Forecasting thermoacoustic instabilities in liquid propellant rocket engines using multimodal Bayesian deep learning. Issue 3 (September 2022)

• Record Type: Journal Article
• Authors: Sengupta, Ushnish; Waxenegger-Wilfing, Günther; Martin, Jan; Hardi, Justin; Juniper, Matthew P.
• Is Part Of: International journal of spray and combustion dynamics. Volume 14:Issue 3/4(2022)
• Page Start: 218
• Page End: 228
• Publication Date: 2022-09
• Subjects: Thermoacoustic instabilities -- multimodal data -- bayesian machine learning -- interpretable machine learning; Combustion engineering -- Periodicals; Fluid dynamics -- Periodicals; Combustion -- Periodicals; Spraying -- Periodicals; Combustion; Combustion engineering; Fluid dynamics; Spraying; Periodicals; 541.361
• DOI: 10.1177/17568277221139974
• Languages: English
• ISSNs: 1756-8285

Abstract

We present a method that combines multiple sensory modalities in a rocket thrust chamber to predict impending thermoacoustic instabilities with uncertainties. This is accomplished by training an autoregressive Bayesian neural network model that forecasts the future amplitude of the dynamic pressure time series, using multiple sensor measurements (injector pressure/ temperature measurements, static chamber pressure, high-frequency dynamic pressure measurements, high-frequency OH* chemiluminescence measurements) and future flow rate control signals as input. The method is validated using experimental data from a representative cryogenic research thrust chamber. The Bayesian nature of our algorithms allows us to work with a dataset whose size is restricted by the expense of each experimental run, without making overconfident extrapolations. We find that the networks are able to accurately forecast the evolution of the pressure amplitude and anticipate instability events on unseen experimental runs 500 milliseconds in advance. We compare the predictive accuracy of multiple models using different combinations of sensor inputs. We find that the high-frequency dynamic pressure signal is particularly informative. We also use the technique of integrated gradients to interpret the influence of different sensor inputs on the model prediction. The negative log-likelihood of data points in the test dataset indicates that prediction uncertainties are well-characterized by our model and simulating a sensor failure event results in a dramatic increase in the epistemic component of the uncertainty, as would be expected when a Bayesian method encounters unfamiliar, out-of-distribution inputs.