• 대한기계학회논문집
• /
• 제17권12호
• /
• pp.3045-3054
• /
• 1993

The mechanics related with piston-slap induced vibration has been studied in terms of non-dimensionalized dynamic equation of motion, various non-dimensional parameters such as non-dimensional side-thrust force and non-dimensional impact velocity throughout the numerical simulation. Experimental verification on the suggested prediction method has been also performed by using single cylinder engine which was carefully designed and manufactured to wisely control the engine parameters, especially clearance and the mass of piston. The predicted and experimentally observed vibration signature confirm that the proposed method is practically useful.

• 한국가시화정보학회지
• /
• 제17권2호
• /
• pp.83-89
• /
• 2019

In this study, we show the maximum cavity radius prediction model that a droplet impacts an inclined bath. Surface tensions, viscosities, inclination angles of a bottom substrate, droplet diameters, falling heights of the droplet are varied for the experiment. We experimentally observe that the cavity grows in hemispherical shape like the cavity formed in a deep bath although the depth of the bath is non-uniform due to an inclined bottom substrate. We derive two theoretical models to predict the experimental results of the fully developed cavity. Although each model has error, we observe that qualitatively theoretical model predicts the trend of experiment results well.

• 디지털융복합연구
• /
• 제18권11호
• /
• pp.267-272
• /
• 2020

거시경제는 한 나라 경제 전체의 움직임을 보여주기 때문에 주식을 분석할 때 선행되어 분석되는 지표 중 하나이다. 실업률, 이자율, 물가, 국민소득, 환율, 통화량, 국제수지 등 국가차원의 경제 상황 전반은 주식시장에 직접적인 영향을 미치고, 경제 지표는 개별 주가와의 상관관계가 있기 때문에 주식을 예측하기 위해 많은 증권사 애널리스트들이 관심 있게 지켜보고, 개별 주가에 영향을 고려하여 매수와 매도를 판단하는 주요한 근거자료가 되고 있다. 주가에 영향을 미치는 경제 지표를 선행지표로 분석하고, 주가예측을 딥러닝 기반의 예측을 통하여 예측 후 실제 주가를 비교하여 차이가 발생하면 거시지표에 대한 가중치를 조절하여 지속적인 반복학습을 통하여 주식의 매수와 매도를 판단한다면, 주식은 더 이상 도박과 같은 투기가 아닌 건전한 투자가 될 수 있다. 따라서 본 연구는 거시지표와 인공지능의 딥러닝 알고리즘방식을 이용하여 자동화된 주식매매가 가능하도록 연구를 수행하였다.

• 한국복합재료학회:학술대회논문집
• /
• 한국복합재료학회 2003년도 춘계학술발표대회 논문집
• /
• pp.129-134
• /
• 2003

The importance of understanding the response of structural composites to impact and CAI cannot be overstated to develop analytical models for impact damage and CAI strength predictions. This paper presents experimental findings observed from quasi-static lateral load tests, low velocity impact tests, CAI strength and open hole compressive strength tests using 3mm thick composite plates ($[45/-45/0/90]_{3s}$ - IM7/8552). The conclusion is drawn that damage areas for both quasi-static lateral load and impact tests are similar and the curves of several drop weight impacts with varying energy levels (between 5.4 J and 18.7 J) fallow the static curve well. In addition, at a given energy the peak force is in good agreement between the static and impact cases. From the CAI strength and open hole compressive strength tests, it is identified that the failure behaviour of the specimens was very similar to that observed in laminated plates with open holes under compression loading. The residual strengths are in good agreement with the measured open hole compressive strengths, considering the impact damage site as an equivalent hole. The experimental findings suggest that simple analytical models for the prediction of impact damage area and CAI strength can be developed on the basis of the failure mechanism observed from the experimental tests.

• 한국수자원학회논문집
• /
• 제55권spc1호
• /
• pp.1295-1303
• /
• 2022

안정적인 수도 공급을 위한 상수도관망의 역할이 더욱 주목받음에 따라 비정상 상황에 대한 신속한 탐지와 적절한 대처 역시 중요시되고 있다. 장치에 의존한 탐지기법 등 기존의 방법론에는 한계가 존재하므로 데이터를 이용한 모델 기반의 방법이 개발되었다. 하지만 상수도관망 내 측정 데이터는 불확실성을 가져 실제 사용량과 다르다. 따라서 본 연구에서는 기계학습 방법의 하나인 인공신경망 모델을 이용하여 상수도관망 압력값을 예측함에 있어 데이터 불확실성의 영향을 조사한다. 정규분포를 따르는 임의의 값을 고려하여 데이터에 측정치 오류를 형성하고 측정치 오류 여부 및 종류에 따라 총 9가지 데이터를 인공신경망 모델을 통해 예측해 경향성을 비교한다. 분석을 통해 데이터 불확실성이 증가할수록 모델 성능이 감소하며, 출력데이터의 측정치 오류가 모델 성능에 미치는 정도가 더 큼을 확인하였다. 특히 입력데이터와 출력데이터의 측정 오차 크기가 동일한 경우 예측 정확도는 각각 72.25%, 38.61%로 큰 차이를 보였다. 따라서 ANN 모델 예측 성능 향상을 위해서는 입력 데이터보다 출력데이터인 주절점의 측정 오류 크기를 줄이는 것이 중요하다.

• 대한조선학회논문집
• /
• 제51권6호
• /
• pp.503-509
• /
• 2014

This paper describes the time-domain numerical method for prediction of slamming loads on a ship in waves using the strip theory. The slamming loads was calculated considering the relative vertical velocity between the instantaneous ship motion and wave elevation. For applying the slamming force on a ship section, the momentum slamming theory and the empirical formula-based bottom slamming force were used corresponding to the vertical location of wetted body surface. Using the developed method, the vertical bending moments, relative vertical velocities, and impact forces of S175 containership were compared in the time series for various section locations and wave conditions.

• 환경영향평가
• /
• 제14권1호
• /
• pp.25-36
• /
• 2005

Actually, prediction formula of road traffic noise for EIA(Environmental Impact Assessment) has been used that proposed by National Institute of Environmental Research in 1999. The prediction formula, however, was calculated predicted noise level according to noise level producing on first floor, then needs to correct noise level at each floor in the case of apartment building. The investigation was carried out to calculate the correction coefficient for commonly using in EIA of large scaled apartment development areas. The noised level at each floor were measured from August 2001 to March 2002 at 31 investigation points of large scaled apartment development area in national wide. Measured data were divided and treated with 4 types as 3th floor, 5th floor, 7th floor and 10th floor and then the correction coefficients of each floor were calculated using by correlation formula according to each floor.

• 산업경영시스템학회지
• /
• 제41권3호
• /
• pp.154-161
• /
• 2018

This study conducted to predict the stock market prices based on the assumption that internet news articles might have an impact and effect on the rise and fall of stock market prices. The internet news articles were tested to evaluate the accuracy by comparing predicted values of the actual stock index and the forecasting models of the companies. This paper collected stock news from the internet, and analyzed and identified the relationship with the stock price index. Since the internet news contents consist mainly of unstructured texts, this study used text mining technique and multiple regression analysis technique to analyze news articles. A company H as a representative automobile manufacturing company was selected, and prediction models for the stock price index of company H was presented. Thus two prediction models for forecasting the upturn and decline of H stock index is derived and presented. Among the two prediction models, the error value of the prediction model (1) is low, and so the prediction performance of the model (1) is relatively better than that of the prediction model (2). As the further research, if the contents of this study are supplemented by real artificial intelligent investment decision system and applied to real investment, more practical research results will be able to be developed.

• 환경영향평가
• /
• 제1권1호
• /
• pp.21-30
• /
• 1992

Environmental Impact Assessment(EIA) is developing as a tool for environmentally sound and sustainable development in Korea. For more effective implementation of it, we try to apply Environmental Information System (EIS) to EIA process. EIS is composed of geographic and attribute data related to environment and Geographic Information System(GIS), and it will be applied to scoping, prediction, and alternative assessment, etc. in EIA. This study focuses on application of geographic data using GIS in suitability analysis of alternative assessment. We use TIN, buffering, and overlaying in GIS functions.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2005년도 춘계학술대회논문집
• /
• pp.800-804
• /
• 2005

In this paper, the radiated sound pressure induced by low velocity impact is obtained by solving the Rayleigh integral equation. For structurally radiated noise, the sound field is directly coupled to the structural motion. Therefore the impact response should be analyzed. It is well known that the presence of the delamination in a composite laminate introduces a local flexibility which changes the dynamic characteristic of the structure. The 2-D simplified delamination model is used to analyze the impact response. And the 3-D non-linear finite element model is developed using gap element to avoid the overlap and penetration between the upper and lower sub-laminates at delamination region. Predicted impact response using 2-D equivalent delamination model are compared with the numerical ones from the 3-D non-linear finite element model.