Data-driven models and digital twins for sustainable combustion technologies

被引：11

作者：

Parente, Alessandro ^{[1
,2
,3
,4
]}

Swaminathan, Nedunchezhian ^{[5
]}

机构：

[1] Univ Libre Bruxelles, Ecole Polytech Bruxelles, Aerothermo Mech Dept, Ave Franklin D,Roosevelt 50, B-1050 Brussels, Belgium

[2] WEL Res Inst, Ave Pasteur 6, B-1300 Wavre, Belgium

[3] Univ Libre Bruxelles, Brussels Inst Thermal Fluid Syst & Clean Energy B, B-1050 Ixelles, Belgium

[4] Vrije Univ Brussel, B-1050 Ixelles, Belgium

[5] Univ Cambridge, Dept Engn, Hopkinson Lab, Cambridge CB2 1PZ, England

来源：

ISCIENCE | 2024年 / 27卷 / 04期

基金：

英国工程与自然科学研究理事会;

关键词：

PRINCIPAL COMPONENT ANALYSIS; DIRECT NUMERICAL-SIMULATION; GENERATIVE ADVERSARIAL NETWORKS; PROPER ORTHOGONAL DECOMPOSITION; CONVOLUTIONAL NEURAL-NETWORKS; NOX EMISSIONS; TURBULENT; LES; IDENTIFICATION; FRAMEWORK;

D O I：

10.1016/j.isci.2024.109349

中图分类号：

O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];

学科分类号：

07 ; 0710 ; 09 ;

摘要：

We highlight the critical role of data in developing sustainable combustion technologies for industries requiring high -density and localized energy sources. Combustion systems are complex and difficult to predict, and high-fidelity simulations are out of reach for practical systems because of computational cost. Data -driven approaches and artificial intelligence offer promising solutions, enabling renewable synthetic fuels to meet decarbonization goals. We discuss open challenges associated with the availability and fidelity of data, physics -based numerical simulations, and machine learning, focusing on developing digital twins capable of mirroring the behavior of industrial combustion systems and continuously updating based on newly available information.

引用

页数：10