Fast prediction of aerodynamic noise induced by the flow around a cylinder based on deep neural network

Accurate and fast prediction of aerodynamic noise has always been a research hotspot in fluid mechanics aeroacoustics. The conventional methods based on numerical simulation often demand huge computational resources, which are difficult to balance between accuracy efficiency. Here, we present data-driven deep neural network (DNN) method realize while maintaining accuracy. proposed learning can predict the spatial distributions information under different working conditions. Based large eddy turbulence model Ffowcs Williams–Hawkings acoustic analogy theory, dataset composed 1216 samples is established. With reference method, DNN framework map relationship coordinates, inlet velocity overall sound pressure level. root-mean-square-errors below 0.82 dB test dataset, directivity predicted by basically consistent with simulation. This work paves novel way for high application potential field prediction.