Dimensionality Reduction and Dynamical Mode Recognition of Circular Arrays of Flame Oscillators Using Deep Neural Network

Abstract

Oscillatory combustion in aero engines and modern gas turbines often has significant adverse effects on their operation, and accurately recognizing various oscillation modes is the prerequisite for understanding and controlling combustion instability. However, the high-dimensional spatial-temporal data of a complex combustion system typically poses considerable challenges to the dynamical mode recognition. Based on a two-layer bidirectional long short-term memory variational autoencoder (Bi-LSTM-VAE) dimensionality reduction model and a two-dimensional Wasserstein distance-based classifier (WDC), this study proposes a promising method (Bi-LSTM-VAE-WDC) for recognizing dynamical modes in oscillatory combustion systems. Specifically, the Bi-LSTM-VAE dimension reduction model was introduced to reduce the high-dimensional spatial-temporal data of the combustion system to a low-dimensional phase space; Gaussian kernel density estimates (GKDE) were computed based on the distribution of phase points in a grid; two-dimensional WD values were calculated from the GKDE maps to recognize the oscillation modes. The time-series data used in this study were obtained from numerical simulations of circular arrays of laminar flame oscillators. The results show that the novel Bi-LSTM-VAE method can produce a non-overlapping distribution of phase points, indicating an effective unsupervised mode recognition and classification. Furthermore, the present method exhibits a more prominent performance than VAE and PCA (principal component analysis) for distinguishing dynamical modes in complex flame systems, implying its potential in studying turbulent combustion.

arXiv commentresearch paper (18 pages, 1 table 10 figures) with supplementary material (8 pages, 1 table, 5 figures)

References in corpus (14)

• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• Statistical Aspects of Wasserstein Distances
• Latent Variable Models in the Era of Industrial Big Data: Extension and Beyond
• Learning physics-based reduced-order models for a single-injector combustion process
• Flickering of buoyant diffusion flames: a vortex dynamics revisit
• Vortex-dynamical Interpretation of Anti-phase and In-phase Flickering of Dual Buoyant Diffusion Flames
• Diffusion-flame flickering as a hydrodynamic global mode
• Velocity Reconstruction in Puffing Pool Fires with Physics-Informed Neural Networks
• Dynamical Mode Recognition of Triple Flickering Buoyant Diffusion Flames: from Physical Space to Phase Space and to Wasserstein Space
• Vortex Interaction in Triple Flickering Buoyant Diffusion Flames
• Flickering Buoyant Diffusion Flames in Weakly Rotatory Flows
• Dynamics of Minimal Networks of Limit Cycle Oscillators
• Dynamical Mode Recognition of Coupled Flame Oscillators by Supervised and Unsupervised Learning Approaches
• Computational Identification and Stuart-Landau Modeling of Collective Dynamical Behaviors of Octuple Laminar Diffusion Flame Oscillators