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

Title: Evaluating Optimization Strategies for Engine Simulations Using Machine Learning Emulators

Abstract

This work evaluates different optimization algorithms for computational fluid dynamics (CFD) simulations of engine combustion. Due to the computational expense of CFD simulations, emulators built with machine learning algorithms were used as surrogates for the optimizers. Two types of emulators were used: a Gaussian process (GP) and a weighted variety of machine learning methods called SuperLearner (SL). The emulators were trained using a dataset of 2048 CFD simulations that were run concurrently on a supercomputer. The design of experiments (DOE) for the CFD runs was obtained by perturbing nine input parameters using a Monte-Carlo method. The CFD simulations were of a heavy duty engine running with a low octane gasoline-like fuel at a partially premixed compression ignition mode. Ten optimization algorithms were tested, including types typically used in research applications. Each optimizer was allowed 800 function evaluations and was randomly tested 100 times. The optimizers were evaluated for the median, minimum, and maximum merits obtained in the 100 attempts. Some optimizers required more sequential evaluations, thereby resulting in longer wall clock times to reach an optimum. The best performing optimization methods were particle swarm optimization (PSO), differential evolution (DE), GENOUD (an evolutionary algorithm), and micro-genetic algorithm (GA). These methods foundmore » a high median optimum as well as a reasonable minimum optimum of the 100 trials. Moreover, all of these methods were able to operate with less than 100 successive iterations, which reduced the wall clock time required in practice. Two methods were found to be effective but required a much larger number of successive iterations: the DIRECT and MALSCHAINS algorithms. A random search method that completed in a single iteration performed poorly in finding optimum designs but was included to illustrate the limitation of highly concurrent search methods. The last three methods, Nelder–Mead, bound optimization by quadratic approximation (BOBYQA), and constrained optimization by linear approximation (COBYLA), did not perform as well.« less

Authors:
; ; ; ; ; ; ;
Publication Date:
Research Org.:
Argonne National Lab. (ANL), Argonne, IL (United States)
Sponsoring Org.:
USDOE Office of Energy Efficiency and Renewable Energy (EERE) - Office of Vehicle Technologies (VTO)
OSTI Identifier:
1550800
DOE Contract Number:  
AC02-06CH11357
Resource Type:
Journal Article
Journal Name:
Journal of Engineering for Gas Turbines and Power
Additional Journal Information:
Journal Volume: 141; Journal Issue: 9
Country of Publication:
United States
Language:
English

Citation Formats

Probst, Daniel M., Raju, Mandhapati, Senecal, Peter K., Kodavasal, Janardhan, Pal, Pinaki, Som, Sibendu, Moiz, Ahmed A., and Pei, Yuanjiang. Evaluating Optimization Strategies for Engine Simulations Using Machine Learning Emulators. United States: N. p., 2019. Web. doi:10.1115/1.4043964.
Probst, Daniel M., Raju, Mandhapati, Senecal, Peter K., Kodavasal, Janardhan, Pal, Pinaki, Som, Sibendu, Moiz, Ahmed A., & Pei, Yuanjiang. Evaluating Optimization Strategies for Engine Simulations Using Machine Learning Emulators. United States. https://doi.org/10.1115/1.4043964
Probst, Daniel M., Raju, Mandhapati, Senecal, Peter K., Kodavasal, Janardhan, Pal, Pinaki, Som, Sibendu, Moiz, Ahmed A., and Pei, Yuanjiang. Thu . "Evaluating Optimization Strategies for Engine Simulations Using Machine Learning Emulators". United States. https://doi.org/10.1115/1.4043964.
@article{osti_1550800,
title = {Evaluating Optimization Strategies for Engine Simulations Using Machine Learning Emulators},
author = {Probst, Daniel M. and Raju, Mandhapati and Senecal, Peter K. and Kodavasal, Janardhan and Pal, Pinaki and Som, Sibendu and Moiz, Ahmed A. and Pei, Yuanjiang},
abstractNote = {This work evaluates different optimization algorithms for computational fluid dynamics (CFD) simulations of engine combustion. Due to the computational expense of CFD simulations, emulators built with machine learning algorithms were used as surrogates for the optimizers. Two types of emulators were used: a Gaussian process (GP) and a weighted variety of machine learning methods called SuperLearner (SL). The emulators were trained using a dataset of 2048 CFD simulations that were run concurrently on a supercomputer. The design of experiments (DOE) for the CFD runs was obtained by perturbing nine input parameters using a Monte-Carlo method. The CFD simulations were of a heavy duty engine running with a low octane gasoline-like fuel at a partially premixed compression ignition mode. Ten optimization algorithms were tested, including types typically used in research applications. Each optimizer was allowed 800 function evaluations and was randomly tested 100 times. The optimizers were evaluated for the median, minimum, and maximum merits obtained in the 100 attempts. Some optimizers required more sequential evaluations, thereby resulting in longer wall clock times to reach an optimum. The best performing optimization methods were particle swarm optimization (PSO), differential evolution (DE), GENOUD (an evolutionary algorithm), and micro-genetic algorithm (GA). These methods found a high median optimum as well as a reasonable minimum optimum of the 100 trials. Moreover, all of these methods were able to operate with less than 100 successive iterations, which reduced the wall clock time required in practice. Two methods were found to be effective but required a much larger number of successive iterations: the DIRECT and MALSCHAINS algorithms. A random search method that completed in a single iteration performed poorly in finding optimum designs but was included to illustrate the limitation of highly concurrent search methods. The last three methods, Nelder–Mead, bound optimization by quadratic approximation (BOBYQA), and constrained optimization by linear approximation (COBYLA), did not perform as well.},
doi = {10.1115/1.4043964},
url = {https://www.osti.gov/biblio/1550800}, journal = {Journal of Engineering for Gas Turbines and Power},
number = 9,
volume = 141,
place = {United States},
year = {2019},
month = {6}
}

Works referenced in this record:

Modeling the Effects of In-Cylinder Flows on HSDI Diesel Engine Performance and Emissions
journal, April 2008


Modeling Investigation of Different Methods to Suppress Engine Knock on a Small Spark Ignition Engine
journal, June 2015


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


Fuel reactivity controlled compression ignition (RCCI): a pathway to controlled high-efficiency clean combustion
journal, June 2011


CFD-Guided Heavy Duty Mixing-Controlled Combustion System Optimization with a Gasoline-Like Fuel
journal, March 2017


Optimization of a HSDI Diesel Engine for Passenger Cars Using a Multi-Objective Genetic Algorithm and Multi-Dimensional Modeling
journal, April 2009


GA : A Package for Genetic Algorithms in R
journal, January 2013


Self-Adapting Control Parameters in Differential Evolution: A Comparative Study on Numerical Benchmark Problems
journal, December 2006


Memetic algorithms based on local search chains for large scale continuous optimisation problems: MA-SSW-Chains
journal, September 2010


Memetic Algorithms for Continuous Optimisation Based on Local Search Chains
journal, March 2010


Lipschitzian optimization without the Lipschitz constant
journal, October 1993


A Simplex Method for Function Minimization
journal, January 1965


Enhancement on a Skeletal Kinetic Model for Primary Reference Fuel Oxidation by Using a Semidecoupling Methodology
journal, November 2012


Conventional and Low Temperature Combustion Using Naphtha Fuels in a Multi-Cylinder Heavy-Duty Diesel Engine
journal, April 2016


Numerical Investigation of a Gasoline-Like Fuel in a Heavy-Duty Compression Ignition Engine Using Global Sensitivity Analysis
journal, March 2017


GPfit : An R Package for Fitting a Gaussian Process Model to Deterministic Simulator Outputs
journal, January 2015


A Computationally Stable Approach to Gaussian Process Interpolation of Deterministic Computer Simulation Data
journal, November 2011


Optimization and Uncertainty Analysis of a Diesel Engine Operating Point Using CFD
conference, October 2016