Prediction of transonic wing buffet pressure based on deep learning

Abstract In the present study, a deep learning approach based on long short-term memory (LSTM) neural network is applied for prediction of transonic wing buffet pressure. particular, fluctuations in surface pressure over certain time period as measured by piezoresistive sensor, are considered. As test case, generic XRF-1 aircraft configuration developed Airbus used. The has been investigated at different conditions European Transonic Wind tunnel (ETW). During ETW campaign, sensor data obtained local span—and chordwise positions lower and upper horizontal tail plane. For training network, flow condition with fixed angle attack $$\alpha$$ α position Subsequent, trained towards angles considering network. final step, LSTM used from considered training. By comparing results wind experiment good agreement indicated.