• 대한기계학회논문집B
• /
• 제32권7호
• /
• pp.549-557
• /
• 2008

Despite of the laminar-turbulent transition region co-exist with fully turbulence region around the leading edge of an airfoil, still lots of researchers apply to fully turbulence models to predict aerodynamic characteristics. It is well known that fully turbulent model such as standard k-model couldn't predict the complex stall and the separation behavior on an airfoil accurately, it usually leads to over prediction of the aerodynamic characteristics such as lift and drag forces. So, we apply correlation based transition model to predict aerodynamic performance of the NREL (National Renewable Energy Laboratory) Phase IV wind turbine. And also, compare the computed results from transition model with experimental measurement and fully turbulence results. Results are presented for a range of wind speed, for a NREL Phase IV wind turbine rotor. Low speed shaft torque, power, root bending moment, aerodynamic coefficients of 2D airfoil and several flow field figures results included in this study. As a result, the low speed shaft torque predicted by transitional turbulence model is very good agree with the experimental measurement in whole operating conditions but fully turbulent model(${\kappa}-\;{\varepsilon}$) over predict the shaft torque after 7m/s. Root bending moment is also good agreement between the prediction and experiments for most of the operating conditions, especially with the transition model.

• 터널과지하공간
• /
• 제28권3호
• /
• pp.277-291
• /
• 2018

이 논문에서는 재료의 단축하중 하에서의 응력-변형률 곡선을 예측하기 위하여 순환 신경망의 일종인 LSTM(Long Short-Term Memory) 알고리즘을 사용하였다. 석고와 규사를 혼합해 만든 재료에 일축압축시험을 수행하여 얻은 응력-변형률 데이터를 이용하였으며, 낮은 응력 구간의 초반 데이터를 활용해서 파괴 전까지의 거동을 예측하였다. 앞부분의 데이터를 활용하여 단계적으로 뒤쪽 구간의 값을 예측하는 LSTM 순환 신경망의 구조상 큰 응력에 대응하는 변형률을 예측할 경우에는 앞쪽 구간의 오차가 누적되어 실측값과 차이가 늘어났으나 전반적으로 높은 정확도로 응력-변형률 곡선을 예측하였다. 예측에 사용한 초기 데이터의 길이가 늘어나는 경우 정확도는 조금 증가했다. 그러나 접선을 이용한 단순 예측과의 성능 차이는 초기 데이터의 길이가 작은 경우에 두드러졌으며, 적은양의 데이터로도 응력-변형률 곡선 전체 구간의 예측을 가능하게 한다는 점으로부터 신경망 모델의 필요성을 확인하였다.

• 한국분무공학회지
• /
• 제22권4호
• /
• pp.210-217
• /
• 2017

A gasoline direct injection engine has an intake air temperature can be lowered by the fuel vaporization in the combustion chamber increase the volume efficiency is high compression ratio. Therefore, study for injection rate and characteristics which influence mixture formation in combustion chamber is important. Movement of the injector needle has a direct effect on the injection of the fuel, such as formation of cavitation, the fuel injection rate, etc. Therefore, recent studies on the dynamic characteristics of the injector considering the movement of the needle have been reported, but it takes a lot of time and cost to experimentally confirm the movement of the needle inside the injector. In this study, AMESim, a commercial 1-D code, and Star-CCM+, a 3-D CFD code, were used to predict the dynamic performance of the injector with needle motion. In order to predict the movement of the needle under the high pressure, the result of the surface pressure distribution according to the movement of the needle was derived by using the morphing technique of flow analysis. In addition, we predicted the injection rate of the injector considering the movement of the needle in conjunction with the 1-D code. The injection rate of the injector was measured by the BOSCH's method and the results were similar to those of the simulation results. This method can predict the injection rate and injection characteristics and this result is expected to be used to predict the performance of gasoline direct injection engines with low cost and time in the future.

• Smart Structures and Systems
• /
• 제30권6호
• /
• pp.601-612
• /
• 2022

The prediction of structural mechanical behaviors is vital important to early perceive the abnormal conditions and avoid the occurrence of disasters. Especially for underground engineering, complex geological conditions make the structure more prone to disasters. Aiming at solving the problems existing in previous studies, such as incomplete consideration factors and can only predict the continuous performance, the deep attention fused temporal convolution network (DATCN) is proposed in this paper to predict the spatial mechanical behaviors of structure, which integrates both the temporal effect and spatial effect and realize the cross-time prediction. The temporal convolution network (TCN) and self-attention mechanism are employed to learn the temporal correlation of each monitoring point and the spatial correlation among different points, respectively. Then, the predicted result obtained from DATCN is compared with that obtained from some classical baselines, including SVR, LR, MLP, and RNNs. Also, the parameters involved in DATCN are discussed to optimize the prediction ability. The prediction result demonstrates that the proposed DATCN model outperforms the state-of-the-art baselines. The prediction accuracy of DATCN model after 24 hours reaches 90 percent. Also, the performance in last 14 hours plays a domain role to predict the short-term behaviors of the structure. As a study case, the proposed model is applied in an underwater shield tunnel to predict the stress variation of concrete segments in space.

• 스마트미디어저널
• /
• 제11권2호
• /
• pp.31-38
• /
• 2022

하천의 염분 변화를 신속히 예측하는 것은 염분 침투로 인한 농업, 생태계의 피해를 예측하고 재해 방지 대책을 수립하기 위해서 중요한 작업이다. 머신러닝 기법은 물리 기반 수리 모델에 비해 계산량이 훨씬 적기 때문에, 비교적 짧은 시간에 염분농도를 예측 가능하여 물리 기반 수리 모델의 보완 기법으로 연구되고 있다. 해외에서는 머신러닝 기법 기반 염분 예측 연구들이 활발히 연구되고 있으나, 대한민국의 공공데이터에 머신러닝 기법을 적용한 연구는 충분치 않다. 낙동강 하구의 환경 정보에 관한 공공데이터와 함께, 본 연구는 여러 종류의 머신러닝 기법의 염분농도에 대한 예측 성능을 측정하였다. 실험 결과에서, 결정 트리 기반의 LightGBM 알고리즘은 평균 RMSE 0.37의 예측 정확도와 타 알고리즘 대비 2-20배 빠른 학습 속도를 보여주었다. 따라서 국내 하천의 염분농도 예측에도 머신러닝 기법을 적용할 수 있다고 판단된다.

• 한국공간구조학회지
• /
• 제20권4호
• /
• pp.21-25
• /
• 2020

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2001년도 춘계학술대회논문집E
• /
• pp.807-812
• /
• 2001

The effects of casing shapes on the interaction of the impeller and volute in a small-size turbo-compressor are investigated. Numerical analysis is conducted for the compressor with circular and single volute casings from inlet to discharge nozzle. In order to predict the flow pattern inside the entire impeller, vaneless diffuser, and casing, calculations with a multiple frame of reference method between the rotating and stationery parts of the domain are carried out. For incompressible turbulent flow fields, the continuity and three-dimensional time-averaged Navier-Stokes equations are employed. To predict the performance of two types of casings, the static pressure and loss coefficients are obtained with various flow rates. Also, static pressure distributions around casings are studied for different casing shapes, which are very important to predict the distribution of radial load.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2008년도 춘계 학술발표회 초청강연 및 논문집
• /
• pp.644-655
• /
• 2008

Conventional hyperbolic model does not satisfactorily predict the overall stress-strain behaviors of various geomaterials. Tatsuoka and Shibuya(1992) suggest the generalized hyperbolic equation(GHE) considering strain dependency and calculated performance is in good agreement with precise triaxial compression test results of stress-strain relations over wide range of strains before peak stress condition in some cases, but GHE model also does not satisfactorily predict stress-strain relations as strain goes on state of peak stress in most cases. For improve a weak point of the GHE, in this study, modified form of generalized hyperbolic equation (MGHE model) is proposed which can predict highly nonlinear stress-strain behavior for various geomaterials from small strain to peak stress condition.

• Journal of Information Processing Systems
• /
• 제8권2호
• /
• pp.241-262
• /
• 2012

An understanding of quality attributes is relevant for the software organization to deliver high software reliability. An empirical assessment of metrics to predict the quality attributes is essential in order to gain insight about the quality of software in the early phases of software development and to ensure corrective actions. In this paper, we predict a model to estimate fault proneness using Object Oriented CK metrics and QMOOD metrics. We apply one statistical method and six machine learning methods to predict the models. The proposed models are validated using dataset collected from Open Source software. The results are analyzed using Area Under the Curve (AUC) obtained from Receiver Operating Characteristics (ROC) analysis. The results show that the model predicted using the random forest and bagging methods outperformed all the other models. Hence, based on these results it is reasonable to claim that quality models have a significant relevance with Object Oriented metrics and that machine learning methods have a comparable performance with statistical methods.

• International Journal of Computer Science & Network Security
• /
• 제22권11호
• /
• pp.265-271
• /
• 2022

Social media is a form of communication based on the internet to share information through content and images. Their choice of profile images and type of image they post can be closely connected to their personality. The user posted images are designated as personality traits. The objective of this study is to predict five factor model personality dimensions from profile images by using deep learning and neural networks. Developed a deep learning framework-based neural network for personality prediction. The personality types of the Big Five Factor model can be quantified from user profile images. To measure the effectiveness, proposed two models using convolution Neural Networks to classify each personality of the user. Done performance analysis among two different models for efficiently predict personality traits from profile image. It was found that VGG-69 CNN models are best performing models for producing the classification accuracy of 91% to predict user personality traits.