Physics-trained neural network for sparse-view volumetric laser absorption imaging of species and temperature in reacting flows.

A deep learning method for laser absorption tomography was developed to effectively integrate physical priors related to flow-field thermochemistry and transport. Mid-fidelity reacting flow simulations were coupled with a forward molecular absorption model to train a deep neural network that performs the tomographic inversion of laser absorption images to predict temperature and species fields in flames. The method was evaluated through numerical simulation and experimental testing in benchtop laminar flames. The target flow-fields involved a spatially-convolved laminar ethylene-flame doublet, backlit with tunable radiation from a quantum cascade laser near 4.85 µm probing rovibrational absorption transitions of carbon monoxide. 2D images were collected at 11 different projection angles, yielding an aggregate of 50,688 unique lines of sight capturing the scene with a pixel resolution of approximately 70 µm. A convolutional neural network was introduced to efficiently generate temperature and species profiles and trained with a large dataset of large-eddy simulations of laminar flames at variable conditions. The learning-based approach to the inversion problem was found to more accurately predict species and temperature fields of the flame with fewer projection angles, reduce convergence time, and expand the field domain relative to classical linear tomography.

Deep neural network inversion for 3D laser absorption imaging of methane in reacting flows.

Mid-infrared laser absorption imaging of methane in flames is performed with a learning-based approach to the limited view-angle inversion problem. A deep neural network is trained with superimposed Gaussian field distributions of spectral absorption coefficients, and the prediction capability is compared to linear tomography methods at a varying number of view angles for simulated fields representative of a flame pair. Experimental 3D imaging is demonstrated on a methane-oxygen laminar flame doublet (${\lt}\text{cm}$

Time-resolved laser absorption imaging of ethane at 2 kHz in unsteady partially premixed flames.

In this work, laser absorption imaging is expanded in temporal resolution capability to kilohertz measurement rates by coupling sparsely sampled wavelength scanning and digital image postprocessing for diffraction correction. The setup employs an interband cascade laser near 3.34 µm to backlight an unsteady flame for species-specific 2D imaging of ethane (C2H6) with a high-speed infrared camera. Injection-current laser tuning is achieved with a high-duty-cycle square wave that involves a sparse number of data samples per scan to recover an integrated absorbance area for the target ethane feature, thereby minimizing the number of camera frames needed. In conjunction, an image-by-image computational diffraction pattern removal scheme is employed based on inverse Fourier transformations with the aim to reject high spatial frequencies associated with diffraction while preserving spatial resolution of the flow field, without averaging in time. These methods are applied to achieve species-specific 2D cinematography of ethane absorption in an unsteady partially premixed flame with a spatial resolution of ∼415 µm and a temporal resolution of 2 kHz.