Navigation and service

Project DL-Aero - Prediction of Acoustic Fields Using a Lattice-Boltzmann Method and Deep Learning

SDL Highly Scalable Fluids & Solids Engineering

Project description

Using traditional computational fluid dynamics and aeroacoustics methods, the accurate simulation of aeroacoustic sources requires high compute resources to resolve all necessary physical phenomena. In contrast, once trained, artificial neural networks such as deep encoder-decoder convolutional networks allow to predict aeroacoustics at lower cost and, deepening on the quality of the employed network, also at high accuracy. In this project, the architecture for such a neural network is developed to predict the room aeroacoustics. It is trained by numerical results from up to GPU-based lattice-Boltzmann simulations that include randomly distributed rectangular and circular objects, and monopole noise sources. Several parameters are studied to tune the predictions and to increase their accuracy.

Project publications:

[1]Rüttgers, M., Koh, S.-R., Jitsev, J., Schröder, W., & Lintermann, A. (2020). Prediction of Acoustic Fields Using a Lattice-Boltzmann Method and Deep Learning. In High Performance Computing, Proceedings of the 35th International Conference, ISC High Performance 2020 (pp. 81–101). doi:10.1007/978-3-030-59851-8_6