• 한국음향학회지
• /
• 제22권6호
• /
• pp.512-518
• /
• 2003

본 논문에서는 차량시스템의 진동효과를 고려하는 내구평가를 위한 공진내구해석이 수행된다. 공진내구해석을 수행하는데 있어서 주파수응답과 주파수영역의 동하중이 사용된다. 다물체 동역학해석, 유한요소해석 및 피로수명예측기법이 가상내구 평가를 위해 적용된다. 주파수응답과 동하중이력을 얻기 위해 차량 다물체 모델을 이용하여 전형적인 파트홀과 벨지안로를 통과하는 컴퓨터 시뮬레이션을 수행한다. 공진내구해석기법을 사용하여 승용차의 후방 현가장치에 대한 내구평가를 수행하고 그 결과를 준정적내구해석결과와 비교한다. 본 연구를 통하여 차량 시스템의 공진주파수를 고려한 피로수명을 초기설계 단계에서 효과적으로 평가할 수 있다는 것을 알 수 있다.

• 항공우주기술
• /
• 제5권2호
• /
• pp.149-158
• /
• 2006

분리된 페어링의 동안정 미계수 예측을 위해 기술 및 비용적 측면을 고려하여 어떤 방 법이 가장 적합할지에 대한 검토가 수행되었으며, 탑재물 페어링의 형상적 특성, 계산 조 건, 그리고 요구되는 정확도 등을 고려한 최적의 예측 방법을 선정하였다. 관성 좌표계에 대해 기술된 Euler 방정식을 해석하여 강제조화운동이 가해진 분리 PLF의 비정상 공력계수를 구하였으며, 이를 한 주기 동안 적분하여 동안정 미계수를 산출하였다. 이와 같은 기 법을 적용함으로써 분리된 3차원 PLF 형상에 대해 마하수 0.60~2.00, 받음각 $-180^{\circ}$~$180^{\circ}$ 및 옆미끄럼각 $-90^{\circ}$~$90^{\circ}$에 대하여 동안정 미계수를 얻을 수 있었다.

• 자동차안전학회지
• /
• 제13권4호
• /
• pp.14-19
• /
• 2021

This paper presents LiDAR static obstacle map based vehicle dynamic state estimation algorithm for urban autonomous driving. In an autonomous driving, state estimation of host vehicle is important for accurate prediction of ego motion and perceived object. Therefore, in a situation in which noise exists in the control input of the vehicle, state estimation using sensor such as LiDAR and vision is required. However, it is difficult to obtain a measurement for the vehicle state because the recognition sensor of autonomous vehicle perceives including a dynamic object. The proposed algorithm consists of two parts. First, a Bayesian rule-based static obstacle map is constructed using continuous LiDAR point cloud input. Second, vehicle odometry during the time interval is calculated by matching the static obstacle map using Normal Distribution Transformation (NDT) method. And the velocity and yaw rate of vehicle are estimated based on the Extended Kalman Filter (EKF) using vehicle odometry as measurement. The proposed algorithm is implemented in the Linux Robot Operating System (ROS) environment, and is verified with data obtained from actual driving on urban roads. The test results show a more robust and accurate dynamic state estimation result when there is a bias in the chassis IMU sensor.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권4호
• /
• pp.2060-2077
• /
• 2019

Recently, mobile healthcare services have attracted significant attention because of the emerging development and supply of diverse wearable devices. Smartwatches and health bands are the most common type of mobile-based wearable devices and their market size is increasing considerably. However, simple value comparisons based on accumulated data have revealed certain problems, such as the standardized nature of health management and the lack of personalized health management service models. The convergence of information technology (IT) and biotechnology (BT) has shifted the medical paradigm from continuous health management and disease prevention to the development of a system that can be used to provide ground-based medical services regardless of the user's location. Moreover, the IT-BT convergence has necessitated the development of lifestyle improvement models and services that utilize big data analysis and machine learning to provide mobile healthcare-based personal health management and disease prevention information. Users' health data, which are specific as they change over time, are collected by different means according to the users' lifestyle and surrounding circumstances. In this paper, we propose a prediction model of user physical activity that uses data characteristics-based long short-term memory (DC-LSTM) recurrent neural networks (RNNs). To provide personalized services, the characteristics and surrounding circumstances of data collectable from mobile host devices were considered in the selection of variables for the model. The data characteristics considered were ease of collection, which represents whether or not variables are collectable, and frequency of occurrence, which represents whether or not changes made to input values constitute significant variables in terms of activity. The variables selected for providing personalized services were activity, weather, temperature, mean daily temperature, humidity, UV, fine dust, asthma and lung disease probability index, skin disease probability index, cadence, travel distance, mean heart rate, and sleep hours. The selected variables were classified according to the data characteristics. To predict activity, an LSTM RNN was built that uses the classified variables as input data and learns the dynamic characteristics of time series data. LSTM RNNs resolve the vanishing gradient problem that occurs in existing RNNs. They are classified into three different types according to data characteristics and constructed through connections among the LSTMs. The constructed neural network learns training data and predicts user activity. To evaluate the proposed model, the root mean square error (RMSE) was used in the performance evaluation of the user physical activity prediction method for which an autoregressive integrated moving average (ARIMA) model, a convolutional neural network (CNN), and an RNN were used. The results show that the proposed DC-LSTM RNN method yields an excellent mean RMSE value of 0.616. The proposed method is used for predicting significant activity considering the surrounding circumstances and user status utilizing the existing standardized activity prediction services. It can also be used to predict user physical activity and provide personalized healthcare based on the data collectable from mobile host devices.

• 한국공간구조학회논문집
• /
• 제20권2호
• /
• pp.51-58
• /
• 2020

Recently, deep learning that is the most popular and effective class of machine learning algorithms is widely applied to various industrial areas. A number of research on various topics about structural engineering was performed by using artificial neural networks, such as structural design optimization, vibration control and system identification etc. When nonlinear semi-active structural control devices are applied to building structure, a lot of computational effort is required to predict dynamic structural responses of finite element method (FEM) model for development of control algorithm. To solve this problem, an artificial neural network model was developed in this study. Among various deep learning algorithms, a recurrent neural network (RNN) was used to make the time history response prediction model. An RNN can retain state from one iteration to the next by using its own output as input for the next step. An eleven-story building structure with semi-active tuned mass damper (TMD) was used as an example structure. The semi-active TMD was composed of magnetorheological damper. Five historical earthquakes and five artificial ground motions were used as ground excitations for training of an RNN model. Another artificial ground motion that was not used for training was used for verification of the developed RNN model. Parametric studies on various hyper-parameters including number of hidden layers, sequence length, number of LSTM cells, etc. After appropriate training iteration of the RNN model with proper hyper-parameters, the RNN model for prediction of seismic responses of the building structure with semi-active TMD was developed. The developed RNN model can effectively provide very accurate seismic responses compared to the FEM model.

• 한국시뮬레이션학회논문지
• /
• 제17권3호
• /
• pp.19-26
• /
• 2008

본 논문에서는 중기 국채(Treasure Note; T-Note)의 실제 자료를 이용하여 채권 가격에 대한 이자율을 예측하는 동적인 예측 알고리즘을 제안하고 있다. 제안한 알고리즘은 이자율 기간 구조를 근본으로 하고 있으며 표준 위너 과정(standard Wiener process)과 같은 다양한 금융 모형의 대안으로 활용 가능하다. 본 논문에서는 실제 자료의 누적 분포 함수(Cumulative Distribution Function; CDF)를 이용하여 이자율을 측정하였으며 CDF는 수치적 방법인 보간법 중에 자주 활용되는 내츄럴 큐빅 스플라인(natural cubic spline; NCS)방법을 통하여 얻었다. 위에서 얻은 CDF를 통하여 난수 생성기법(random number generation scheme; RNGS)을 이용하여 채권의 가격를 계산하였다. 컴퓨터 시뮬레이션을 통해 얻은 실험결과로부터 제안된 예측 알고리즘에서 엄밀도(precision)의 낮은 값을 얻음으로써 채권의 가치가 더욱 예리하고 정확하게 평가되었음을 확인할 수 있었으며, 이는 매우 근거 있는 예측이라 할 수 있다.

• 디지털융복합연구
• /
• 제19권1호
• /
• pp.67-75
• /
• 2021

국내 수입차량 판매 증가에도 불구하고 부품 물류센터의 판매 예측에 관한 연구는 매우 부족한 현실이다. 이러한 측면에서 본 연구는 부품 물류센터의 상위 판매 상품에 대한 판매 예측을 수행 하는 것을 연구의 목적으로 한다. 연구는 판매 예측에 대한 동적특성과 영향을 주는 변수의 인과관계 및 피드백 루프를 고려할 수 있는 시스템 다이내믹스 방법론을 도입하였다. 연구결과 'Oil'의 경우 시간이 지날수록 소모품 판매 수량이 증가하는 패턴을 보이고, MAPE을 실시한 결과 31.3%의 합리적 예측모델로 평가되었다. 상품 'Battery'의 경우 실제 데이터와 예측 데이터 모두 매년 10월을 기점으로 판매가 증가하여 12월에서 가장 높은 판매를 보이고 다음해 2월부터 감소하는 계절성 판매패턴을 보였다. 본 연구는 기존 연구에는 존재하지 않았던 특정 수입 자동차 부품 물류센터의 실제 데이터를 확보하고, 시스템 다이내믹스를 통하여 미래 판매 물동량 예측을 정량적으로 분석하여 제시하였다는 점에서 학문적 시사점을 갖는다.

• International Journal of Aeronautical and Space Sciences
• /
• 제16권2호
• /
• pp.264-277
• /
• 2015

This article investigates various transcription techniques for the Legendre pseudospectral (PS) method to compare the pros and cons of each approach. Eight combinations from four different types of collocation points and two discretization methods for dynamic constraints, which differentiate Legendre PS transcription techniques, are implemented to solve a carefully selected test set of nonlinear optimal control problems (NOCPs). The convergence property and prediction accuracy are compared to provide a useful guideline for selecting the best combination. The tested NOCPs consist of the minimum time, minimum energy, and problems with state and control constraints. Therefore, the results drawn from this comparative study apply to the solution of similar types of NOCPs and can mitigate much debate about the best combinations. Additionally, important findings from this study can be used to improve the numerical efficiency of the Legendre PS methods. Three PS applications to the aerospace engineering problems are demonstrated to prove this point.

• 대한기계학회논문집A
• /
• 제30권4호
• /
• pp.379-386
• /
• 2006

The hyper-elastic material has been used gradually and its range was extended all over the industry. The performance prediction of hyper-elastic material was required not only experimental methods but also numerical methods. In this study, we presented the process how to use numerical method for hyper-elastic material and applied it to seat-ring of butterfly valve. The finite element analysis was executed to evaluate the mechanical characteristics of hyper-elastic material. And the optimum model considered conditions and features. According to that model, the load conditions were obtained by using CFD analysis.

• Wind and Structures
• /
• 제5권2_3_4호
• /
• pp.151-164
• /
• 2002

Predictions of the pedestrian level wind speeds for the downtown area of Auckland that have been obtained by wind tunnel and computational fluid dynamic (CFD) modelling are presented. The wind tunnel method involves the observation of erosion patterns as the wind speed is progressively increased. The computational solutions are mean flow calculations, which were obtained by using the finite volume code PHOENICS and the $k-{\varepsilon}$ turbulence model. The results for a variety of wind directions are compared, and it is observed that while the patterns are similar there are noticeable differences. A possible explanation for these differences arises because the tunnel prediction technique is sensitivity to gust wind speeds while the CFD method predicts mean wind speeds. It is shown that in many cases the computational model indicates high mean wind speeds near the corner of a building while the erosion patterns are consistent with eddies being shed from the edge of the building and swept downstream.