This content is not included in your SAE MOBILUS subscription, or you are not logged in.
Development of High Compression-Ratio Stepped-Lip Piston using Machine Learning
ISSN: 0148-7191, e-ISSN: 2688-3627
Published August 30, 2022 by SAE International in United States
Annotation ability available
Interaction between a diesel spray and piston plays a significant role in overall combustion and emissions performance in compression-ignition engines. It is essential to design the lip feature respective to spray targeting and the following charge motion for combustion systems that rely on spray-piston interaction strongly, such as a stepped-lip piston. This study used a numerical campaign using computational fluid dynamics (CFD) simulation to optimize a stepped-lip combustion system at a 22:1 compression ratio (CR) for both performance and emissions. This is a substantial step up in CR from the stock value of 17:1 for the same engine platform.
A machine learning model was used to identify the best combination of features from a design space involving hundreds of potential piston designs and injector nozzle configurations. This study provides a discussion on the general combustion characteristics of the stepped-lip combustion system and the sensitivity of the design parameters. Comparison of the CFD predictions for the final system design and single-cylinder engine (SCE) experimental results showed good agreement for combustion performance and emissions. Further opportunities for improvements to the combustion system are also discussed.
CitationJha, P., Bitsis, C., Smith, E., Briggs, T. et al., "Development of High Compression-Ratio Stepped-Lip Piston using Machine Learning," SAE Technical Paper 2022-01-1054, 2022, https://doi.org/10.4271/2022-01-1054.
- Wu , A. et al. Numerical and Experimental Studies of a Novel Dimpled Stepped-Lip Piston Design on Turbulent Flow Development in a Medium-Duty Diesel Engine SAE International 2022
- Belgiorno , G. et al. Experimental Study of Additive-Manufacturing-Enabled Innovative Diesel Combustion Bowl Features for Achieving Ultra-Low Emissions and High Efficiency SAE International 2020
- Manolas , D.A. et al. Operation Optimization of an Industrial Cogeneration System by a Genetic Algorithm Energy Conversion and Management 38 15-17 1997 1625 1636
- Wong , P.K. et al. Modeling and Optimization of Biodiesel Engine Performance using Kernel-Based Extreme Learning Machine and Cuckoo Search Renewable Energy 74 2015 640 647
- Probst , D.M. et al. 2016
- Moiz , A.A. et al. A Machine Learning-Genetic Algorithm (ML-GA) Approach for Rapid Optimization Using High-Performance Computing SAE International 2018
- Mohan , B. et al. Machine Learning and Response Surface-Based Numerical Optimization of the Combustion System for a Heavy-Duty Gasoline Compression Ignition Engine SAE International 2021
- Badra , J.A. et al. Engine Combustion System Optimization using Computational Fluid Dynamics and Machine Learning: a Methodological Approach Journal of Energy Resources Technology 143 2 2021
- Moiz , A.A. et al. Investigation of Gasoline Compression Ignition in a Heavy-Duty Diesel Engine using Computational Fluid Dynamics SAE Technical Paper 2021-01-0493 2021 https://doi.org/10.4271/2021-01-0493
- 2019 https://www.caeses.com/
- Pei , Y. et al. CFD-Guided Combustion System Optimization of a Gasoline Range Fuel in a Heavy-Duty Compression Ignition Engine Using Automatic Piston Geometry Generation and a Supercomputer SAE International 2019
- Cung , K. et al. Demonstration of High Compression Ratio Combustion Systems for Heavy-Duty Diesel Engine with Improved Efficiency and Lower Emissions SAE International 2022
- Cung , K. et al. Gasoline Compression Ignition (GCI) Combustion of Pump-grade Gasoline Fuel under High Compression Ratio Diesel Engine Transportation Engineering 2021 100066