Pressure fluctuations at the wall beneath turbulent boundary layers are major sources of vibration and acoustic fatigue on aerospace structures. Hypersonic aircraft design requires accurate estimation of the acoustic loading on various surfaces of the aircraft.Wall-pressure spectra models derived to fit experimental and simulation data can provide an estimate of the pressure fluctuations at a reduced cost compared to wind tunnel experiments and high-fidelity simulations. These models are usually derived from theoretical analysis, by incorporating some knowledge about the physics of the problem, and tuning the parameters such as constants and exponents so that the model fits to available experimental data.In this work, we model the pressure fluctuations spectra beneath subsonic, supersonic and hypersonic turbulent boundary layers (TBLs) at zero pressure gradient using neural networks, a powerful statistical learning technique. We collect and consolidate data about the pressure fluctuation spectra from a large number of previous studies on TBLs. While past works have relied on hand-tuning of model parameters to fit available data, the use of a modern statistical tool like NNs provides an automatic and quick way to fit a model. The major contributions of this work are: (a) We demonstrate the use of NNs to build empirical models from data in fluid mechanics and lay out a framework for their use in the future when more data is available, (b) We achieve a trained model that performs better than previous empirical models both in terms of quantitative and qualitative accuracy.<br style="font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: 2; text-align: -webkit-auto; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px">
&nbsp;

Modelling Wall-Pressure Spectra in Turbulent Boundary Layers Using Neural Networks

Paper Proceedings: https://asmedigitalcollection.asme.org/GTINDIA/GTINDIA2021/volume/85536

ASME 2021 Gas Turbine India Conference (GTINDIA2021)

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.