Detecting the transition to an impending instability is important to initiate effective control in a combustion system. As one of the early applications of characterizing thermoacoustic instability using Deep Neural Networks, we train our proposed deep convolutional neural network (CNN) model on sequential image frames extracted from hi-speed flame videos by inducing instability in the system following a particular protocol — varying the acoustic length. We leverage the sound pressure data to define a non-dimensional instability measure used for applying an inexpensive but noisy labeling technique to train our supervised 2D CNN model. We attempt to detect the onset of instability in a transient dataset where instability is induced by a different protocol. With the continuous variation of the control parameter, we can successfully detect the critical transition to a state of high combustion instability demonstrating the robustness of our proposed detection framework, which is independent of the combustion inducing protocol.
- Dynamic Systems and Control Division
Characterizing Combustion Instability Using Deep Convolutional Neural Network
- Views Icon Views
- Share Icon Share
- Search Site
Gangopadhyay, T, Locurto, A, Boor, P, Michael, JB, & Sarkar, S. "Characterizing Combustion Instability Using Deep Convolutional Neural Network." Proceedings of the ASME 2018 Dynamic Systems and Control Conference. Volume 1: Advances in Control Design Methods; Advances in Nonlinear Control; Advances in Robotics; Assistive and Rehabilitation Robotics; Automotive Dynamics and Emerging Powertrain Technologies; Automotive Systems; Bio Engineering Applications; Bio-Mechatronics and Physical Human Robot Interaction; Biomedical and Neural Systems; Biomedical and Neural Systems Modeling, Diagnostics, and Healthcare. Atlanta, Georgia, USA. September 30–October 3, 2018. V001T13A004. ASME. https://doi.org/10.1115/DSCC2018-9208
Download citation file: