Abstract

We explain the advantages of using big-data methods for evaluating numerical optimization. The investigation focuses on the performance potential of three-dimensional return channel vanes under realistic manufacturing constraints. Based on an analysis of an optimization database, this paper presents a systematic approach for analysis and design guidelines for three-dimensional return channel vanes. To this end, a validated numerical setup was developed on the basis of experimental investigations, followed by a numerical optimization using a genetic algorithm and an artificial neural network. The optimization database was analyzed with a dimension reduction method called t-stochastic neighbor embedding. This method enabled linking geometric design features with physical correlations and, finally, with the objective functions of the optimization. With the help of the detected correlations within the database, it has been possible to work out a method for deciding on the selection of a design on the Pareto front and to draw new relevant conclusions. The systematic use of big-data methods proposed enables a more penetrating insight to be gained into numerical optimization, which is more general and relevant than those gained by simply comparing a single optimized design with a reference design. An analysis of the Pareto front reveals that 0.6% efficiency can be exchanged for 20% more homogeneous outflow.

References

1.
Hastie
,
T.
,
Tibshirani
,
R.
, and
Friedman
,
J.
,
2009
,
The Elements of Statistical Learning: Data Mining, Inference and Prediction
, 2nd ed,
Springer
,
New York
.
2.
Rossbach
,
T.
,
Bisping
,
J.
,
Grates
,
D. R.
,
Jeschke
,
P.
,
Hildebrandt
,
A.
, and
Franz
,
H.
,
2020
, “
Secondary Flows in the Return System of a Centrifugal Compressor Stage
,”
ASME J. Turbomach.
,
142
(
9
), p.
091002
.
3.
Bisping
,
J.
,
Rossbach
,
T.
,
Grates
,
D.
,
Hildebrandt
,
A.
, and
Jeschke
,
P.
,
2018
, “
Influence of Diffuser Diamter Ratio on the Performance of a Return Channel Within a Centrifugal Compressor Stage
,”
Proceedings of the Global Power & Propulsion Forum
,
Montreal, Canada
,
Sept 5–7
.
4.
Aalburg
,
C.
,
Simpson
,
A.
,
Schmitz
,
M.
,
Michelassi
,
V.
,
Evangelisti
,
S.
,
Belardini
,
E.
, and
Ballarini
,
V.
,
2008
, “
Design and Testing of Multistage Centrifugal Compressors With Small Diffusion Ratios
,”
Proceedings of ASME Turbo Expo 2008
, No. GT2008-51263.
5.
Nishida
,
Y.
,
Kobayashi
,
H.
,
Nishida
,
H.
, and
Sugimura
,
K.
,
2013
, “
Performance Improvement of a Return Channel in a Multistage Centrifugal Compressor Using Multiobjective Optimization
,”
ASME J. Turbomach.
,
135
(
3
), p.
031026
.
6.
Bellis
,
F. D.
,
Guidotti
,
E.
, and
Rubino
,
D. T.
,
2015
, “
Centrifugal Compressor Return Channel Optimization by Means of Advanced 3d CFD
,”
Proceedings of ASME Turbo Expo
, No. GT2015-44143.
7.
Jariwala
,
V.
,
Larosiliere
,
L.
, and
Hardin
,
J.
,
2016
, “
Design Exploration of a Return Channel for Multistage Centrifugal Compressors
,”
Proceedings of ASME Turbo Expo
, No. GT2016-57777.
8.
Hildebrandt
,
A.
, and
Schilling
,
F.
,
2017
, “
Numerical and Experimental Investigation of Return Channel Vane Aerodynamics With Two-Dimensional and Three-Dimensional Vanes
,”
ASME J. Turbomach.
,
139
(
1
), p.
011010
.
9.
Rossbach
,
T.
,
Rube
,
C.
,
Wedeking
,
M.
,
Franz
,
H.
, and
Jeschke
,
P.
,
2015
, “
Performance Measurements of a Full-Stage Centrifugal Process Gas Compressor Test Rig
,”
European Conference on Turbomachinery Fluid Dynamics and Thermodynamics
,
Madrid, Spain
,
Mar. 23–27
.
10.
Rube
,
C.
,
Rossbach
,
T.
,
Wedeking
,
M.
,
Grates
,
D. R.
, and
Jeschke
,
P.
,
2016
, “
Experimental and Numerical Investigation of the Flow Inside the Return Channel of a Centrifugal Process Compressor
,”
ASME J. Turbomach.
,
138
(
10
), p.
101006
.
11.
Deb
,
K.
, and
Jain
,
H.
,
2014
, “
An Evolutionary Many-Objective Optimization Algorithm Using Reference-Point Based Non-Dominated Sorting Approach, Part I: Solving Problems With Box Constraints
,”
IEEE Trans. Evol. Comput.
,
18
(
4
), pp.
577
601
.
12.
Jain
,
H.
, and
Deb
,
K.
,
2014
, “
An Evolutionary Many-Objective Optimization Algorithm Using Reference-Point-Based Nondominated Sorting Approach, Part II: Handling Constraints and Extending to an Adaptive Approach
,”
IEEE Trans. Evol. Comput.
,
18
(
4
), pp.
602
622
.
13.
Nishida
,
Y.
,
Nishida
,
H.
,
Kobayashi
,
H.
, and
Nishioka
,
T.
,
2015
, “
Experimental and Numerical Study of Return Channel Flow Influence on Surge Margin of a Multi-Stage Centrifugal Compressor
,”
Proceedings of ASME Turbo Expo
, No. GT2015-42546.
14.
Hehn
,
A.
,
Mosdzien
,
M.
,
Grates
,
D.
, and
Jeschke
,
P.
,
2017
, “
Aerodynamic Optimization of a Transonic Centrifugal Compressor by Using Arbitrary Blade Surfaces
,”
ASME J. Turbomach.
,
142
(
9
), p.
091002
.
15.
Hinton
,
G. E.
, and
Roweis
,
S. T.
,
2002
,
Advances in Neural Information Processing Systems 15
,
S.
Becker
,
S.
Thrun
, and
K.
Obermayer
, eds.,
MIT Press
,
Cambridge
, pp.
857
864
.
16.
van der Maaten
,
L.
,
2014
, “
Accelerating t-SNE Using Tree-Based Algorithms
,”
J. Mach. Learn. Res.
,
15
(
93
), pp.
3221
3245
.
17.
Herwig
,
H.
, and
Kock
,
F.
,
2007
, “
Direct and Indirect Methods of Calculating Entropy Generation Rates in Turbulent Convective Heat Transfer Problems
,”
Heat Mass Transfer
,
43
(
1
), pp.
207
215
.
18.
Denton
,
J.
,
1993
, “
Loss Mechanisms in Turbomachines
,”
ASME J. Turbomach.
,
115
(
1
), pp.
621
656
.
19.
Bisping
,
J.
,
2020
, “
Multi-Objective Optimization and Analysis of Three-Dimensional Return Systems of a Multistage Centrifugal Compressor
,” PhD thesis,
RWTH Aachen
,
Aachen
.
You do not currently have access to this content.