4.7 Article

Laminar Flame Speed modeling for Low Carbon Fuels using methods of Machine Learning

Related references

Note: Only part of the references are listed.
Article Thermodynamics

Physical-oriented and machine learning-based emission modeling in a diesel compression ignition engine: Dimensionality reduction and regression

Aran Mohammad et al.

Summary: The development of engine-out emission models for internal combustion engines is essential for meeting exhaust gas emissions legislation and improving performance. This study utilizes data-driven methods to select and extract relevant features, and applies support vector machine and neural network for emission modeling. The results demonstrate that the features selected using the lasso algorithm provide more accurate predictions compared to those extracted through principal component analysis and factor analysis.

INTERNATIONAL JOURNAL OF ENGINE RESEARCH (2023)

Article Energy & Fuels

Optimization of low carbon fuels operation on a CI engine under a simplified driving cycle for transportation de-fossilization

Antonio F. Garcia et al.

Summary: The current focus of internal combustion engine research is on reducing pollutant emissions while maintaining or improving efficiency and fuel consumption. Studying low carbon fuels (LCF) as an alternative seems promising, but testing a fuel with different properties requires significant resources. To address this issue, a cycle simplification methodology is proposed in this study to evaluate the homologation potential of the studied fuel.
Review Thermodynamics

Modeling, diagnostics, optimization, and control of internal combustion engines via modern machine learning techniques: A review and future directions

Masoud Aliramezani et al.

Summary: This paper provides a critical review of challenges in Internal Combustion Engine (ICE) modeling, optimization, diagnosis, and control, and discusses promising Machine Learning (ML) solutions. Major challenges include RDE modeling and control, combustion knock detection and control, and combustion mode transition in multi-mode engines. ML approaches are categorized into unsupervised, supervised, and reinforcement learning to address these challenges.

PROGRESS IN ENERGY AND COMBUSTION SCIENCE (2022)

Article Automation & Control Systems

Deep learning based model predictive control for compression ignition engines

Armin Norouzi et al.

Summary: In this paper, machine learning and a nonlinear model predictive controller are applied to minimize emissions and fuel consumption of a compression ignition engine. Machine learning is used to identify a model for predictive control optimization and to learn the optimal control action by mimicking the behavior of the predictive controller. A deep recurrent neural network with LSTM layers is used to model the engine, and a deep learning scheme is used to clone the behavior of the developed controller. Results show significant reduction in NO???? emissions and slight decrease in fuel quantity with improved computation time.

CONTROL ENGINEERING PRACTICE (2022)

Article Thermodynamics

An experimental and modeling study of ammonia with enriched oxygen content and ammonia/hydrogen laminar flame speed at elevated pressure and temperature

Krishna Prasad Shrestha et al.

Summary: This study experimentally investigated the laminar flame speeds of ammonia and ammonia-hydrogen blends under different temperature, pressure, and oxygen content conditions, and developed a new kinetic model for predicting the oxidation mechanisms, considering the formation and reduction of nitrogen oxides. The results showed that the laminar flame speed increases with increasing initial temperature, fuel hydrogen content, or oxidizer oxygen content, but decreases with increasing initial pressure. The proposed kinetic model predicts the same trends as experiments and highlights the importance of N2H2 formation under rich conditions.

PROCEEDINGS OF THE COMBUSTION INSTITUTE (2021)

Article Thermodynamics

Exploring the fuel structure dependence of laminar burning velocity: A machine learning based group contribution approach

Florian vom Lehn et al.

Summary: The study developed a quantitative structure-property relationship model to predict the laminar burning velocities (LBVs) of a wide range of fuels, with a mean absolute error of 3.3 cm/s. Results show that unsaturation increases LBV, while methyl substitution consistently has a negative effect within the considered range of fuel structures.

COMBUSTION AND FLAME (2021)

Article Energy & Fuels

Hybrid Machine Learning Approaches and a Systematic Model Selection Process for Predicting Soot Emissions in Compression Ignition Engines

Saeid Shahpouri et al.

Summary: This study presents a comprehensive analysis of diesel engine soot emissions modeling for control applications, including the development of physical, black-box, and gray-box models, as well as testing different feature sets and machine learning methods. The black-box model consisting of GPR with feature selection by LASSO showed the best performance with a test R-2 of 0.96, while the best gray-box model consisted of an SVM-based method with physical insight feature set along with LASSO for feature selection with a test R-2 of 0.97.

ENERGIES (2021)

Article Energy & Fuels

New Combustion Modelling Approach for Methane-Hydrogen Fueled Engines Using Machine Learning and Engine Virtualization

Santiago Molina et al.

Summary: The achievement of a carbon-free emissions economy is a main goal to reduce climate change, with transportation being the main contributor of emissions. This necessitates evaluating alternative fuels, with hydrogen being a possible solution, but drawbacks exist. Consideration of dual-fuel strategies, involving mixing different fuels, is also important.

ENERGIES (2021)

Article Thermodynamics

Numerical study on the influence of gasoline properties and thermodynamic conditions on premixed laminar flame velocity at multiple conditions

Yong Wang et al.

Summary: This paper investigates the effects of two key gasoline properties on laminar flame velocity, using a hybrid computation method combining flame kinetics model and machine learning algorithms. Results show all ML models perform well on the test set, especially the GBDT algorithm.

ENERGY (2021)

Proceedings Paper Automation & Control Systems

Soot Emission Modeling of a Compression Ignition Engine Using Machine Learning

Saeid Shahpouri et al.

Summary: This paper introduces an innovative modeling approach that combines a physics-based model and a black-box model to predict soot emissions from a diesel engine under varying load and speed conditions. The study shows that, in most cases, grey-box models outperform black-box models, but this difference becomes negligible when a single hidden layer neural network is used.

IFAC PAPERSONLINE (2021)

Review Chemistry, Physical

A review of ammonia as a compression ignition engine fuel

Pavlos Dimitriou et al.

INTERNATIONAL JOURNAL OF HYDROGEN ENERGY (2020)

Article Chemistry, Analytical

A grey-box machine learning based model of an electrochemical gas sensor

Masoud Aliramezani et al.

SENSORS AND ACTUATORS B-CHEMICAL (2020)

Article Green & Sustainable Science & Technology

Nitrogen oxides reduction and performance enhancement of combustor with direct water injection and humidification of inlet air

Saeid Shahpouri et al.

CLEAN TECHNOLOGIES AND ENVIRONMENTAL POLICY (2019)

Review Thermodynamics

Methanol as a fuel for internal combustion engines

Sebastian Verhelst et al.

PROGRESS IN ENERGY AND COMBUSTION SCIENCE (2019)

Article Chemistry, Physical

Chemical kinetic modeling of ammonia oxidation with improved reaction mechanism for ammonia/air and ammonia/hydrogen/air combustion

Junichiro Otomo et al.

INTERNATIONAL JOURNAL OF HYDROGEN ENERGY (2018)

Article Energy & Fuels

Reduced Kinetic Mechanism for Methanol Combustion in Spark-Ignition Engines

Christoffer Pichler et al.

ENERGY & FUELS (2018)

Review Chemistry, Physical

A review of hydrogen as a compression ignition engine fuel

Pavlos Dimitriou et al.

INTERNATIONAL JOURNAL OF HYDROGEN ENERGY (2017)

Review Thermodynamics

Advances and challenges in laminar flame experiments and implications for combustion chemistry

F. N. Egolfopoulos et al.

PROGRESS IN ENERGY AND COMBUSTION SCIENCE (2014)

Article Energy & Fuels

Influence of water vapour and tar compound on laminar flame speed of gasified biomass gas

Nur Farizan Munajat et al.

APPLIED ENERGY (2012)