Prediction of wind loads on high-rise building using a BP neural network combined with POD

High-rise buildings are very sensitive to wind excitations, and wind-induced responses have always been the key factors for structural design. Facade openings have often been used as aerodynamic measures for wind-resistant design of high-rise buildings to meet the requirement of structural safety and comfort. Obvious wind speed amplifications can also be observed inside the openings. Therefore, implementing wind turbines in the openings is of great importance for the utilization of abundant wind energy resources in high-rise buildings and the development of green buildings. Based on numerical simulation and wind tunnel testing, the wind loads and wind speed amplifications on high-rise buildings with openings are investigated in detail. The three-dimensional numerical simulation for wind effects on high-rise building with openings was firstly carried out on FLUENT 15.0 platform by SST k − ε model. The mean wind pressure coefficients and the wind flow characteristics were obtained. The wind speed amplifications at the opening were analyzed, and the distribution law of wind speed in the openings is presented. Meanwhile, a series of wind tunnel tests were conducted to assess the mean and fluctuating wind pressure coefficients in high-rise building models with various opening rates. The variation of wind pressure distribution at typical measuring layers with wind direction was analyzed. Finally, the wind speed amplifications in the openings were studied and verified by the numerical simulation results.

Download Full-text

Active Control in a High-Rise Building under Multidirectional Wind Loads

Structures Congress 2008 ◽

10.1061/41016(314)285 ◽

2008 ◽

Cited By ~ 4

Author(s):

Aly Mousaad Aly ◽

Ferruccio Resta ◽

Alberto Zasso

Keyword(s):

Active Control ◽

Wind Loads ◽

High Rise ◽

High Rise Building

Download Full-text

Study on the Applications of Neural Networks for Processing Deformation Monitoring Data

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.501-504.2149 ◽

2014 ◽

Vol 501-504 ◽

pp. 2149-2153 ◽

Cited By ~ 2

Author(s):

Cai Yun Gao ◽

Xi Min Cui ◽

Xue Qian Hong

Keyword(s):

Neural Network ◽

Neural Networks ◽

Prediction Models ◽

Deformation Monitoring ◽

Monitoring Data ◽

Nonlinear Fitting ◽

High Rise ◽

High Rise Building ◽

Good Ability ◽

Neural Network Prediction

Accurately estimating the deformation of high-rise building is a very important work for surveyors, however it is very difficult to get an accurate and reliable predictor. In this paper, artificial neural network has been applied here because of its good ability of nonlinear fitting. On the basis of the high-rise building monitoring data, three prediction models including the BP, RBF and GRNN neural network prediction models were established, the comparative analysis for the prediction accuracy of the three models was obtained. The results show that neural network is capable for prediction, and GRNN possess higher capability in prediction and better adaptability in comparing with other two neural networks.

Download Full-text