Applying Physics-Informed Enhanced Super-Resolution Generative Adversarial Networks to Finite-Rate-Chemistry Flows and Predicting Lean Premixed Gas Turbine Combustors
This work addresses the problem of predictive simulations for combustion in gas turbines, which is incremental as it modifies an existing method for a specific bottleneck in reactive flows.
The authors tackled the challenge of accurately predicting small scales in underresolved reactive flows by extending a physics-informed enhanced super-resolution generative adversarial network (PIESRGAN) to finite-rate-chemistry flows, achieving good agreement in laminar lean premixed combustion tests. They also developed a reduced model that solves only major species and uses lookup for others, demonstrating usability in a gas turbine combustor.
The accurate prediction of small scales in underresolved flows is still one of the main challenges in predictive simulations of complex configurations. Over the last few years, data-driven modeling has become popular in many fields as large, often extensively labeled datasets are now available and training of large neural networks has become possible on graphics processing units (GPUs) that speed up the learning process tremendously. In fact, the successful application of deep neural networks in fluid dynamics, such as for underresolved reactive flows, is still challenging. This work advances the recently introduced PIESRGAN to reactive finite-rate-chemistry flows. However, since combustion chemistry typically acts on the smallest scales, the original approach needs to be extended. Therefore, the modeling approach of PIESRGAN is modified to accurately account for the challenges in the context of laminar finite-rate-chemistry flows. The modified PIESRGAN-based model gives good agreement in a priori and a posteriori tests in a laminar lean premixed combustion setup. Furthermore, a reduced PIESRGAN-based model is presented that solves only the major species on a reconstructed field and employs PIERSGAN lookup for the remaining species, utilizing staggering in time. The advantages of the discriminator-supported training are shown, and the usability of the new model demonstrated in the context of a model gas turbine combustor.