Uploaded by Talha Naseer

Abstract by Bilal,Talha and Hajira

advertisement
PREDICTION OF THERMOACOUSTIC INSTABILITIES IN AN ELECTRICALLY
HEATED RIJKE TUBE WITH MACHINE LEARNING
Muhammad Bilal, Talha Naseer Abbasi, Hajira Anwar
Department of Aeronautics and Astronautics
Institute of Space Technology
ranabilal2024@gmail.com, talhanaseer8@gmailc.com
hajiraanwar11@gmail.com
Abstract: Thermoacoustic instability states the phenomenon that arises in combustion systems
due to the coupling between heat release and acoustic waves that leads to the self-excited
oscillations. These instabilities are significant in numerous thermal devices like gas turbines,
rocket engines and industrial furnaces may induce severe thermomechanical stresses in structural
components of combustors, which often lead to performance degradation and even system failures.
From this perspective, it is important to identify operating conditions which can potentially lead
to thermoacoustic instabilities. In this regard, data-driven approaches have shown considerable
success in predicting the instability map as a function of operating conditions. However, often the
available data are limited to learn such a relationship efficiently in a data-driven approach for a
practical combustion system. A Rijke Tube is a simple and inexpensive experimental setup,
designed and developed for research and to study the fundamental mechanism of thermoacoustic
instability. Deep neural network trained on relatively inexpensive experiments on this electrically
heated Rijke tube has been adapted to predict the unstable operating conditions. The knowledge
transfer from the electrically heated Rijke tube apparatus helps in formulating an accurate datadriven surrogate model for predicting the unstable operating conditions in combustion systems.
Keywords: Acoustics Instabilities, Limited data, Rijke Tube, neural network.
Specialized Tools: Pressure sensors, Thermocouples, Microphone, Arduino, Rotameter, Python
language.
Project Supervisor: Mr. / Dr Ihtizaz Qamar
Download