Open AccessProceedings Article10.1115/ICEF2019-7238

Engine Combustion System Optimization Using CFD and Machine Learning: A Methodological Approach

- 09 Dec 2019

TL;DR: The potential of ML-GGA to significantly reduce the time needed for optimization problems, without loss in accuracy compared to traditional approaches is demonstrated.

Abstract: This work has been supported by the Fuel Technology Division at Saudi Aramco R&DC. We would also like to thank Aramco Services Company for their support with the computing cluster at the Aramco Research Center Houston. The submitted manuscript was created partly by UChicago Argonne, LLC, Operator of Argonne National Laboratory. Argonne, a US Department of Energy (DOE) Office of Science laboratory, is operated under Contract No. DE-AC02-06CH11357. This research was partly funded by the US DOE Office of Vehicle Technologies, Office of Energy Efficiency and Renewable Energy under Contract No. DE-AC02-06CH11357. Blues High Performance LCRC cluster facilities at Argonne National Laboratory were used for some of the simulations.

AI Agents for this Paper

Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps

Most frequently asked questions

1. What are the contributions mentioned in the paper "Engine combustion system optimization using cfd and machine learning: a methodological approach" ?

In this work, a Machine Learning-Grid Gradient Algorithm ( ML-GGA ) approach was developed to optimize the performance of internal combustion engines.. Detailed descriptions of the different procedures, optimization tools and criteria that must be followed for a successful output are provided here.. This study demonstrates the potential of ML-GGA to significantly reduce the time needed for optimization problems, without loss in accuracy compared to traditional approaches.

Figure 9. Evolution of the cross-validation error of the Superlearner ML a function of the training data size. 5-fold cross validation error is divided by the number of test designs to get the average 5-fold CV error.

Figure 4. Robustness of the five local optimum designs.

Table 4: Design variables, emissions, fuel consumption, merit values and merit improvements of the best CFD and ML-GGA designs at all operating conditions.

Figure 11. ML-GGA piston bowl geometry optimization scheme.

Figure 5. Top five CFD designs at the four operating conditions (adapted from Ref. [39]).

Figure 6. Piston bowl profile with design parameters.

Citations

Fundamental Concepts In The Design Of Experiments

Leonie Kohl

- 01 Jan 2016

TL;DR: The fundamental concepts in the design of experiments is universally compatible with any devices to read and an online access to it is set as public so you can get it instantly.

...read moreread less

542

Journal Article•10.1016/j.pecs.2021.100967

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

01 Jan 2022

- Progress in Energy and Combustion Scienc...

TL;DR: A critical review of the existing internal combustion engine (ICE) modeling, optimization, diagnosis, and control challenges and the promising state-of-the-art Machine Learning (ML) solutions for them is provided in this paper .

...read moreread less

158

Journal Article•10.1016/J.ENERGY.2021.120331

Towards a comprehensive optimization of engine efficiency and emissions by coupling artificial neural network (ANN) with genetic algorithm (GA)

Yaopeng Li, +4 more

- 15 Jun 2021

- Energy

TL;DR: The ANN-GA method shows the superiority in accuracy, efficiency, expansibility, and flexibility for DDFS strategy optimization, and is promising to integrate ANN with optimization algorithm for further improvements of engine performance.

...read moreread less

120

Proceedings Article•10.4271/2020-01-1313

Combustion System Optimization of a Light-Duty GCI Engine Using CFD and Machine Learning

Jihad Badra, +10 more

- 14 Apr 2020

•Journal Article•10.1016/J.PECS.2021.100967

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

Masoud Aliramezani, +2 more

- 01 Jan 2022

- Progress in Energy and Combustion Scienc...

...read moreread less

...

Expand

References

Monograph•10.1002/9780470172261

Genetic algorithms and engineering optimization

Mitsuo Gen, +1 more

- 17 Dec 1999

TL;DR: This paper presents a meta-modelling framework that automates the very labor-intensive and therefore time-heavy and therefore expensive and labor-heavy process of designing and solving optimization problems.

...read moreread less

2.7K

Journal Article•10.1109/23.589532

Importance of input data normalization for the application of neural networks to complex industrial problems

J. Sola, +1 more

- 01 Jun 1997

- IEEE Transactions on Nuclear Science

TL;DR: It is shown how data normalization affects the performance error of parameter estimators trained to predict the value of several variables of a PWR nuclear power plant.

...read moreread less

825

Fundamental Concepts In The Design Of Experiments

Leonie Kohl

- 01 Jan 2016

TL;DR: The fundamental concepts in the design of experiments is universally compatible with any devices to read and an online access to it is set as public so you can get it instantly.

...read moreread less

542

International Energy Outlook 1996(米エネルギ-情報局)

忠司堀江

- 01 Oct 1996

420

The Outlook for Energy: A View to 2040

Randy Selin

- 01 Jan 2013

TL;DR: In the South East Asia Petroleum Exploration Society (SEAPEX) Conference, Singapore, 2013 as discussed by the authors, the authors presented that the global unconventional gas development will continue and the Asia market growth will dominate however there are still a lot of unknowns.

...read moreread less

394

...

Expand

Engine Combustion System Optimization Using CFD and Machine Learning: A Methodological Approach

Chat with Paper

AI Agents for this Paper

Most frequently asked questions

1. What are the contributions mentioned in the paper "Engine combustion system optimization using cfd and machine learning: a methodological approach" ?

Figures

Citations

Fundamental Concepts In The Design Of Experiments

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

Towards a comprehensive optimization of engine efficiency and emissions by coupling artificial neural network (ANN) with genetic algorithm (GA)

Combustion System Optimization of a Light-Duty GCI Engine Using CFD and Machine Learning

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

References

Genetic algorithms and engineering optimization

Importance of input data normalization for the application of neural networks to complex industrial problems

Fundamental Concepts In The Design Of Experiments

International Energy Outlook 1996(米エネルギ-情報局)

The Outlook for Energy: A View to 2040

Related Papers (5)

A Machine Learning-Genetic Algorithm (ML-GA) Approach for Rapid Optimization Using High-Performance Computing

Exploring the potential of machine learning in reducing the computational time/expense and improving the reliability of engine optimization studies

Combustion System Optimization of a Light-Duty GCI Engine Using CFD and Machine Learning

Scikit-learn: Machine Learning in Python

Evaluating Optimization Strategies for Engine Simulations Using Machine Learning Emulators