Abstract

Machine learning has gone way beyond a ground-breaking technology a few decades ago to now taken for granted in many day-to-day activities. It is now providing new ways for manufacturing, assembling, operating, monitoring, and maintaining products. Typical application areas include performance optimization, quality improvements, fault detection and predictive maintenance. In this paper application of machine learning algorithms to forced response prediction during the design and analysis of a typical gas turbine compressor blade is reported. The forced response prediction process typically involves utilizing harmonic or time domain computational fluid dynamics (CFD) analyses to compute the forcing and the aero damping, to calculate reserve factors that represent the high cycle fatigue life of the blade. This time-consuming process is generally limited to the later phases of the design cycle and can lead to hundreds of calculations if one must address all the resonances in a typical twin shaft running range. A neural network trained using historical data is used to directly predict the reserve factor with high confidence without the need for costlier high fidelity CFD by using just the finite elements (FE) predicted parameters. This allows to perform high-fidelity aero-mechanical assessment at an early stage in the design process. Further, application of image recognition using a convoluted neural network to aid in the identification of FE predicted Modeshapes is also demonstrated, which can also improve the quality of the reserve factor predictions.

References

1.
Chiang
,
H. D.
, and
Kielb
,
R. E.
,
1993
, “
An Analysis System for Blade Forced Response
,”
ASME J. Turbomach.
,
115
(
4
), pp.
762
770
.10.1115/1.2929314
2.
Hilbert
,
G. R.
,
Ni
,
R. H.
, and
Takahashi
,
R. K.
,
1997
, “
Forced Response Prediction of Gas Turbine Rotor Blades
,”
ASME
Paper No. IMECE1997-0750.10.1115/IMECE1997-0750
3.
Green
,
J.
, and
Marshall
,
J. G.
,
1999
, “
Forced Response Prediction Within the Design Process
,”
3rd European Conference on Turbomachinary - Fluid Dynamics and Thermodynamics
, London, UK, Mar. 2–5.http://www.divaportal.org/smash/record.jsf?pid=diva2%3A10530&dswid=-2539
4.
Silkowski
,
P. D.
,
Rhie
,
C. M.
,
Copeland
,
G. S.
,
Eley
,
J. A.
, and
Bleeg
,
J. M.
,
2001
, “
CFD Investigation of Aeromechanics
,”
ASME
Paper No. 2001-GT-0267.10.1115/2001-GT-0267
5.
Moffatt
,
S.
, and
He
,
L.
,
2003
, “
Blade Forced Response Prediction for Industrial Gas Turbines. Part 1: Methodologies
,”
ASME
Paper No. GT2003-38640.10.1115/GT2003-38640
6.
Ning
,
W.
,
Moffatt
,
S.
,
Li
,
Y.
, and
Wells
,
R. G.
,
2003
, “
Blade Forced Response Prediction for Industrial Gas Turbines. Part 2: Verification and Application
,”
ASME
Paper No. GT2003-38642.10.1115/GT2003-38642
7.
Vahdati
,
M.
,
Sayma
,
A. I.
,
Imregun
,
M.
, and
Simpson
,
G.
,
2007
, “
Multibladerow Forced Response Modelling in Axial-Flow Core Compressors
,”
ASME J. Turbomach.
,
129
(
2
), pp.
412
420
.10.1115/1.2436892
8.
Krishnababu
,
S. K.
,
2017
, “
Validation of a Modal Method Using Measured Synchronous Response of an Industrial Compressor Rotor Blade
,”
Int. J. Turbines Sustainable Energy
,
1
(
1
), pp.
15
20
.
9.
Krishnababu
,
S. K.
,
Bruni
,
G.
, and
Frach
,
A.
,
2021
, “
On the Forced Response Predictions and Life Improvements of an Industrial Axial Compressor Rotor Blade
,”
ASME
Paper No. GT2021-58923.10.1115/GT2021-58923
10.
Rahmati
,
M. T.
,
He
,
L.
,
Wang
,
D. X.
,
Li
,
Y. S.
,
Wells
,
R. G.
, and
Krishnababu
,
S. K.
,
2012
, “
Non-Linear Time and Frequency Domain Methods for Multi-Row Aeromechanical Analysis
,”
ASME
Paper No. GT2012-68723.10.1115/GT2012-68723
11.
He
,
L.
, and
Ning
,
W.
,
1998
, “
Efficient Approach for Analysis of Unsteady Viscous Flows in Turbomachines
,”
AIAA J.
,
36
(
11
), pp.
2005
2012
.10.2514/2.328
12.
Frey
,
C.
,
Ashcroft
,
G.
,
Kersken
,
H.
, and
Voigt
,
C.
,
2014
, “
A Harmonic Balance Technique for Multistage Turbomachinery Applications
,”
ASME
Paper No. GT2014-25230.10.1115/GT2014-25230
13.
Fei
,
J.
,
Zhao
,
N.
,
Shi
,
Y.
,
Feng
,
Y.
, and
Wang
,
Z.
,
2016
, “
Compressor Performance Prediction Using a Novel Feed-Forward Neural Network Based on Gaussian Kernel Function
,”
Adv. Mech. Eng.
,
8
(
1
), pp.
1
14
.10.1177/1687814016628396
14.
Taylor
,
J. V.
,
Conduit
,
B.
,
Hall
,
C.
,
Hiller
,
M.
, and
Miller
,
R. J.
,
2019
, “
Predicting the Operability of Damaged Compressors Using Machine Learning
,”
ASME
Paper No. GT2019-91339.10.1115/GT2019-91339
15.
Krishnababu
,
S.
,
Valero
,
O.
, and
Wells
,
R.
,
2021
, “
AI Assisted High Fidelity Multi-Physics Digital Twin of Industrial Gas Turbines
,”
ASME
Paper No. GT2021-58925.10.1115/GT2021-58925
16.
Kelly
,
S. T.
,
Lupini
,
A.
, and
Epureanu
,
B. I.
,
2021
, “
Data-Driven Approach for Identifying Mistuning in as-Manufactured Blisks
,”
ASME
Paper No. GT2021-59887.10.1115/GT2021-59887
17.
Pongetti
,
J.
,
Kipouros
,
T.
,
Emmanuelli
,
M.
,
Ahlfeld
,
R.
, and
Shahpar
,
S.
,
2021
, “
Using Autoencoders and Output Consolidation to Improve Machine Learning Models for Turbomachinery Applications
,”
ASME
Paper No. GT2021-60158.10.1115/GT2021-60158
18.
Chollet
,
F.
, 2022, “
Keras
,” GitHub, Online, accessed Sept. 21, 2022, https://keras.io
19.
Pedregosa
,
F.
,
Varoquaux
,
G.
,
Gramfort
,
A.
,
Michel
,
V.
,
Thirion
,
B.
,
Grisel
,
O.
,
Blondel
,
M.
, et al.,
2011
, “
Scikit-Learn: Machine Learning in Python
,”
J. Mach. Learn. Res.
,
12
(
85
), pp.
2825
2830
.10.5555/1953048.2078195
You do not currently have access to this content.