## Correlation Effects in Bayesian Neural Networks for Computational Aeroacoustics Ice Detection

### Abstract

In-flight rotor icing presents a serious problem in the operation of rotorcraft in cold climates, as complex ice shapes can significantly degrade the aerodynamic performance and handling characteristics of rotorcraft. Reliable real-time detection of ice formation is thus a critical enabling technology in improving rotorcraft safety. In this paper, we continue our previous work to explore a novel approach towards developing a real-time in-flight ice detection system using computational aeroacoustics and Bayesian neural networks. We focus on our use of Bayesian neural networks constructed from the simulated aeroacoustics dataset to enable rapid predictions of aerodynamic performance indicators together with quantified uncertainty. Specifically, we investigate the effectiveness and tradeoffs among several approximate Bayesian inference techniques for training Bayesian neural networks: (Gaussian) mean-field variational inference (MFVI), full-covariance variational inference (FCVI), and Stein variational gradient descent (SVGD). We find that although MFVI provides accurate mean predictions with accompanying uncertainty trends, neglecting parameter correlations in a neural network model fails to provide the rich uncertainty information that can be captured by FCVI and SVGD.

Type
Publication
AIAA Scitech 2020 Forum
Date
Citation
J. Hauth, X. Huan, B. Y. Zhou, N. R. Gauger, M. Morelli, and A. Guardone. Correlation Effects in Bayesian Neural Networks for Computational Aeroacoustics Ice Detection. In AIAA Scitech 2020 Forum, AIAA paper 2020–1414, Orlando, FL, 2020. https://dx.doi.org/10.2514/6.2020-1414

### BibTeX

@inproceedings{Hauth2020a,