The mechanisms leading to blowoff were investigated numerically by analyzing bluff body stabilized flame at two conditions: a condition far from blowoff to a condition just prior to blowoff. Large eddy simulations have been used to capture the time dependent, three-dimensional evolution of the field. The results were first validated to available experimental data, showing very good agreement for the flow and overall good agreement for the flame. Changes in the large-scale structures are investigated by means of proper orthogonal decomposition and the wavelet method, elucidating the underlying dynamics of the complex flow-flame interaction of a flame approaching blowoff. Our results reveal that, when the flame approaches blowoff conditions, significant changes are found in the large-scale structures responsible for entrainment of species into the recirculation zone located downstream of the bluff body. Possible causes of this shift in large-scale structures are also discussed, which may be useful for extending the blowoff limits of bluff body stabilized burners.
This study investigates the application of machine learning, specifically Fourier neural operator (FNO) and convolutional neural network (CNN), to learn time-advancement operators for parametric partial differential equations (PDEs). Our focus is on extending existing operator learning methods to handle additional inputs representing PDE parameters. The goal is to create a unified learning approach that accurately predicts short-term solutions and provides robust long-term statistics under diverse parameter conditions, facilitating computational cost savings and accelerating development in engineering simulations. We develop and compare parametric learning methods based on FNO and CNN, evaluating their effectiveness in learning parametric-dependent solution time-advancement operators for one-dimensional PDEs and realistic flame front evolution data obtained from direct numerical simulations of the Navier–Stokes equations.
Predicting the evolution of complex systems governed by partial differential equations remains challenging, especially for nonlinear, chaotic behaviors. This study introduces Koopman-inspired Fourier neural operators and convolutional neural networks to learn solution advancement operators for flame front instabilities. By transforming data into a high-dimensional latent space, these models achieve more accurate multi-step predictions compared to traditional methods. Benchmarking across one- and two-dimensional flame front scenarios demonstrates the proposed approaches' superior performance in short-term accuracy and long-term statistical reproduction, offering a promising framework for modeling complex dynamical systems.
Recent advancements in the integration of artificial intelligence (AI) and machine learning (ML) with physical sciences have led to significant progress in addressing complex phenomena governed by nonlinear partial differential equations (PDEs). This paper explores the application of novel operator learning methodologies to unravel the intricate dynamics of flame instability, particularly focusing on hybrid instabilities arising from the coexistence of Darrieus–Landau (DL) and Diffusive–Thermal (DT) mechanisms. Training datasets encompass a wide range of parameter configurations, enabling the learning of parametric solution advancement operators using techniques such as parametric Fourier Neural Operator (pFNO) and parametric convolutional neural networks (pCNNs). Results demonstrate the efficacy of these methods in accurately predicting short-term and long-term flame evolution across diverse parameter regimes, capturing the characteristic behaviors of pure and blended instabilities. Comparative analyses reveal pFNO as the most accurate model for learning short-term solutions, while all models exhibit robust performance in capturing the nuanced dynamics of flame evolution. This research contributes to the development of robust modeling frameworks for understanding and controlling complex physical processes governed by nonlinear PDEs.