In this work, we have applied a machine learning (ML) technique to provide insights into the underlying causes of cycle-to-cycle variation (CCV) in a gasoline spark-ignited (SI) engine. The analysis was performed on a set of large eddy simulation (LES) calculations of a single cylinder of a four-cylinder port-fueled SI engine. The operating condition studied was stoichiometric, without significant knock, and represents a load of 16 bar brake mean effective pressure (BMEP), at an engine speed of 2500 revolutions per minute. A total of 123 cycles was simulated. Of these, 49 were run in sequence, while 74 were run in a parallel manner. For the parallel approach, each cycle is initialized with its own synthetic turbulent field (through perturbation of the base field) to generate CCV, as part of another work performed by us. In the current work, we post-processed three-dimensional information from all 123 cycles to compute various flame topology and pre-ignition flow-field metrics. We then evaluated correlations between these computed metrics, and peak cylinder pressure (PCP) employing an ML technique called random forest which was used to learn the correlation between PCP, and these flame topology and pre-ignition flow-field metrics. The computed metrics form the inputs to the random forest model developed, and PCP is the predicted output. The random forest model inherently captures the effect of all inputs, as well as interactions between them owing to its decision-tree structure. The goal of this work is to demonstrate (as a first step) that ML models can implicitly learn complex relationships between pre-ignition flow-fields, flame shapes, and the eventual outcome of the cycle (whether a cycle will be a high or a low cycle).
Skip Nav Destination
ASME 2017 Internal Combustion Engine Division Fall Technical Conference
October 15–18, 2017
Seattle, Washington, USA
Conference Sponsors:
- Internal Combustion Engine Division
ISBN:
978-0-7918-5832-5
PROCEEDINGS PAPER
Machine Learning Analysis of Factors Impacting Cycle-to-Cycle Variation in a Gasoline Spark-Ignited Engine Available to Purchase
Janardhan Kodavasal,
Janardhan Kodavasal
Argonne National Laboratory, Argonne, IL
Search for other works by this author on:
Ahmed Abdul Moiz,
Ahmed Abdul Moiz
Argonne National Laboratory, Argonne, IL
Search for other works by this author on:
Muhsin Ameen,
Muhsin Ameen
Argonne National Laboratory, Argonne, IL
Search for other works by this author on:
Sibendu Som
Sibendu Som
Argonne National Laboratory, Argonne, IL
Search for other works by this author on:
Janardhan Kodavasal
Argonne National Laboratory, Argonne, IL
Ahmed Abdul Moiz
Argonne National Laboratory, Argonne, IL
Muhsin Ameen
Argonne National Laboratory, Argonne, IL
Sibendu Som
Argonne National Laboratory, Argonne, IL
Paper No:
ICEF2017-3604, V002T06A020; 10 pages
Published Online:
November 30, 2017
Citation
Kodavasal, J, Moiz, AA, Ameen, M, & Som, S. "Machine Learning Analysis of Factors Impacting Cycle-to-Cycle Variation in a Gasoline Spark-Ignited Engine." Proceedings of the ASME 2017 Internal Combustion Engine Division Fall Technical Conference. Volume 2: Emissions Control Systems; Instrumentation, Controls, and Hybrids; Numerical Simulation; Engine Design and Mechanical Development. Seattle, Washington, USA. October 15–18, 2017. V002T06A020. ASME. https://doi.org/10.1115/ICEF2017-3604
Download citation file:
101
Views
Related Proceedings Papers
Related Articles
Combustion and Performance Evaluation of Methanol (M15)-Fueled BS-VI Compliant Light-Duty Spark-Ignition Engine
ASME Open J. Engineering (January,2023)
Large Eddy Simulation of Lean Mixed-Mode Combustion Assisted by Partial Fuel Stratification in a Spark-Ignition Engine
J. Energy Resour. Technol (July,2021)
Numerical Investigation of the Effect of Knock on Heat Transfer in a Turbocharged Spark Ignition Engine
J. Eng. Gas Turbines Power (December,2015)
Related Chapters
Reciprocating Engine Performance Characteristics
Fundamentals of heat Engines: Reciprocating and Gas Turbine Internal Combustion Engines
Later Single-Cylinder Engines
Air Engines: The History, Science, and Reality of the Perfect Engine
Front Matter
Methodology Used to Update the Gasoline Volatility Schedule for U.S. Seasonal and Geographic Classes