Predicting wind pressures around circular cylinders using machine learning techniques: Fid-Bau Portal

Predicting wind pressures around circular cylinders using machine learning techniques

Hu, Gang / Kwok, K.C.S.

Abstract Numerous studies have been carried out to measure wind pressures around circular cylinders since the early 20th century due to its engineering significance. Consequently, a large amount of wind pressure data sets have accumulated, which presents an excellent opportunity for using machine learning (ML) techniques to train models to predict wind pressures around circular cylinders. Wind pressures around smooth circular cylinders are a function of mainly Reynolds number (Re), turbulence intensity (Ti) of the incident wind, and circumferential angle of the cylinder. Considering these three parameters as the inputs, this study trained two ML models to predict mean and fluctuating pressures respectively. Three machine learning algorithms including decision tree regressor, random forest, and gradient boosting regression trees (GBRT) were tested. The GBRT models exhibited the best performance for predicting both mean and fluctuating pressures, and they are capable of making accurate predictions for Re ranging from 10⁴ to 10⁶ and Ti ranging from 0% to 15%. It is believed that the GBRT models provide an efficient and economical alternative to traditional wind tunnel tests and computational fluid dynamic simulations for determining wind pressures around two-dimensional smooth circular cylinders within the studied Re and Ti range.

Highlights • Machine learning models were trained to predict wind pressures on circular cylinders. • Effects of Reynolds number and turbulence intensity were taken into account. • Decision tree, random forest, and gradient boosting regression trees were employed. • Gradient boosting regression trees models can make accurate predictions.