skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Using Machine Learning to Analyze Factors Determining Cycle-to-Cycle Variation in a Spark-Ignited Gasoline Engine

Abstract

In this work, we have applied a machine learning (ML) technique to provide insights into the 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 was stoichiometric, without significant knock, at 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 parallel. For the parallel approach, each cycle is initialized with its own synthetic turbulent field to generate CCV, as part of another work performed by us. In the current work, we used 3D information from all 123 cycles to compute flame topology and pre-ignition flow-field metrics. We then evaluated correlations between these metrics, and peak cylinder pressure (PCP) employing an ML technique called random forest. The computed metrics form the inputs to the random forest model, and PCP is the output. This model captures the effect of all inputs, as well as interactions between them owing to its decision-tree structure. The goal ofmore » 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).« less

Authors:
 [1];  [1];  [1];  [1]
  1. Argonne National Lab. (ANL), Argonne, IL (United States)
Publication Date:
Research Org.:
Argonne National Lab. (ANL), Argonne, IL (United States)
Sponsoring Org.:
USDOE Office of Energy Efficiency and Renewable Energy (EERE), Vehicle Technologies Office (EE-3V)
OSTI Identifier:
1487207
Grant/Contract Number:  
AC02-06CH11357
Resource Type:
Accepted Manuscript
Journal Name:
Journal of Energy Resources Technology
Additional Journal Information:
Journal Volume: 140; Journal Issue: 10; Journal ID: ISSN 0195-0738
Publisher:
ASME
Country of Publication:
United States
Language:
English
Subject:
42 ENGINEERING; CFD; Internal Combustion Engine; Machine Learning

Citation Formats

Kodavasal, Janardhan, Abdul Moiz, Ahmed, Ameen, Muhsin, and Som, Sibendu. Using Machine Learning to Analyze Factors Determining Cycle-to-Cycle Variation in a Spark-Ignited Gasoline Engine. United States: N. p., 2018. Web. doi:10.1115/1.4040062.
Kodavasal, Janardhan, Abdul Moiz, Ahmed, Ameen, Muhsin, & Som, Sibendu. Using Machine Learning to Analyze Factors Determining Cycle-to-Cycle Variation in a Spark-Ignited Gasoline Engine. United States. doi:10.1115/1.4040062.
Kodavasal, Janardhan, Abdul Moiz, Ahmed, Ameen, Muhsin, and Som, Sibendu. Tue . "Using Machine Learning to Analyze Factors Determining Cycle-to-Cycle Variation in a Spark-Ignited Gasoline Engine". United States. doi:10.1115/1.4040062. https://www.osti.gov/servlets/purl/1487207.
@article{osti_1487207,
title = {Using Machine Learning to Analyze Factors Determining Cycle-to-Cycle Variation in a Spark-Ignited Gasoline Engine},
author = {Kodavasal, Janardhan and Abdul Moiz, Ahmed and Ameen, Muhsin and Som, Sibendu},
abstractNote = {In this work, we have applied a machine learning (ML) technique to provide insights into the 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 was stoichiometric, without significant knock, at 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 parallel. For the parallel approach, each cycle is initialized with its own synthetic turbulent field to generate CCV, as part of another work performed by us. In the current work, we used 3D information from all 123 cycles to compute flame topology and pre-ignition flow-field metrics. We then evaluated correlations between these metrics, and peak cylinder pressure (PCP) employing an ML technique called random forest. The computed metrics form the inputs to the random forest model, and PCP is the output. This model 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).},
doi = {10.1115/1.4040062},
journal = {Journal of Energy Resources Technology},
number = 10,
volume = 140,
place = {United States},
year = {2018},
month = {5}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 3 works
Citation information provided by
Web of Science

Figures / Tables:

Table 1 Table 1: Engine specifications and operating condition

Save / Share:

Works referenced in this record:

Cylinder Pressure Variations, A Fundamental Combustion Problem
conference, February 1966

  • Patterson, Donald J.
  • 1966 Automotive Engineering Congress and Exposition, SAE Technical Paper Series
  • DOI: 10.4271/660129

A New Support Vector Machine and Artificial Neural Networks for Prediction of Stuck Pipe in Drilling of Oil Fields
journal, April 2014

  • Rostami, Habib; Khaksar Manshad, Abbas
  • Journal of Energy Resources Technology, Vol. 136, Issue 2
  • DOI: 10.1115/1.4026917

LES Simulation of Flame Propagation in a Direct-Injection SI-Engine to Identify the Causes of Cycle-to-Cycle Combustion Variations
conference, April 2013

  • Tatschl, Reinhard; Bogensperger, Michael; Pavlovic, Zoran
  • SAE 2013 World Congress & Exhibition, SAE Technical Paper Series
  • DOI: 10.4271/2013-01-1084

Achieving Stable Engine Operation of Gasoline Compression Ignition Using 87 AKI Gasoline Down to Idle
conference, April 2015

  • Kolodziej, Christopher; Kodavasal, Janardhan; Ciatti, Stephen
  • SAE 2015 World Congress & Exhibition, SAE Technical Paper Series
  • DOI: 10.4271/2015-01-0832

LES Multi-cycle Analysis of a High Performance GDI Engine
conference, April 2013

  • Fontanesi, Stefano; Paltrinieri, Stefano; Tiberi, Alessandro
  • SAE 2013 World Congress & Exhibition, SAE Technical Paper Series
  • DOI: 10.4271/2013-01-1080

Effects of injection parameters, boost, and swirl ratio on gasoline compression ignition operation at idle and low-load conditions
journal, October 2016

  • Kodavasal, Janardhan; Kolodziej, Christopher P.; Ciatti, Stephen A.
  • International Journal of Engine Research, Vol. 18, Issue 8
  • DOI: 10.1177/1468087416675709

Dynamic One-Equation Nonviscosity Large-Eddy Simulation Model
journal, April 2002

  • Pomraning, Eric; Rutland, Christopher J.
  • AIAA Journal, Vol. 40, Issue 4
  • DOI: 10.2514/2.1701

Reaction-space analysis of homogeneous charge compression ignition combustion with varying levels of fuel stratification under positive and negative valve overlap conditions
journal, July 2016

  • Kodavasal, Janardhan; Lavoie, George A.; Assanis, Dennis N.
  • International Journal of Engine Research, Vol. 17, Issue 7
  • DOI: 10.1177/1468087415613208

LES study of cycle-to-cycle variations in a spark ignition engine
journal, January 2011


Cyclic Combustion Variations in Dual Fuel Partially Premixed Pilot-Ignited Natural Gas Engines
journal, September 2013

  • Srinivasan, K. K.; Krishnan, S. R.; Qi, Y.
  • Journal of Energy Resources Technology, Vol. 136, Issue 1
  • DOI: 10.1115/1.4024855

Parallel methodology to capture cyclic variability in motored engines
journal, July 2016

  • Ameen, Muhsin M.; Yang, Xiaofeng; Kuo, Tang-Wei
  • International Journal of Engine Research, Vol. 18, Issue 4
  • DOI: 10.1177/1468087416662544

Computational Fluid Dynamics Simulation of Gasoline Compression Ignition
journal, May 2015

  • Kodavasal, Janardhan; Kolodziej, Christopher P.; Ciatti, Stephen A.
  • Journal of Energy Resources Technology, Vol. 137, Issue 3
  • DOI: 10.1115/1.4029963

Development of a Stiffness-Based Chemistry Load Balancing Scheme, and Optimization of Input/Output and Communication, to Enable Massively Parallel High-Fidelity Internal Combustion Engine Simulations
journal, February 2016

  • Kodavasal, Janardhan; Harms, Kevin; Srivastava, Priyesh
  • Journal of Energy Resources Technology, Vol. 138, Issue 5
  • DOI: 10.1115/1.4032623

Support Vector Regression and Computational Fluid Dynamics Modeling of Newtonian and Non-Newtonian Fluids in Annulus With Pipe Rotation
journal, October 2014

  • Sorgun, Mehmet; Murat Ozbayoglu, A.; Evren Ozbayoglu, M.
  • Journal of Energy Resources Technology, Vol. 137, Issue 3
  • DOI: 10.1115/1.4028694

The effect of diluent composition on homogeneous charge compression ignition auto-ignition and combustion duration
journal, January 2015

  • Kodavasal, Janardhan; Lavoie, George A.; Assanis, Dennis N.
  • Proceedings of the Combustion Institute, Vol. 35, Issue 3
  • DOI: 10.1016/j.proci.2014.06.152

Cyclic Variability in Spark Ignition Engines A Literature Survey
conference, March 1994

  • Ozdor, Nir; Dulger, Mark; Sher, Eran
  • International Congress & Exposition, SAE Technical Paper Series
  • DOI: 10.4271/940987

Towards the understanding of cyclic variability in a spark ignited engine using multi-cycle LES
journal, August 2009


A New Parallel Cut-Cell Cartesian CFD Code for Rapid Grid Generation Applied to In-Cylinder Diesel Engine Simulations
conference, April 2007

  • Senecal, P. K.; Richards, K. J.; Pomraning, E.
  • SAE World Congress & Exhibition, SAE Technical Paper Series
  • DOI: 10.4271/2007-01-0159

LES Multi-Cycle Analysis of the Combustion Process in a Small SI Engine
journal, April 2014

  • Koch, Jann; Schmitt, Martin; Wright, Yuri M.
  • SAE International Journal of Engines, Vol. 7, Issue 1
  • DOI: 10.4271/2014-01-1138

Capturing Cyclic Variability in EGR Dilute SI Combustion Using Multi-Cycle RANS
conference, January 2016

  • Scarcelli, Riccardo; Sevik, James; Wallner, Thomas
  • ASME 2015 Internal Combustion Engine Division Fall Technical Conference, Volume 2: Emissions Control Systems; Instrumentation, Controls, and Hybrids; Numerical Simulation; Engine Design and Mechanical Development
  • DOI: 10.1115/ICEF2015-1045

Effective Prediction and Management of a CO2 Flooding Process for Enhancing Oil Recovery Using Artificial Neural Networks
journal, October 2017

  • Van, Si Le; Chon, Bo Hyun
  • Journal of Energy Resources Technology, Vol. 140, Issue 3
  • DOI: 10.1115/1.4038054

Effect of Retarded Injection Timing on Knock Resistance and Cycle to Cycle Variation in Gasoline Direct Injection Engine
journal, February 2018

  • Zhou, Lei; Shao, Aifang; Hua, Jianxiong
  • Journal of Energy Resources Technology, Vol. 140, Issue 7
  • DOI: 10.1115/1.4039322

Examining the role of flame topologies and in-cylinder flow fields on cyclic variability in spark-ignited engines using large-eddy simulation
journal, September 2017

  • Zhao, Le; Moiz, Ahmed Abdul; Som, Sibendu
  • International Journal of Engine Research, Vol. 19, Issue 8
  • DOI: 10.1177/1468087417732447

Global Sensitivity Analysis of a Gasoline Compression Ignition Engine Simulation with Multiple Targets on an IBM Blue Gene/Q Supercomputer
conference, April 2016

  • Kodavasal, Janardhan; Pei, Yuanjiang; Harms, Kevin
  • SAE 2016 World Congress and Exhibition, SAE Technical Paper Series
  • DOI: 10.4271/2016-01-0602

Structure of High-Pressure Fuel Sprays
conference, February 1987

  • Reitz, Rolf D.; Diwakar, R.
  • SAE International Congress and Exposition, SAE Technical Paper Series
  • DOI: 10.4271/870598

The effects of thermal and compositional stratification on the ignition and duration of homogeneous charge compression ignition combustion
journal, February 2015


An accelerated multi-zone model for engine cycle simulation of homogeneous charge compression ignition combustion
journal, June 2013

  • Kodavasal, Janardhan; McNenly, Matthew J.; Babajimopoulos, Aristotelis
  • International Journal of Engine Research, Vol. 14, Issue 5
  • DOI: 10.1177/1468087413482480

An extended multi-zone combustion model for PCI simulation
journal, December 2011

  • Kodavasal, Janardhan; Keum, SeungHwan; Babajimopoulos, Aristotelis
  • Combustion Theory and Modelling, Vol. 15, Issue 6
  • DOI: 10.1080/13647830.2011.578663

LES Modelling of Spark-Ignition Cycle-to-Cycle Variability on a Highly Downsized DISI Engine
journal, January 2015

  • d'Adamo, Alessandro; Breda, Sebastiano; Fontanesi, Stefano
  • SAE International Journal of Engines, Vol. 8, Issue 5
  • DOI: 10.4271/2015-24-2403

Using large-eddy simulation and multivariate analysis to understand the sources of combustion cyclic variability in a spark-ignition engine
journal, December 2015


Large-Eddy simulation analysis of spark configuration effect on cycle-to-cycle variability of combustion and knock
journal, January 2015

  • Fontanesi, Stefano; d’Adamo, Alessandro; Rutland, Christopher J.
  • International Journal of Engine Research, Vol. 16, Issue 3
  • DOI: 10.1177/1468087414566253

Assessment and Evolutionary Based Multi-Objective Optimization of a Novel Renewable-Based Polygeneration Energy System
journal, June 2016

  • El-Emam, Rami S.; Dincer, Ibrahim
  • Journal of Energy Resources Technology, Vol. 139, Issue 1
  • DOI: 10.1115/1.4033625

Towards Large Eddy Simulation in Internal-Combustion Engines: Simulation of a Compressed Tumble Flow
conference, June 2004

  • Moureau, Vincent; Barton, Iain; Angelberger, Christian
  • 2004 SAE Fuels & Lubricants Meeting & Exhibition, SAE Technical Paper Series
  • DOI: 10.4271/2004-01-1995

Cycle-to-Cycle Variations in Multi-Cycle Engine RANS Simulations
conference, April 2016

  • Scarcelli, Riccardo; Richards, Keith; Pomraning, Eric
  • SAE 2016 World Congress and Exhibition, SAE Technical Paper Series
  • DOI: 10.4271/2016-01-0593

    Works referencing / citing this record:

    Prediction of Cyclic Variability and Knock-Limited Spark Advance in a Spark-Ignition Engine
    journal, April 2019

    • Yue, Zongyu; Edwards, K. Dean; Sluders, C. Scott
    • Journal of Energy Resources Technology, Vol. 141, Issue 10
    • DOI: 10.1115/1.4043393