Abstract

Supervised machine learning is used to classify a continuous and deterministic design space into a nondominated Pareto frontier and dominated design points. The effect of the initial training data quantity on the Pareto frontier and output parameter sensitivity is explored. The study is performed with the optimization of a subsonic small-scale cavity-stabilized combustor. A 3D geometry is created and parameterized using computer aided design (CAD) that is combined with a software for meshing, which automatically transfers grids and boundary conditions to the solver and postprocessing tool. Steady, compressible three-dimensional simulations are conducted employing a multiphase Realizable k–ε Reynolds-averaged Navier–Stokes (RANS) physics with an adiabatic flamelet progress variable (FPV) model. The near-wall turbulence modeling is computed with scalable wall functions (SWFs). For each computational fluid dynamics (CFD) simulation, four levels of adaptive mesh refinement (AMR) are utilized on the original cut-cell grid. There are 15 geometrical input parameters and three output parameters, viz., a pattern factor proxy, a combustion efficiency proxy, and total pressure loss (TPL). Three times the number of input parameters plus one (48) is necessary to yield an optimization independent of the initial sampling. This conclusion is drawn by examining and comparing the Pareto frontiers and global sensitivities. However, the latter provides a better metric. The relative influence of the input parameters on the outputs is assessed by Spearman's order-rank correlation and an active subspace analysis. Some persistent geometric features for nondominated designs are also discussed.

References

1.
Briones
,
A. M.
,
Burrus
,
D. L.
,
Sykes
,
J. P.
,
Rankin
,
B. A.
, and
Caswell
,
A. W.
,
2018
, “Automated Design Optimization of a Small-Scale High-Swirl Cavity-Stabilized Combustor,”
ASME
Paper No. GT2018-76900. 10.1115/GT2018-76900
2.
Briones
,
A. M.
,
Burrus
,
D. L.
,
Sykes
,
J. P.
,
Rankin
,
B. A.
, and
Caswell
,
A. W.
,
2018
, “
Automated Design Optimization of a Small-Scale High-Swirl Cavity-Stabilized Combustor
,”
ASME J. Eng. Gas Turbines Power
,
140
(
12
), p.
121509
.10.1115/1.4040821
3.
Thomas
,
N.
,
Rumpfkeil
,
M. P.
,
Briones
,
A. M.
,
Erdmann
,
T. J.
, and
Rankin
,
B. A.
,
2019
, “
Multiple-Objective Optimization of a Small-Scale Cavity-Stabilized Combustor
,”
AIAA
Paper No. 2019-0990. 10.2514/6.2019-0990
4.
Constantine
,
P.
,
2015
,
Active Subspaces: Emerging Ideas in Dimension Reduction for Parameter Studies
,
SIAM
,
Philadelphia, PA
.
5.
Briones
,
A. M.
,
Rumpfkeil
,
M. P.
,
Thomas
,
N. R.
, and
Rankin
,
B. A.
, “
Effect of Deterministic and Continuous Design Space Resolution on Multiple-Objective Combustor Optimization
,”
ASME
Paper No. GT2019-91388.10.1115/1.4045284
6.
SAS IP, Inc., 2017, “
Ansys, Workbench User's Guide, v18.0
,” SAS IP, Inc.
7.
SAS IP, Inc., 2017, “
Ansys, DesignXplorer User's Guide, v18.0
,” SAS IP, Inc.
8.
SAS IP, Inc., 2017, “
Ansys, DesignModeler User's Guide, v18.0
,” SAS IP, Inc.
9.
SAS IP, Inc., 2017, “
Ansys, Meshing User's Guide, v18.0
,” SAS IP, Inc.
10.
SAS IP, Inc., 2017, “
Ansys, Fluent User's Guide, v18.0
,” SAS IP, Inc.
11.
SAS IP, Inc., 2017, “
Ansys, Fluent Theory Guide, v18.0
,” SAS IP, Inc.
12.
SAS IP, Inc., 2017, “
Ansys, CFD-Post User's Guide, v18.0
,” SAS IP, Inc.
13.
Deb
,
K.
,
Pratap
,
A.
,
Agarwal
,
S.
, and
Meyarivan
,
T.
,
2002
, “
A Fast and Elitist Multiobjective Genetic Algorithm: NSGA-II
,”
IEEE Trans. Evol. Comput.
,
6
(
2
), p.
182
.10.1109/4235.996017
14.
Russi
,
T. M.
,
2010
, “
Uncertainty Quantification With Experimental Data and Complex System Models
,” Ph.D. thesis, UC Berkeley, Berkeley, CA.
15.
Saltelli
,
A.
,
Ratto
,
M.
,
Andres
,
T.
,
Campolongo
,
F.
,
Cariboni
,
J.
,
Gatelli
,
D.
,
Saisana
,
M.
, and
Tarantola
,
S.
,
2008
,
Global Sensitivity Analysis: The Primer
,
Wiley
, Hoboken, NJ.
16.
Li
,
K.-C.
,
1991
, “
Sliced Inverse Regression for Dimension Reduction
,”
J. Am. Stat. Assoc.
,
86
(
414
), pp.
316
327
.10.1080/01621459.1991.10475035
17.
Tipireddy
,
R.
, and
Ghanem
,
R.
,
2014
, “
Basis Adaptation in Homogeneous Chaos Spaces
,”
J. Comput. Phys.
,
259
, pp.
304
317
.10.1016/j.jcp.2013.12.009
18.
Tyagi
,
H.
, and
Cevher
,
V.
,
2014
, “
Learning Non-Parametric Basis Independent Models From Point Queries Via Low-Rank Methods
,”
Appl. Comput. Harmonic Anal.
,
37
(
3
), pp.
389
412
.10.1016/j.acha.2014.01.002
19.
Rumpfkeil
,
M. P.
,
Bryson
,
D. E.
, and
Beran
,
P.
,
2019
, “
Multi-Fidelity Sparse Polynomial Chaos Surrogate Models for Flutter Database Generation
,”
AIAA
Paper No. 2019-1998.
10.2514/6.2019-1998
20.
Constantine
,
P.
,
Howard
,
R.
,
Glaws
,
A.
,
Grey
,
Z.
,
Diaz
,
P.
, and
Fletcher
,
L.
,
2016
, “
Python Active subspaces Utility Library
,”
J. Open Source Software
,
1
(
5
), p.
79
.10.21105/joss.00079
You do not currently have access to this content.