Detection of precursors of combustion instability using convolutional recurrent neural networks

Many combustors are prone to Thermoacoustic Instabilities (TAI). Being able to avoid TAI is mandatory to efficiently operate a system without sacrificing neither performance nor safety. Based on Deep Learning techniques, and more specifically Convolutional Recurrent Neural Networks (CRNN) 1 , this study presents a tool able to detect and translate precursors of TAI in a swirled combustor for different fuel injection strategies. The tool is trained to use only time-series recorded by a few sensors in stable conditions to predict the proximity of unstable operating points on a mass flow rate / equivalence ratio operating map, offering a real-time information on the margin of the system versus TAI. This allows to change operating conditions, and detect the directions to avoid in order to remain in the stable domain. (c) 2021 The Combustion Institute. Published by Elsevier Inc. All rights reserved.

Automated summary

This study introduces a tool based on Deep Learning techniques to detect and translate TAI precursors in a swirled combustor for different fuel injection strategies. The tool offers real-time information on the system's margin versus TAI and allows for adjustments in operating conditions to avoid instability.