60283 - Bayesian Neural Networks Trained on Dynamic Pressure Information to Improve Prediction of the Onset of Combustion Instability 

Many combustion systems become thermoacoustically unstable around certain operating conditions. The exact onset condition is uncertain because of stochasticity, such as turbulent combustion, and the influence of hidden variables, such as un-measured wall temperatures or differences in geometry within manufacturing tolerances. Practical systems tend to be more elaborate than laboratory systems and tend to have less instrumentation, meaning that they suffer more from uncertainty induced by hidden variables. In many commercial systems, the only direct measurement of the combustor comes from a dynamic pressure sensor. In this study we train a Bayesian Neural Network (BNN) to predict the probability of onset of thermoacoustic instability at various times in the future, using only dynamic pressure measurements and the current operating condition. We show that, on a practical system, the error in the onset time predicted by the BNNs is less than half of the error when using the operating condition alone and more informative than the warning provided by commonly used precursor detection methods. This is demonstrated on two systems: (i) a premixed hydrogen/methane annular combustor, where the hidden variables are wall temperatures that depend on the rate of change of operating condition, and (ii) full scale gas turbines, where the hidden variables arise from differences between the engines.