• Wind and Structures
• /
• 제34권6호
• /
• pp.525-538
• /
• 2022

High-rise wooden pagodas generate large displacement responses under wind action. It is necessary and wise to reduce the wind loads and wind-induced responses on the architectural heritage using artificial plants, which do not damage ancient architecture and increase greenery. This study calculates and analyzes the wind loads and wind-induced responses on the Yingxian Wooden Pagoda, in China, using artificial plants via the finite element analysis (FEA). A three-dimensional wind-loading field was simulated using a wind tunnel test. Wind loads and wind-induced responses, including the displacement and acceleration of the pagoda with and without artificial plants, were analyzed. In addition, three types of tree arrangements were discussed and analyzed using the score method. The results revealed that artificial plants can effectively control wind loads and wind-induced displacements, but the wind-induced accelerations are enlarged to some extent during the process. The height of the tree significantly affected the shelter effects of the structure. The distance of trees from the pagoda and arrangement width of the tree had less influence on shelter effects. This study extends the understanding of the nondestructive method based on artificial plants, for controlling the wind base loads and structural responses of wooden pagodas and preserving architectural heritage via FEA.

• Wind and Structures
• /
• 제20권2호
• /
• pp.169-189
• /
• 2015

To investigate the effects of "sudden change" of wind fluctuations on vehicle running performance, which is caused by the artificial discrete simulation of wind field, a three-dimensional vehicle model is set up with multi-body dynamics theory and the vehicle dynamic responses in crosswind conditions are obtained in time domain. Based on Hilbert Huang Transform, the effects of simulation separations on time-frequency characteristics of wind field are discussed. In addition, the probability density distribution of "sudden change" of wind fluctuations is displayed, addressing the effects of simulation separation, mean wind speed and vehicle speed on the "sudden change" of wind fluctuations. The "sudden change" of vehicle dynamic responses, which is due to the discontinuity of wind fluctuations on moving vehicle, is also analyzed. With Principal Component Analysis, the comprehensive evaluation of vehicle running performance in crosswind conditions at different simulation separations of wind field is investigated. The results demonstrate that the artificial discrete simulation of wind field often causes "sudden change" in the wind fluctuations and the corresponding vehicle dynamic responses are noticeably affected. It provides a theoretical foundation for the choice of a suitable simulation separation of wind field in engineering application.

• Wind and Structures
• /
• 제36권6호
• /
• pp.405-421
• /
• 2023

Strong wind is the main factors of wind-damage of high-rise buildings, which often creates largely economical losses and casualties. Wind pressure plays a critical role in wind effects on buildings. To obtain the high-resolution wind pressure field, it often requires massive pressure taps. In this study, two traditional methods, including bilinear and bicubic interpolation, and two deep learning techniques including Residual Networks (ResNet) and Generative Adversarial Networks (GANs), are employed to reconstruct wind pressure filed from limited pressure taps on the surface of an ideal building from TPU database. It was found that the GANs model exhibits the best performance in reconstructing the wind pressure field. Meanwhile, it was confirmed that k-means clustering based retained pressure taps as model input can significantly improve the reconstruction ability of GANs model. Finally, the generalization ability of k-means clustering based GANs model in reconstructing wind pressure field is verified by an actual engineering structure. Importantly, the k-means clustering based GANs model can achieve satisfactory reconstruction in wind pressure field under the inputs processing by k-means clustering, even the 20% of pressure taps. Therefore, it is expected to save a huge number of pressure taps under the field reconstruction and achieve timely and accurately reconstruction of wind pressure field under k-means clustering based GANs model.

• 한국정보과학회논문지:시스템및이론
• /
• 제27권8호
• /
• pp.701-709
• /
• 2000

실세계에서의 바람은 자연 발생적인 것과 인위적으로 생성한 것으로 분류할 수 있다. 이제까지의 연구 결과들은 자연 현상으로서의 바람을 모델링하였다. 본 논문에서는 사람의 입이나 선풍기, 에어컨 등에서 발생하는 인공적인 바람을 모델링하기 위한 바람 모델을 제시한다. 본 논문의 바람 모델에서는 생성된 바람이 도달하는 물체를 찾아내고, 그 물체에 가해지는 힘을 계산하는 방법을 제공한다. 특히, 이 모델은 가상 현실과 같은 실시간 처리가 필요한 분야들에서 사용 가능하도록 최적화된 계산을 수행하도록 설계되었다. 본 논문에서 제시한 방법은 기존의 자연 발생적인 바람 모델들과는 보완적인 관계에 있다. 이들 모델들을 통합하여 종합적인 바람 생성 시스템을 구성할 수 있을 것으로 기대된다.

• Wind and Structures
• /
• 제5권1호
• /
• pp.1-14
• /
• 2002

Artificial Neural Networks (ANN) have the capability to develop functional relationships between input-output patterns obtained from any source. Thus ANN can be conveniently used to develop a generalised relationship from limited and sometimes inconsistent data, and can therefore also be applied to tackle the data obtained from wind tunnel tests on building models with large number of variables. In this paper ANN model has been developed for predicting wind induced pressures in various zones of a Gable Building from limited test data. The procedure is also extended to a case wherein interference effects on a gable roof building by a similar building are studied. It is found that the Artificial Neural Network modelling is seen to predict successfully, the pressure coefficients for any roof slope that has not been covered by the experimental study. It is seen that ANN modelling can lead to a reduction of the wind tunnel testing effort for interference studies to almost half.

• Wind and Structures
• /
• 제32권2호
• /
• pp.161-167
• /
• 2021

In this study, the artificial neural network (ANN) method was used for estimating the monthly mean wind speed of Sivas, in the central part of Turkey. Eighteen years of wind speed data obtained from nine measurement stations during the period of 2000-2017 at 10 m height was used for ANN analysis. It was found that mean absolute percentage error (MAPE) ranged from 3.928 to 6.662, mean bias error (MBE) ranged from -0.089 to -0.003, while root mean square error (RMSE) ranged from 0.050 to 0.157 and R2 ranged from 0.86 to 0.966. ANN models provide a good approximation of the wind speed for all measurement stations, however, a tendency to underestimate is also obvious.

• Journal of Electrical Engineering and Technology
• /
• 제10권1호
• /
• pp.41-46
• /
• 2015

It is very important to make accurate forecast of wind power because of its indispensable requirement for power system stable operation. The research is to predict wind power by chaos and BP artificial neural networks (CBPANNs) method based on genetic algorithm, and to evaluate feasibility of the method of predicting wind power. A description of the method is performed. Firstly, a calculation of the largest Lyapunov exponent of the time series of wind power and a judgment of whether wind power has chaotic behavior are made. Secondly, phase space of the time series is reconstructed. Finally, the prediction model is constructed based on the best embedding dimension and best delay time to approximate the uncertain function by which the wind power is forecasted. And then an optimization of the weights and thresholds of the model is conducted by genetic algorithm (GA). And a simulation of the method and an evaluation of its effectiveness are performed. The results show that the proposed method has more accuracy than that of BP artificial neural networks (BP-ANNs).

• 한국지진공학회논문집
• /
• 제21권6호
• /
• pp.295-301
• /
• 2017

This paper relates to the study of load characteristics applicable to wind turbine generators induced by earthquakes. An artificial design earthquake wave generated through the target spectrum and the envelope function of Richter Magnitude Scale (ML) 7.0 as in ASCE4-98 was created. A simulation of earthquake loads were performed according to the design load cases (DLC) 9.5~9.7 of GL guidelines. Additionally, simulation of seismic loads experienced by Wind Turbines installed in the Gyeongju region were carried out utilizing artificial earthquakes of ML 5.8 simulating the real earthquakes during the Gyeongju Earthquakes of Sept. 2016.

• 한국지능시스템학회논문지
• /
• 제20권2호
• /
• pp.243-250
• /
• 2010

최근 풍력발전 시스템은 가장 빨리 발전하고 있는 신재생 에너지원중 하나로 각광을 받고 있으며, 풍력발전 시스템의 주된 관심사는 어떻게 광범위한 풍속의 변화에서도 효율적으로 시스템을 동작시키는 가에 있다. 가변속 풍력발전 시스템은 고정속 풍력발전 시스템에 비해 더 높은 에너지 효율, 낮은 컴포넌트 스트레스를 달성할 수 있다는 장점을 갖는다. 일반적으로 가변속 풍력발전 시스템의 제어를 위해서는 풍속정보의 취득이 필수적으로 요구된다. 하지만 풍속계 등에 의해 측정된 풍속은 여러 요인에 의해 정확하지 않다는 문제점을 갖는다. 이에 본 연구에서는 풍속의 추정을 위한 칼만 필터와 칼만 필터에 의해 추정된 정보를 사용하여 학습된 인공신경망으로부터 최적의 로터 회전 속도를 유추할 수 있는 새로운 형태의 가변속 풍력발전 시스템을 위한 제어 알고리듬을 제안하고자 한다. 또한 Matlab의 시뮬링크를 사용하여 다양한 시뮬레이션 수행하여 제안된 기법의 유용성을 확인하고자 한다.

• 대한원격탐사학회지
• /
• 제32권2호
• /
• pp.185-194
• /
• 2016

본 연구에서는 지리정보시스템(GIS) 자료와 전산유체역학(CFD) 모델을 이용하여, 해상교량 건설에 따른 하의도 남쪽 지역의 인공적 지형변화가 국지풍에 미치는 영향을 조사하였다. 수치모델의 지표 경계 입력 자료로써 대상영역의 3차원 수치지형은 GIS 자료를 기반으로 구축하였으며, 유입류는 하의도 자동기상관측소(AWS)에서 관측된 바람자료로부터 설정하였다. 수치모의는 인공적 지형변화 전과 후에 대하여 계절별로 수행하였으며, 인근 염전지역의 바람 차단 효과를 중점적으로 분석하였다. 지표풍속은 접속도로 건설 구간에 인접한 남서쪽 지역에서 최대 유입류 대비 약 5~20% 정도 감소하는 것으로 나타났으며, 염전지역 전체에 대한 지표풍속은 평균 유입류 대비 약 2% 미만 감소하는 것으로 평가되었다. 또한, 서풍계열의 바람은 상대적으로 인공적 지형변화의 영향이 크게 나타났다.