3D convolutional selective autoencoder for instability detection in combustion systems

highlights•A novel semi-supervised deep learning architecture for early detection of combustion instability.•Capturing transition from a stable to an unstable regime using spatiotemporal data (snippets of flame videos).•Demonstration of excellent generalization capability for different operating con...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Energy and AI Jg. 4; S. 100067
Hauptverfasser: Gangopadhyay, Tryambak, Ramanan, Vikram, Akintayo, Adedotun, K Boor, Paige, Sarkar, Soumalya, Chakravarthy, Satyanarayanan R, Sarkar, Soumik
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 01.06.2021
Elsevier
Schlagworte:
3D deep learning
Combustion instability
Convolutional autoencoder
Early detection
Gas turbine engines
Hi-speed video analytics
Instability precursors
Physics-based validation
3D deep learning
Instability precursors
Combustion instability
Hi-speed video analytics
Gas turbine engines
Physics-based validation
Convolutional autoencoder
Early detection
ISSN:2666-5468, 2666-5468
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:highlights•A novel semi-supervised deep learning architecture for early detection of combustion instability.•Capturing transition from a stable to an unstable regime using spatiotemporal data (snippets of flame videos).•Demonstration of excellent generalization capability for different operating conditions.•Verification of the identified precursors of transitions using physics-based understanding. [Display omitted] While analytical solutions of critical (phase) transitions in dynamical systems are abundant for simple nonlinear systems, such analysis remains intractable for real-life dynamical systems. A key example is thermoacoustic instability in combustion, where prediction or early detection of the onset of instability is a hard technical challenge, which needs to be addressed to build safer and more energy-efficient gas turbine engines powering aerospace and energy industries. The instabilities arising in combustion chambers of engines are mathematically too complex to model. To address this issue in a data-driven manner instead, we propose a novel deep learning architecture called 3D convolutional selective autoencoder (3D-CSAE) to detect the evolution of self-excited oscillations using spatiotemporal data, i.e., hi-speed videos taken from a swirl-stabilized combustor (laboratory surrogate of gas turbine engine combustor). 3D-CSAE consists of filters to learn, in a hierarchical fashion, the complex visual and dynamic features related to combustion instability from the training videos (i.e., two spatial dimensions for the image frames and the third dimension for time). We train the 3D-CSAE on frames of videos obtained from a limited set of operating conditions. We select the 3D-CSAE hyper-parameters that are effective for characterizing hierarchical and multiscale instability structure evolution by utilizing the dynamic information available in the video. The proposed model clearly shows performance improvement in detecting the precursors and the onset of instability. The machine learning-driven results are verified with physics-based off-line measures. Advanced active control mechanisms can directly leverage the proposed online detection capability of 3D-CSAE to mitigate the adverse effects of combustion instabilities on the engine operating under various stringent requirements and conditions.
ISSN:2666-5468
2666-5468
DOI:10.1016/j.egyai.2021.100067