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

Abstract

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

Deep learning-based wind noise prediction study for automotive clay model

“…A study by a university in South Korea [46] involved inputting images of a car from various angles into a deep learning model to predict the wind noise of modern car models. Meng et al [50], based on large-eddy simulation and acoustic analogy theory, utilized deep learning to predict the noise of a cylinder flow model using spatial coordinates and flow velocity as input. In summary, deep learning methods can predict both fluid and acoustic characteristics.…”

Fast prediction of the mechanical response for layered pavement under instantaneous large impact based on random forest regression

“…With the rapid development of data science, datadriven machine learning methods have the potential to replace the expensive high-fidelity analyses with less expensive approximations. [17][18][19] So far, machine learning has been widely applied in flexible pavement assessment and prediction. Xie et al [20] firstly determined the subgrade modulus by two DBPs, base damage index (BDI) and shape factor F 2 , and then trained an artificial neural network (ANN) with the subgrade modules and other parameters to estimate the upper layer module.…”

Crysformer: An attention-based graph neural network for properties prediction of crystals

“…[5,8,9] Such approaches have the potential to overcome the limitations of traditional methods and provide more accurate and generalizable predictions of crystal properties, facilitating the discovery of novel materials with desirable properties. [10][11][12] In recent years, deep learning has shown remarkable success in various fields, [13] including image recognition, natural language processing, and speech recognition. [14][15][16][17] Among the various architectures, transformer-based models have gained widespread attention for their ability to model complex dependencies effectively.…”