Low-rise gable roof buildings pressure prediction using deep neural networks

This paper presents a deep neural network (DNN) based approach for predicting mean and peak wind pressure coefficients on the surface of a scale model low-rise, gable roof building. Pressure data were collected on the model at multiple prescribed wind directions and terrain roughness. The resultant pressure coefficients quantified from a subset of these directions and terrains were used to train a DNN to predict coefficients for directions and terrains excluded from the training. The approach can leverage a variety of input conditions to predict pressure coefficients with high accuracy, while the prior work has limited flexibility with the number of input variables and yielded lower prediction accuracy. A two-step nested DNN procedure is introduced to improve the prediction of peak coefficients. The optimal correlation coefficients of return predictions were 0.9993 and 0.9964, for mean and peak coefficient prediction, respectively. The concept of super-resolution based on global prediction is also discussed. With a sufficiently large database, the proposed DNN-based approach can augment existing experimental methods to improve the yield of knowledge while reducing the number of tests required to gain that knowledge. •Deep learning improves pressure prediction accuracy with information from all surface.•Mean and peak pressure coefficients can be accurately predicted with deep learning.•Globally prediction adaptively increases spatial resolution of pressure distribution.•Wind tunnel sensor distribution has various effects on spatial resolution enhancement.•Deep learning method shows strong generality for multiple pressure prediction tasks.