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.
Skip Nav Destination
Article navigation
September 2019
Research-Article
Evaluating Optimization Strategies for Engine Simulations Using Machine Learning Emulators
Daniel M. Probst,
Daniel M. Probst
Convergence Science, Inc.,
Madison, WI 53719
Madison, WI 53719
Search for other works by this author on:
Mandhapati Raju,
Mandhapati Raju
Convergent Science, Inc.,
Madison, WI 53719
Madison, WI 53719
Search for other works by this author on:
Peter K. Senecal,
Peter K. Senecal
Convergence Science, Inc.,
Madison, WI 53719
Madison, WI 53719
Search for other works by this author on:
Janardhan Kodavasal,
Janardhan Kodavasal
Argonne National Laboratory,
Argonne, IL 60439
Argonne, IL 60439
Search for other works by this author on:
Pinaki Pal,
Pinaki Pal
Argonne National Laboratory,
Argonne, IL 60439
Argonne, IL 60439
Search for other works by this author on:
Sibendu Som,
Sibendu Som
Argonne National Laboratory,
Argonne, IL 60439
Argonne, IL 60439
Search for other works by this author on:
Ahmed A. Moiz,
Ahmed A. Moiz
Argonne National Laboratory,
Argonne, IL 60439
Argonne, IL 60439
Search for other works by this author on:
Yuanjiang Pei
Yuanjiang Pei
Aramco Research Center,
Detroit, MI 48377
Detroit, MI 48377
Search for other works by this author on:
Daniel M. Probst
Convergence Science, Inc.,
Madison, WI 53719
Madison, WI 53719
Mandhapati Raju
Convergent Science, Inc.,
Madison, WI 53719
Madison, WI 53719
Peter K. Senecal
Convergence Science, Inc.,
Madison, WI 53719
Madison, WI 53719
Janardhan Kodavasal
Argonne National Laboratory,
Argonne, IL 60439
Argonne, IL 60439
Pinaki Pal
Argonne National Laboratory,
Argonne, IL 60439
Argonne, IL 60439
Sibendu Som
Argonne National Laboratory,
Argonne, IL 60439
Argonne, IL 60439
Ahmed A. Moiz
Argonne National Laboratory,
Argonne, IL 60439
Argonne, IL 60439
Yuanjiang Pei
Aramco Research Center,
Detroit, MI 48377
Detroit, MI 48377
Manuscript received April 25, 2019; final manuscript received May 30, 2019; published online June 20, 2019. Editor: Jerzy T. Sawicki.
J. Eng. Gas Turbines Power. Sep 2019, 141(9): 091011 (9 pages)
Published Online: June 20, 2019
Article history
Received:
April 25, 2019
Revised:
May 30, 2019
Citation
Probst, D. M., Raju, M., Senecal, P. K., Kodavasal, J., Pal, P., Som, S., Moiz, A. A., and Pei, Y. (June 20, 2019). "Evaluating Optimization Strategies for Engine Simulations Using Machine Learning Emulators." ASME. J. Eng. Gas Turbines Power. September 2019; 141(9): 091011. https://doi.org/10.1115/1.4043964
Download citation file:
Get Email Alerts
Operation of a Compression Ignition Engine at Idling Load Under Simulated Cold Weather Conditions
J. Eng. Gas Turbines Power (August 2025)
In-Cylinder Imaging and Emissions Measurements of Cold-Start Split Injection Strategies
J. Eng. Gas Turbines Power (August 2025)
Effects of Lattice Orientation Angle on TPMS-Based Transpiration Cooling
J. Eng. Gas Turbines Power (September 2025)
Compressor Development for CO2-Based Pumped Thermal Energy Storage Systems
J. Eng. Gas Turbines Power (September 2025)
Related Articles
Engine Combustion System Optimization Using Computational Fluid Dynamics and Machine Learning: A Methodological Approach
J. Energy Resour. Technol (February,2021)
Design and Performance Analyses of Evacuated U-Tube Solar Collector Using Data-Driven Machine Learning Models
J. Sol. Energy Eng (February,2023)
Machine Learning-Based Reverse Modeling Approach for Rapid Tool Shape Optimization in Die-Sinking Micro Electro Discharge Machining
J. Comput. Inf. Sci. Eng (June,2020)
Using Machine Learning to Predict Core Sizes of High-Efficiency Turbofan Engines
J. Eng. Gas Turbines Power (November,2019)
Related Proceedings Papers
Related Chapters
Fuzzy-Based Firefly Algotithm for Data Clustering
International Conference on Computer Research and Development, 5th (ICCRD 2013)
Regression of Representative Keys for Classification: A Simple Learning Approach
Intelligent Engineering Systems through Artificial Neural Networks
An Algorithm Implementation about SVR Based on Spider
International Symposium on Information Engineering and Electronic Commerce, 3rd (IEEC 2011)