[HTML][HTML] Global reaction neural networks with embedded stoichiometry and thermodynamics for learning kinetics from reactor data

T Kircher, FA Döppel, M Votsmeier - Chemical Engineering Journal, 2024 - Elsevier
The digitalization of chemical research and industry is vastly increasing the available data
for developing and parametrizing kinetic models. To exploit this data, machine learning …

Reinforcement Learning for Submodel Assignment in Adaptive Modeling of Turbulent Flames

T Yang, Y Yin, Q Liu, T Yu, Y Wang, H Zhou, Z Ren - AIAA Journal, 2024 - arc.aiaa.org
Reinforcement learning (RL), an unsupervised machine learning approach, is innovatively
introduced to turbulent combustion modeling and demonstrated through the automated …

An extended neural ordinary differential equation network with grey system and its applications

F Zhang, X Xiao, M Gao - Neurocomputing, 2024 - Elsevier
The neural ordinary differential equation (NODE) has attracted much attention for its
applicability in dynamic system modeling and continuous time series analysis. When the …

Artificial intelligence as a catalyst for combustion science and engineering

M Ihme, WT Chung - Proceedings of the Combustion Institute, 2024 - Elsevier
Combustion and energy conversion play critical roles in all facets of environmental and
technological applications, including the utilization of sustainable energy sources for power …

Model-optimization-guided neural network (MOGNN) applied to chemical processes

FMF Siqueira, L de Sousa Santos - Applied Soft Computing, 2024 - Elsevier
In this work, a Model-Optimization-guided Neural Network (MOGNN) is proposed to optimize
chemical processes. The model is trained with pre-selected process data, resulting from …

FlamePINN-1D: Physics-informed neural networks to solve forward and inverse problems of 1D laminar flames

J Wu, S Zhang, Y Wu, G Zhang, X Li… - arXiv preprint arXiv …, 2024 - arxiv.org
Given the existence of various forward and inverse problems in combustion studies and
applications that necessitate distinct methods for resolution, a framework to solve them in a …

A neural network with embedded stoichiometry and thermodynamics for learning kinetics from reactor data

T Kircher, F Döppel, M Votsmeier - 2023 - chemrxiv.org
The digitalization of chemical research and industry is vastly increasing the available data
for developing and parametrizing kinetic models. To exploit this data, machine learning …

Investigations into the Combustion Interactions of Biofuels and the Optimization of Biomethane Production

L Ji - 2024 - search.proquest.com
The urgent need to address the shortage of fossil fuels and mitigate environmental impacts
from carbon emissions and greenhouse gases necessitates the exploration of renewable …

Data ecosystems and data science for scientific data

E RAMALLI - 2023 - politesi.polimi.it
Predictive models have a pervasive role in many daily applications. The increasing amount
of generated and shared data has recently boosted their development, shifting the model …

Physics-Enhanced Machine Learning for Chemical Kinetics

FA Döppel - tuprints.ulb.tu-darmstadt.de
The energy transition and the transformation of the chemical industry are major efforts in
addressing the challenges of climate change. Both require the development of new and …