张天汉
Personal Homepage
Paper
Current location: Home >> Paper
Enforcing physical conservation in neural network surrogate models for complex chemical kinetics
Hits:

DOI number:10.1016/j.combustflame.2025.114105

Journal:Combustion and Flame

Key Words:machine learning; chemical kinetic; conservation law; surrogate model; direct integration

Abstract:The "AI for Science" movement has sparked a paradigm shift toward incorporating fundamental physical understanding into neural networks, moving beyond pure data-driven approaches. In this context, we propose a novel ANN approach with hard physical constraints (ANN-hard) for chemical source term calculations that strictly enforce conservation laws (mass, energy, and element). We compare ANN-hard against two baselines: a conventional ANN and an ANN with soft conservation constraints implemented through loss function optimization (ANN-soft). Our systematic evaluation spans multiple combustion scenarios using H 2 /air mixtures, including zero-dimensional autoignition, one-dimensional premixed laminar flames, two-dimensional triple flames, and outwardly expanding turbulent spherical flames. We further extend validation to dimethyl ether (DME)/air mixtures, demonstrating the models' capabilities in capturing complex combustion chemistry through simulations of premixed laminar flames and penta-branchial flames exhibiting simultaneous cool, warm, and hot flame structures. Our analysis reveals a critical insight: traditional training or testing error metrics can be misleading indicators of ANN performance, as they may mask violations of physical principles. Even small violations in physics can accumulate, leading to significant physical violations and explaining why conventional ANNs often produce non-physical predictions or diverge during long-term continuous evolution. While both ANN-soft and ANN-hard show improved robustness over conventional ANNs, ANN-hard demonstrates superior stability and physical accuracy by preventing error accumulation, all while maintaining computational efficiency with negligible additional cost. These findings underscore the importance of enforcing physical constraints in machine learning models for reliable combustion simulations, contributing to the broader goal of physics-informed artificial intelligence.

Co-author:Junjie Yao,Zheng Chen

First Author:Yuxiao Yi,Tinghao Wang

Indexed by:Journal paper

Correspondence Author:Zhi-Qin John Xu,Tianhan Zhang

Document Type:J

Volume:275

Translation or Not:no

Date of Publication:2025-03-10

Included Journals:SCI

Links to published journals:https://www.sciencedirect.com/science/article/pii/S0010218025001439?via%3Dihub

Attachments:

Personal information

Professor
Supervisor of Doctorate Candidates
Supervisor of Master's Candidates

E-Mail:

Date of Employment:2024-07-10

School/Department:School of Astronautics

Education Level:博士研究生

Gender:Male

Status:Employed

Alma Mater:Princeton University

Discipline:Power Engineering and Engineering Thermophysics
Mathematics
Aeronautical and Astronautical Science and Technology
Computer Science and Technology
Mechanics

You are visitors

The Last Update Time : ..


Copyright © 2022 Beihang University. All rights reserved.
Address: 37 Xueyuan Road, Haidian District, Beijing, P.R. China, 100191.
Tel: +86-10-82317114

MOBILE Version