Abstract

Gasoline compression ignition (GCI) engines are considered an attractive alternative to traditional spark-ignition and diesel engines. In this work, a Machine Learning-Grid Gradient Ascent (ML-GGA) approach was developed to optimize the performance of internal combustion engines. ML offers a pathway to transform complex physical processes that occur in a combustion engine into compact informational processes. The developed ML-GGA model was compared with a recently developed Machine Learning-Genetic Algorithm (ML-GA). Detailed investigations of optimization solver parameters and variable limit extension were performed in the present ML-GGA model to improve the accuracy and robustness of the optimization process. Detailed descriptions of the different procedures, optimization tools, and criteria that must be followed for a successful output are provided here. The developed ML-GGA approach was used to optimize the operating conditions (case 1) and the piston bowl design (case 2) of a heavy-duty diesel engine running on a gasoline fuel with a research octane number (RON) of 80. The ML-GGA approach yielded >2% improvements in the merit function, compared with the optimum obtained from a thorough computational fluid dynamics (CFD) guided system optimization. The predictions from the ML-GGA approach were validated with engine CFD simulations. This study demonstrates the potential of ML-GGA to significantly reduce the time needed for optimization problems, without loss in accuracy compared with traditional approaches.

References

References
1.
ExxonMobil
,
2018
, “Outlook for Energy: A View to 2040,” ExxonMobil, TX, https://corporate.exxonmobil.com/en/energy/energy-outlook, Accessed August 9, 2020.
2.
EIA
,
2018
, “International Energy Outlook 2018,” U.S.Energy Information Administration (EIA), Washington, DC, https://www.eia.gov/outlooks/ieo/, Accessed August 9, 2020.
3.
Kalghatgi
,
G. T.
,
2014
, “
The Outlook for Fuels for Internal Combustion Engines
,”
Int. J. Engine Res.
,
15
(
4
), pp.
383
398
. 10.1177/1468087414526189
4.
Kesgin
,
U.
,
2004
, “
Genetic Algorithm and Artificial Neural Network for Engine Optimisation of Efficiency and NOx Emission
,”
Fuel
,
83
(
7
), pp.
885
895
. 10.1016/j.fuel.2003.10.025
5.
Gen
,
M.
, and
Cheng
,
R.
,
2000
,
Genetic Algorithms and Engineering Optimization
,
John Wiley & Sons
,
Hoboken, NJ
.
6.
Manolas
,
D. A.
,
Frangopoulos
,
C. A.
,
Gialamas
,
T. P.
, and
Tsahalis
,
D. T.
,
1997
, “
Operation Optimization of an Industrial Cogeneration System by a Genetic Algorithm
,”
Energy Convers. Manage.
,
38
(
15–17
), pp.
1625
1636
. 10.1016/S0196-8904(96)00203-8
7.
Wong
,
K. I.
,
Wong
,
P. K.
,
Cheung
,
C. S.
, and
Vong
,
C. M.
,
2013
, “
Modeling and Optimization of Biodiesel Engine Performance Using Advanced Machine Learning Methods
,”
Energy
,
55
, pp.
519
528
. 10.1016/j.energy.2013.03.057
8.
Probst
,
D. M.
,
Senecal
,
P. K.
,
Chien
,
P. Z.
,
Xu
,
M. X.
, and
Leyde
,
B. P.
,
2018
, “
Optimization and Uncertainty Analysis of a Diesel Engine Operating Point Using Computational Fluid Dynamics
,”
ASME J. Eng. Gas Turbines Power
,
140
(
10
), p.
102806
. 10.1115/1.4040006
9.
Zhang
,
Q.
,
Ogren
,
R. M.
, and
Kong
,
S.-C.
,
2016
, “
A Comparative Study of Biodiesel Engine Performance Optimization Using Enhanced Hybrid PSO–GA and Basic GA
,”
Appl. Energy
,
165
, pp.
676
684
. 10.1016/j.apenergy.2015.12.044
10.
Wickman
,
D. D.
,
Senecal
,
P. K.
, and
Reitz
,
R. D.
,
2001
, “Diesel Engine Combustion Chamber Geometry Optimization Using Genetic Algorithms and Multi-Dimensional Spray and Combustion Modeling,” SAE International, No. 01-0547.
11.
Hanson
,
R.
,
Curran
,
S.
,
Wagner
,
R.
,
Kokjohn
,
S.
,
Splitter
,
D.
, and
Reitz
,
R. D.
,
2012
, “
Piston Bowl Optimization for RCCI Combustion in a Light-Duty Multi-Cylinder Engine
,”
SAE Int. J. Engines
,
5
(
2
), pp.
286
299
. 10.4271/2012-01-0380
12.
Bertram
,
A. M.
,
Zhang
,
Q.
, and
Kong
,
S.-C.
,
2016
, “
A Novel Particle Swarm and Genetic Algorithm Hybrid Method for Diesel Engine Performance Optimization
,”
Int. J. Engine Res.
,
17
(
7
), pp.
732
747
. 10.1177/1468087415611031
13.
Shi
,
Y.
, and
Reitz
,
R. D.
,
2010
, “
Optimization of a Heavy-Duty Compression–Ignition Engine Fueled With Diesel and Gasoline-Like Fuels
,”
Fuel
,
89
(
11
), pp.
3416
3430
. 10.1016/j.fuel.2010.02.023
14.
Wu
,
Z.
,
Rutland
,
C. J.
, and
Han
,
Z.
,
2018
, “
Numerical Optimization of Natural Gas and Diesel Dual-Fuel Combustion for a Heavy-Duty Engine Operated at a Medium Load
,”
Int. J. Engine Res.
,
19
(
6
), pp.
682
696
. 10.1177/1468087417729255
15.
He
,
Y.
, and
Rutland
,
C. J.
,
2002
, “Modeling of a Turbocharged DI Diesel Engine Using Artificial Neural Networks,” SAE Technical Paper No. 0148-7191.
16.
He
,
Y.
, and
Rutland
,
C. J.
,
2003
, “Neural Cylinder Model and Its Transient Results,” SAE Technical Paper No. 0148-7191.
17.
Samadani
,
E.
,
Shamekhi
,
A. H.
,
Behroozi
,
M. H.
, and
Chini
,
R.
,
2009
, “
A Method for Pre-Calibration of DI Diesel Engine Emissions and Performance Using Neural Network and Multi-Objective Genetic Algorithm
,”
Iran. J. Chem. Chem. Eng.
,
28
(
4
), pp.
61
70
.
18.
Vaughan
,
A.
, and
Bohac
,
S. V.
,
2013
, “
A Cycle-to-Cycle Method to Predict HCCI Combustion Phasing
,”
ASME 2013 Internal Combustion Engine Division Fall Technical Conference
,
Dearborn, MI
,
Oct. 13–16
,
American Society of Mechanical Engineers
, p.
V001T003A026
.
19.
Krijnsen
,
H. C.
,
van Leeuwen
,
J. C. M.
,
Bakker
,
R.
,
van den Bleek
,
C. M.
, and
Calis
,
H. P. A.
,
2001
, “
Optimum NOx Abatement in Diesel Exhaust Using Inferential Feedforward Reductant Control
,”
Fuel
,
80
(
7
), pp.
1001
1008
. 10.1016/S0016-2361(00)00188-5
20.
Malikopoulos
,
A. A.
,
Assanis
,
D. N.
, and
Papalambros
,
P. Y.
,
2009
, “
Real-Time Self-Learning Optimization of Diesel Engine Calibration
,”
ASME J. Eng. Gas Turbines Power
,
131
(
2
), p.
022803
. 10.1115/1.3019331
21.
de Lucas
,
A.
,
Durán
,
A.
,
Carmona
,
M.
, and
Lapuerta
,
M.
,
2001
, “
Modeling Diesel Particulate Emissions With Neural Networks
,”
Fuel
,
80
(
4
), pp.
539
548
. 10.1016/S0016-2361(00)00111-3
22.
Orfila
,
O.
,
Saint Pierre
,
G.
, and
Messias
,
M.
,
2015
, “
An Android Based Ecodriving Assistance System to Improve Safety and Efficiency of Internal Combustion Engine Passenger Cars
,”
Transp. Res. Part C: Emerg. Technol.
,
58
(Part D), pp.
772
782
. 10.1016/j.trc.2015.04.026
23.
Bergmeir
,
P.
,
Nitsche
,
C.
,
Nonnast
,
J.
,
Bargende
,
M.
,
Antony
,
P.
, and
Keller
,
U.
,
2014
, “
Using Balanced Random Forests on Load Spectrum Data for Classifying Component Failures of a Hybrid Electric Vehicle Fleet
,”
2014 13th International Conference on Machine Learning and Applications
,
Detroit, MI
,
Dec. 3–6
, pp.
397
404
.
24.
Rychetsky
,
M.
,
Ortmann
,
S.
, and
Glesner
,
M.
,
1999
, “
Support Vector Approaches for Engine Knock Detection
,”
Proceedings of the International Joint Conference on Neural Networks (IJCNN'99)
,
Washington, DC
,
July 10–16
, Vol.
962
, pp.
969
974
, Cat. No.99CH36339.
25.
Moiz
,
A.
,
Pal
,
P.
,
Probst
,
D.
, and
Pei
,
Y.
,
2018
, “A Machine Learning-Genetic Algorithm (ML-GA) Approach for Rapid Optimization Using High-Performance Computing,” SAE Technical Paper No. 01-0190.
26.
Polley
,
E. C.
, and
Van Der Laan
,
M. J.
,
2010
, “Super Learner in Prediction”, U.C. Berkeley Division of Biostatistics Working Paper Series, Working Paper 266, https://biostats.bepress.com/ucbbiostat/paper266
27.
Viollet
,
Y.
,
Chang
,
J.
, and
Kalghatgi
,
G.
,
2014
, “
Compression Ratio and Derived Cetane Number Effects on Gasoline Compression Ignition Engine Running With Naphtha Fuels
,”
SAE Int. J. Fuels Lubr.
,
7
(
2
), pp.
412
426
. 10.4271/2014-01-1301
28.
Badra
,
J.
,
Elwardany
,
A.
,
Sim
,
J.
,
Viollet
,
Y.
,
Im
,
H.
, and
Chang
,
J.
,
2016
, “Effects of In-Cylinder Mixing on Low Octane Gasoline Compression Ignition Combustion,” SAE Technical Paper No. 0148-7191.
29.
Badra
,
J. A.
,
Sim
,
J.
,
Elwardany
,
A.
,
Jaasim
,
M.
,
Viollet
,
Y.
,
Chang
,
J.
,
Amer
,
A.
, and
Im
,
H. G.
,
2016
, “
Numerical Simulations of Hollow-Cone Injection and Gasoline Compression Ignition Combustion With Naphtha Fuels
,”
ASME J. Energy Resour. Technol.
,
138
(
5
), p.
052202
. 10.1115/1.4032622
30.
Badra
,
J.
,
Bakor
,
R.
,
AlRamadan
,
A.
,
Almansour
,
M.
,
Sim
,
J.
,
Ahmed
,
A.
,
Viollet
,
Y.
, and
Chang
,
J.
,
2018
, “Standardized Gasoline Compression Ignition Fuels Matrix,” SAE Technical Paper No. 0148-7191.
31.
Zhang
,
Y.
,
Voice
,
A.
,
Tzanetakis
,
T.
,
Traver
,
M.
, and
Cleary
,
D.
,
2016
, “
An Evaluation of Combustion and Emissions Performance With Low Cetane Naphtha Fuels in a Multicylinder Heavy-Duty Diesel Engine
,”
ASME J. Eng. Gas Turbines Power
,
138
(
10
), p.
102805
. 10.1115/1.4032879
32.
Badra
,
J.
,
Viollet
,
Y.
,
Elwardany
,
A.
,
Im
,
H. G.
, and
Chang
,
J.
,
2016
, “
Physical and Chemical Effects of low Octane Gasoline Fuels on Compression Ignition Combustion
,”
Appl. Energy
,
183
, pp.
1197
1208
. 10.1016/j.apenergy.2016.09.060
33.
Chang
,
J.
,
Kalghatgi
,
G.
,
Amer
,
A.
, and
Viollet
,
Y.
,
2012
, “Enabling High Efficiency Direct Injection Engine With Naphtha Fuel Through Partially Premixed Charge Compression Ignition Combustion,” SAE Technical Paper No. 0148-7191.
34.
Chang
,
J.
,
Viollet
,
Y.
,
Alzubail
,
A.
,
Abdul-Manan
,
A. F. N.
, and
Al Arfaj
,
A.
,
2015
, “Octane-on-Demand as an Enabler for Highly Efficient Spark Ignition Engines and Greenhouse Gas Emissions Improvement,” SAE Technical Paper No. 0148-7191.
35.
Chang
,
J.
,
Viollet
,
Y.
,
Amer
,
A.
, and
Kalghatgi
,
G.
,
2013
, “Fuel Economy Potential of Partially Premixed Compression Ignition (PPCI) Combustion With Naphtha Fuel,” SAE Technical Paper No. 0148-7191.
36.
Viollet
,
Y.
,
Abdullah
,
M.
,
Alhajhouje
,
A.
, and
Chang
,
J.
,
2015
, “Characterization of High Efficiency Octane-on-Demand Fuels Requirement in a Modern Spark Ignition Engine With Dual Injection System,” SAE Technical Paper No. 0148-7191.
37.
Atef
,
N.
,
Badra
,
J.
,
Jaasim
,
M.
,
Im
,
H. G.
, and
Sarathy
,
S. M.
,
2018
, “
Numerical Investigation of Injector Geometry Effects on Fuel Stratification in a GCI Engine
,”
Fuel
,
214
, pp.
580
589
. 10.1016/j.fuel.2017.11.036
38.
Badra
,
J. A.
,
Sim
,
J.
,
Viollet
,
Y.
,
Zhang
,
Y.
, and
Chang
,
J.
,
2017
, “
CFD Guided Gasoline Compression Ignition Engine Calibration
,”
ASME 2017 Internal Combustion Engine Division Fall Technical Conference
,
Seattle, WA
,
Oct. 15–18
,
American Society of Mechanical Engineers
, p.
V002T006A012
.
39.
Pei
,
Y.
,
Pal
,
P.
,
Zhang
,
Y.
,
Traver
,
M.
,
Cleary
,
D.
,
Futterer
,
C.
,
Brenner
,
M.
,
Probst
,
D.
, and
Som
,
S.
,
2019
, “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 Technical Paper No. 01-0001.
40.
Polley
,
E.
,
LeDell
,
E.
,
Kennedy
,
C.
,
Lendle
,
S.
, and
van der Laan
,
M.
,
2018
, “Package ‘SuperLearner’,” CRAN, https://mran.microsoft.com/snapshot/2018-03-03/web/packages/SuperLearner/SuperLearner.pdf, Accessed August 9, 2020.
41.
Bergmeir
,
C. N.
,
Molina Cabrera
,
D.
, and
Benítez Sánchez
,
J. M.
,
2016
, “
Memetic Algorithms With Local Search Chains in R: The Rmalschains Package
,”
J. Stat. Soft.
,
75
(
4
), pp.
1
33
. http://hdl.handle.net/10481/45215.
42.
Fritz
,
S.
,
Hötzendorfer
,
H.
, and
Koller
,
M.
,
2014
, “
Design of Experiments in Large Diesel Engine Optimisation
,”
MTZ Ind.
,
4
(
1
), pp.
40
45
. 10.1007/s40353-014-0121-1
43.
Wilson
,
V. H.
,
2012
, “
Optimization of Diesel Engine Parameters Using Taguchi Method and Design of Evolution
,”
J. Braz. Soc. Mech. Sci. Eng.
,
34
(
4
), pp.
423
428
. 10.1590/S1678-58782012000400001
44.
Hicks
,
C. R.
, and
Turner
,
K. V.
,
1999
,
Fundamental Concepts in the Design of Experiments
,
Oxford University Press
,
New York
.
45.
Sola
,
J.
, and
Sevilla
,
J.
,
1997
, “
Importance of Input Data Normalization for the Application of Neural Networks to Complex Industrial Problems
,”
IEEE Trans. Nucl. Sci.
,
44
(
3
), pp.
1464
1468
. 10.1109/23.589532
46.
Saarinen
,
S.
,
Bramley
,
R.
, and
Cybenko
,
G.
,
1993
, “
Ill-Conditioning in Neural Network Training Problems
,”
SIAM J. Sci. Comput.
,
14
(
3
), pp.
693
714
. 10.1137/0914044
You do not currently have access to this content.