Abstract

The global drive toward renewable energy is imposing challenging operating requirements on power turbines. Flexible load-leveling applications must accept more frequent and demanding start-stop cycles. Full transient analyses are too computationally expensive for real-time simulation across all operating regimes, so monitoring relies on sparse physical measurements. Alone, these sparse data lack the fidelity for real-time prediction of a complex thermal field. A new hybrid methodology is proposed, coupling data across a range of fidelities to bridge the limitations in the individual analyses. Combining several fidelity methods in parallel: low-order models, corrected by real-time physical measurements, are calibrated with high-fidelity simulations. The multifaceted hybrid approach enables the real-time speed of low-order analysis at high resolution. This paper series develops the critical enabling features of the hybrid method. Real-time definition of the simulation thermal boundary condition is fundamental to the methodology. A novel long-short-term-memory (LSTM) neural network is presented, enabling time series prediction of the turbine thermal profile. The remote sensing method utilizes standard plant measurements to reconstruct the turbine temperature history, allowing reliable thermal prediction whilst removing the need for direct monitoring of the casing temperature. Calculations within the training region demonstrated high accuracy, achieving a mean square error of 3.1 K and maximum instantaneous peak error of 7.6 K. Combining a reduced feature space and efficient two-step predictor-corrector structure, the LSTM method offers high-speed temperature calculation, successfully predicting one month of operating data in under a minute.

References

1.
Greis
,
J.
,
Gobrecht
,
E.
, and
Wendt
,
S.
,
2012
, “
Flexible and Economical Operation Of Power Plants - 25 Years Of Expertise
,”
ASME
Paper No. GT2012-68716.10.1115/GT2012-68716
2.
Della Villa
,
S.
, “
Energy Innovation: A Focus on Power Generation Data Capture and Analytics in a Competitive Market
,”
ASME
Paper No. GT2018-75030.10.1115/GT2018-75030
3.
Baker
,
M.
, and
Rosic
,
B.
,
2024
, “
The Hybrid Pathway to Flexible Power Turbines, Part I: Novel Autoencoder Methods for the Automated Optimization of Thermal Probes and Fast Sparse Data Reconstruction, Enabling Real-Time Thermal Analysis
,”
ASME J. Eng. Gas Turbines Power
,
146
(
3
), p.
031020
.10.1115/1.4063581
4.
Baker
,
M.
, and
Rosic
,
B.
,
2023
, p, “
The Hybrid Pathway to Flexible Power Turbines, Part II: Fast Data Transfer Methods Between Varying Fidelity Simulations, to Enable Efficient Conjugate Thermal Field Prediction
,”
ASME J. Eng. Gas Turbines Power
,
146
(
3
), p.
031021
.10.1115/1.4063588
5.
Ng
,
A.
,
2017
, “
Machine Learning
,”
Stanford University
, Stanford, CA, accessed Aug. 1, 2019, https://www.coursera.org/learn/machine-learning
6.
Dominiczak
,
K.
,
Rzadkowski
,
R.
, and
Radulski
,
W.
,
2015
, “
Steam Turbine Stress Control Using NARX Neural Network
,”
Open Eng.
,
5
(
1
),
43
.10.1515/eng-2015-0043
7.
Nowak
,
G.
, and
Rusin
,
A.
,
2016
, “
Using the Artificial Neural Network to Control the Steam Turbine Heating Process
,”
Appl. Therm. Eng.
,
108
, pp.
204
210
.10.1016/j.applthermaleng.2016.07.129
8.
Kosowski
,
K.
,
Tucki
,
K.
, and
Kosowski
,
A.
,
2010
, “
Application of Artificial Neural Networks in Investigations of Steam Turbine Cascades
,”
ASME J. Turbomach.
,
132
(
1
), p.
014501
.10.1115/1.3103923
9.
Goyal
,
V.
,
Xu
,
M.
,
Kapat
,
J.
, and
Vesely
,
L.
,
2020
, “
Prediction of Gas Turbine Performance Using Machine Learning Methods
,”
ASME
Paper No. GT2020-15232.10.1115/GT2020-15232
10.
Ibrahem
,
I.
,
Akhrif
,
O.
,
Moustapha
,
H.
, and
Staniszewski
,
M.
,
2020
, “
An Ensemble of Recurrent Neural Networks for Real Time Performance Modelling of Three-Spool Aero-Derivative Gas Turbine Engine
,”
ASME
Paper No. GT2020-15756.10.1115/GT2020-15756
11.
Panov
,
V.
, and
Cruz-Manzo
,
S.
,
2020
, “
Gas Turbine Performance Digital Twin for Real-Time Embedded Systems
,”
ASME
Paper No. GT2020-14664.10.1115/GT2020-14664
12.
Baker
,
M.
, “
2022
, “
Turbines for Flexible Power Plant Operation
,” Ph.D. thesis,
University of Oxford
, Oxford, UK.
13.
Greff
,
K.
,
Srivastava
,
R.
,
Koutnik
,
J.
,
Steunebrink
,
B.
, and
Schmidhuber
,
J.
,
2017
, “
LSTM: A Search Space Odyssey
,”
IEEE Transaction Neural Networks Learning Systems
,
28
(
10
), pp.
2222
2232
.10.1109/TNNLS.2016.2582924
14.
Carslaw
,
H.
, and
Jaeger
,
J.
,
1947
,
Conduction of Heat in Solids
,
Clarendon Press
,
Oxford, UK
.
15.
Verma
,
A.
,
2020
, “
Building A Neural Net From Scratch Using R – Part 1
,” RStudio PBC, Boston MA, accessed Apr. 1, 2023, https://rviews.rstudio.com/2020/07/20/shallow-neural-net-from-scratch-using-r-part-1/
16.
Scikit-learn 1.0.1
,
2011
, “
Scikit-Learn: Machine Learning in Python
,”
J. Machine Learn. Res.
, 12(85), pp. 2825–2830.
http://jmlr.org/papers/v12/pedregosa11a.html
17.
Kingma
,
D.
, and
Ba
,
J.
,
2014
, “
Adam: A Method for Stochastic Optimization
,”
arXiv:1412.6980v9
.10.48550/arXiv.1412.6980
18.
Losi
,
E.
,
Venturini
,
M.
,
Manservigi
,
L.
,
Ceschini
,
G.
, and
Bechini
,
G.
,
2019
, “
Anomaly Detection in gas turbine time Series by Means of Bayesian Hierarchical Models
,”
ASME J. Eng. Gas Turbines Power
,
141
(
11
), p. 111019.10.1115/1.4044781
19.
Mantelli
,
L.
,
Zaccaria
,
V.
,
Ferrari
,
M.
, and
Kyprianidis
,
K.
,
2021
, “
A Degradation Diagnosis Method for Gas Turbine—Fuel Cell Hybrid Systems Using Bayesian Networks
,”
ASME J. Eng. Gas Turbines Power
,
143
(
5
), p.
054502
.10.1115/1.4050153
20.
Sadeghi
,
M.
,
Behnia
,
F.
, and
Amiri
,
R.
,
2020
, “
Window Selection of the Savitzky-Golay Filters for Signal Recovery From Noisy Measurements
,”
IEEE Trans. Instrum. Meas.
,
69
(
8
), pp.
5418
5427
.10.1109/TIM.2020.2966310
21.
Iwana
,
B.
, and
Uchida
,
S.
,
2021
, “
An Empirical Survey of Data Augmentation for Time Series Classification With Neural Networks
,”
PLoS One
,
16
(
7
), p.
e0254841
.10.1371/journal.pone.0254841
22.
Semenoglou
,
A.-A.
,
Spiliotis
,
E.
, and
Assimakopoulos
,
V.
,
2023
, “
Data Augmentation for Univariate Time Series Forecasting With Neural Networks
,”
Patt. Recognit.
,
134
, p.
109132
.10.1016/j.patcog.2022.109132
23.
Shanker
,
M.
,
Hu
,
M.
, and
Hung
,
M.
,
1996
, “
Effect of Data Standardization on Neural Network Training
,”
Omega
,
24
(
4
), pp.
385
397
.10.1016/0305-0483(96)00010-2
24.
Jolliffe
,
I. T.
, and
Cadima
,
J.
,
2016
, “
Principal Component Analysis: A Review and Recent Developments
,”
Philos. Trans. R. Soc. A: Math., Phys. Eng. Sci.
,
374
(
2065
), p.
20150202
.10.1098/rsta.2015.0202
25.
Chollet
,
F.
,
2015
, “
Keras
,” Google, Mountain View, CA, accessed Aug. 1, 2019, https://github.com/keras-team/keras
26.
Abadi
,
M.
,
Agarwal
,
A.
,
Barham
,
P.
,
Brevdo
,
E.
,
Chen
,
Z.
,
Citro
,
C.
,
Corrado
,
G. A.
,
2015
, “
TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems
,” accessed Mar. 6, 2025, https://www.tensorflow.org/about/bib
27.
Google
,
A. I.
,
2018
, “
Tensorflow
,” Google, Mountain View, CA, accessed Aug. 1, 2019, https://www.tensorflow.org/
28.
Simonyan
,
K.
, and
Zisserman
,
A.
,
2015
, “
Very Deep Convolutional Networks for Large-Scale Image Recognition
,”
International Conference on Learning Representations (ICRL)
, San Diego, CA, May 7–9.
29.
Virtanen
,
P.
,
Gommers
,
R.
,
Oliphant
,
T. E.
,
Haberland
,
M.
,
Reddy
,
T.
,
Cournapeau
,
D.
,
Burovski
,
E.
, et al.,
2020
, “
SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python
,”
Nat. Methods
,
17
(
3
), pp.
261
272
.10.1038/s41592-019-0686-2
30.
Pastore
,
A.
, and
Carnini
,
M.
,
2021
, “
Extrapolating From Neural Network Models: A Cautionary Tale
,”
J. Phys. G: Nucl. Part. Phys.
,
48
(
8
), p.
084001
.10.1088/1361-6471/abf08a
You do not currently have access to this content.