A generative adversarial network (GAN) approach to creating synthetic flame images from experimental data

作     者：Anthony Carreon Shivam Barwey Venkat Raman 

作者机构：University of MichiganDepartment of AerospaceAnn ArborMIUSA Argonne Leadership Computing FacilityArgonne National LaboratoryLemontILUSA 

出 版 物：《Energy and AI》 (能源与人工智能(英文))

年 卷 期：2023年第13卷第3期

页      面：14-24页

核心收录：

学科分类：08[工学] 0714[理学-统计学（可授理学、经济学学位）] 0701[理学-数学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Office of Naval Research, ONR, (N00014-21-1-2475) Office of Science, SC, (DE-AC02-06CH11357) Georgia Institute of Technology, GIT 

主　　题：Generative adversarial network Combustion modeling Data-driven modeling 

摘      要：Modern diagnostic tools in turbulent combustion allow for highly-resolved measurements of reacting flows;however,they tend to generate massive data-sets,rendering conventional analysis intractable and inefficient.To alleviate this problem,machine learning tools may be used to,for example,discover features from the data for downstream modeling and prediction tasks.To this end,this work applies generative adversarial networks(GANs)to generate realistic flame images based on a time-resolved data set of hydroxide concentration snapshots obtained from planar laser induced fluorescence measurements of a model combustor.The generative model is able to generate flames in attached,lifted,and intermediate configurations dictated by the user.Using𝑙-means clustering and proper orthogonal decomposition,the synthetic image set produced by the GAN is shown to be visually similar to the real image set,with recirculation zones and burned/unburned regions clearly present,indicating good GAN performance in capturing the experimental data statistical structure.Combined with techniques for controlling the configuration of generated flames,this work opens new avenues towards tractable statistical analysis and modeling of flame behavior,as well as rapid and inexpensive flame data generation.