Adaptive phase shift control of thermoacoustic combustion instabilities using model-free reinforcement learning

Combustion instability is a significant risk in the development of new engines when using novel zero -carbon fuels such as ammonia and hydrogen. These instabilities can be difficult to predict and control, making them a major barrier to the adoption of carbon-free gas turbine technologies. In order to address this challenge, we propose the use of model-free reinforcement learning (RL) to adjust the parameters of a phase-shift controller in a time-varying combustion system. Our proposed algorithm was tested in a simulated time-varying combustion system, where it demonstrated excellent performance compared to other model-free and model-based methods, including extremum seeking controllers and self-tuning regulators. The ability of RL to effectively adjust the parameters of a phase-shift controller in a time -varying system, while also considering the safety implications of online system exploration, makes it a promising tool for mitigating combustion instabilities and enabling the development of safer, more efficient carbon-free gas turbine technologies.(c) 2023 The Combustion Institute. Published by Elsevier Inc. All rights reserved.

Automated summary

Combustion instability is a significant risk in the development of new engines using zero-carbon fuels. In this study, a model-free reinforcement learning algorithm is proposed to adjust the parameters of a phase-shift controller in a time-varying combustion system. The algorithm showed excellent performance in simulations, outperforming other methods. This approach has the potential to mitigate combustion instabilities and facilitate the development of safer and more efficient carbon-free gas turbine technologies.