Motivated by the need for reliable on-board and real-time rotor blade icing detection with quantified uncertainty, we demonstrate the use of Bayesian recurrent neural networks, particularly the long short-term memory (LSTM), to predict time-series aerodynamic performance metrics from measurements of aeroacoustic time-series. The neural network models are trained using simulation data generated from physics-based models. To help improve robustness against measurement error in real life, we augment the data targets with artificial noise corruption. The training is done by minimizing the negative evidence lower bound (ELBO), taking a mean-field variational inference approach that finds independent Gaussian distribution most closely approximates the true Bayesian posterior. Promising performance is observed in the test set, where Bayesian LSTM achieved lower prediction errors compared to a Monte Carlo dropout version of the LSTM model.

Bayesian Recurrent Neural Networks for Monitoring Rotorcraft Icing from Aeroacoustics Time-Series Data

Morelli, M. C.;Guardone, A.
2022-01-01

Abstract

Motivated by the need for reliable on-board and real-time rotor blade icing detection with quantified uncertainty, we demonstrate the use of Bayesian recurrent neural networks, particularly the long short-term memory (LSTM), to predict time-series aerodynamic performance metrics from measurements of aeroacoustic time-series. The neural network models are trained using simulation data generated from physics-based models. To help improve robustness against measurement error in real life, we augment the data targets with artificial noise corruption. The training is done by minimizing the negative evidence lower bound (ELBO), taking a mean-field variational inference approach that finds independent Gaussian distribution most closely approximates the true Bayesian posterior. Promising performance is observed in the test set, where Bayesian LSTM achieved lower prediction errors compared to a Monte Carlo dropout version of the LSTM model.
2022
AIAA Scitech 2022 Forum
978-1-62410-631-6
File in questo prodotto:
File Dimensione Formato  
TONGH01-22.pdf

Accesso riservato

Descrizione: Paper
: Publisher’s version
Dimensione 699.53 kB
Formato Adobe PDF
699.53 kB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11311/1201485
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? ND
social impact