fluid dynamics. The angle values for the contraction and enlargement part of the channel where the turbine is located are found from the analyses. Additionally, three-dimensional analysis is applied to the optimized channel shape in order to confirm the optimized pipe.

The estimation of heat source model is very important for heat transfer analysis with finite element method. Part I of this study used adaptive simulated annealing which is one of the global optimization algorithm for anticipating the parameters of the Goldak model. Although the analysis with 3D model which depicted the real situation produced the correct answer, that took too much time with moving heat source model based on Fortran and Abaqus. This research suggests the procedure which can reduce time with maintaining quality of analysis. The lead time with 2D model is reduced by 90% comparing that of 3D model, the temperature distribution is similar to each other. That is based on the saturation of heat transfer among the direction of heat source movement. Adaptive simulated annealing with 2D model can be used to estimate more proper heat source model and which could enhance to reduce the resources and time for experiments.

The purpose of this study was to derive the conditions for manufacturing rice porridge with optimum properties after reheating. The characteristics of rice porridge according to the soaking time, water addition rate, heating temperature, heating time, and cooling conditions were compared using the ‘Samkwang’ cultivar. In Step Ⅰ, as the heating temperature increased, the weight change decreased and the viscosity increased, and the temperature known as the main factor of the gelatinization also appeared to affect the viscosity increase. In Step Ⅱ, the viscosity and the texture properties was not significantly different as the soaking time was reduced, and 10 minutes was suitable because of due to the shortening effect of the total process time. In Step Ⅲ, the residual heat was lowered by cooling after the rice porridge production, so the viscosity could be greatly reduced. Also, it was confirmed that the water addition rate of 900% and the heating temperature of 15 minutes were optimal manufacturing conditions. The next study will investigate the porridge processability of rice cultivars using these results.

본 논문에서는 초고층 건물의 철근콘크리트 아웃리거 벽체 개구부의 최적설계를 위한 수학적 최적화 프레임워크를 제시하였다. 전용 유한요소해석 프로그램을 이용하여 아웃리거 벽체를 해석하였으며 깊은 보의 스트럿-타이 거동을 고려하여 개구부를 배치하였다. 최적화를 위해 파이썬 SciPy 라이브러리 중 순차이차계획법(Sequential Quadratic Programming)을 이용하여 제약 경계 최적화를 수행 하였다. 최적화에 필요한 미분가능한 연속 함수를 얻어내기 위해 선형 보간법을 사용하였으며, 최적화 프로그램의 효율성을 위해 데이터베이스를 이용하였다. 2변수 최적화의 결과를 탐색 알고리즘의 이동 경로를 통해 살펴본 결과 알고리즘이 최적화된 결과를 효율적으로 찾아냄을 확인하였다. 그리고 개구부의 폭을 모두 같게 설정한 것이 아닌 각각의 개구부의 크기를 개별 변수로 설정하였을 경우 목적함수의 값이 최소화되어 더 우수한 최적화 결과를 도출함을 확인하였다. 또한, 최적화의 과정에 있어 데이터베이스를 이용할 경우 최적화 시간을 효과적으로 단축시킬 수 있음을 확인하였다.

본 연구에서 적용한 SMRPF system은 구조물 접합부의 패널존을 고려하는 동시에 지진하중에 대하여 각층별 전단력을 산정하여 댐퍼의 감쇠력과 변위를 결정해준다. 이는 내진설계가 반영되지 않은 구조물에 적용할 경우 부재단면을 변경하지 않고 내진성능을 확보 할 수 있는 감쇠기의 역량 결정이 가능함을 보여 주었다. 또한 본 논문에서 적용한 유전자 알고리즘을 통해 최적설계를 수행한 결과, 무보강 구조물에 비해 점성감쇠기와 패널존을 고려한 SMRPF 강골조 구조물의 총 중량이 약 50%이상 감소되는 것이 확인되었다.

The aim of this study was to investigate the effects of timing of collecting date and concentration of IBA and NAA, in order to enhance initial activity and seedling quality of domestic strawberry. Strawberry cuttings were separately taken twice, in June 7 and in July 5, and IBA and NAA were treated with the concentrations of 0.025, 0.05 and 0.1% at cutting date, respectively. The seedlings were evaluated for the percentage of survival during 18 days at 6 times after tunnel cultivation. The NAA treatment was inappropriate for strawberry cutting due to the high rate of seedling mortality, regardless of the collecting date. The vitality of the seedlings was highest at IBA 0.1% in June collecting and at IBA 0.05% in July collecting. The seedlings from June collecting had a higher quantum yield at IBA 0.1% and the seedlings from July collecting at IBA 0.05%. Therefore, IBA could be more effectively applied than NAA to promote the vitality and quality with the appropriate concentration of 0.1% at June collecting and 0.05% at July collecting, respectively.

The purpose of this study was to establish the optimum experimental conditions by investigating the relationship between the nine experimental conditions using Taguchi technique. Through experiments, we found that the weight, thickness, and length of the sample were most affected by the angle at which the sample was installed, while the width had the largest influence on the sample's x-axis and the inner diameter. It was confirmed. Therefore, through this experiment, it was confirmed that the installation angle of the product had the greatest influence on the error occurrence of the product during 3D printer processing.

Anticipation of welding deformation with finite element method is a very interested topic in the industries, adequate heat source model is essential for concluding reasonable results. This study is related to estimate the parameters of Goldak heat source model, and global optimization algorithm is applied to this research. The heat affected zone (HAZ) boundary line of bead on plate (BOP) welding is used as the target, parameters of heat sources are used as the variables. Adaptive simulated annealing is applied and the optimal result is obtained out of 1,000 candidates. The convergence of finite element method and the global optimization is meaningful for estimation of welding deformation, which could enhance to reduce the resources and time for experiments.

Forged part made of Cold heading quality wire materials are used for automotive brake systems. The cost reduction of forged products is a major issue because of the strict shape change. A series of studies were conducted to minimize the cost of EPB spindle process among brake parts. In order to reduce the material cost, heat treatment-abbreviated material was applied and the formability on the processes was verified by the ductile fracture theory. In addition, the causes of shape fixation and die life degradation were analyzed using the numerical simulation. The process cost has been minimized by re-designing process, changing the product shape, and the die material.

In this study, optimizations were carried out for a heater core and an evaporator installed in a passenger car. The main geometric parameters of each component were selected as design variables, and the main performances examined were the outlet temperature and the pressure drop. In addition, the sensitivity analysis was performed to grasp the dominant design variable. The thermal flow analysis for each component was performed using the commercial program STAR CCM+. On the other hand, EasyDesign, a commercial program based on DOE and metamodel-based optimization, was used as an optimization tool. The optimized performances of the heater core were compared with performance target, and finally, the improved designs of the heater and the evaporator were presented.