Abstract

Conventional physics-based or experimental-based approaches for gas turbine combustion tuning are time consuming and cost intensive. Recent advances in data analytics provide an alternative method. In this paper, we present a cross-disciplinary study on the combustion tuning of an F-class gas turbine that combines machine learning with physics understanding. An artificial-neural-network-based (ANN) model is developed to predict the combustion performance (outputs), including NOx emissions, combustion dynamics, combustor vibrational acceleration, and turbine exhaust temperature. The inputs of the ANN model are identified by analyzing the key operating variables that impact the combustion performance, such as the pilot and the premixed fuel flow, and the inlet guide vane angle. The ANN model is trained by field data from an F-class gas turbine power plant. The trained model is able to describe the combustion performance at an acceptable accuracy in a wide range of operating conditions. In combination with the genetic algorithm, the model is applied to optimize the combustion performance of the gas turbine. Results demonstrate that the data-driven method offers a promising alternative for combustion tuning at a low cost and fast turn-around.

References

1.
Angello
,
L. C.
, and
Castaldini
,
C.
,
2004
, “
Combustion Tuning Guidelines: Understanding and Mitigating Dynamic Instabilities in Modern Gas Turbine Combustors
,”
ASME
Paper No. GT2004-54081.10.1115/GT2004-54081
2.
Lefebvre
,
A. H.
,
1984
, “
Fuel Effects on Gas Turbine Combustion-Liner Temperature, Pattern Factor, and Pollutant Emissions
,”
J. Aircr.
,
21
(
11
), pp.
887
898
.10.2514/3.45059
3.
Lewis
,
G. D.
,
1991
, “
A New Understanding of NOx Formation,” Tenth International Symposium on Air-Breathing Engines
,” Nottingham, UK, AIAA, Washington, DC, Paper No. Isabe 91-7064, pp.
625
9
. 10.2514/6.91-7064
4.
Rokke
,
N. A.
,
Hustad
,
J. E.
, and
Berg
,
S.
,
1993
, “
Pollutant Emissions From Gas Fired Turbine Engines in Offshore Practice-Measurement and Scaling
,”
ASME
Paper No. GT1993-170.10.1115/GT1993-170
5.
Syed
,
K. J.
,
Roden
,
K.
, and
Martin
,
P.
,
2007
, “
A Novel Approach to Predicting NOx Emissions From Dry Low Emissions Gas Turbines
,”
J. Eng. Gas Turbines Power
,
129
(
3
), pp.
672
679
.10.1115/1.2718564
6.
Oh
,
J.
,
Kim
,
M.
, and
Yoon
,
Y.
,
2012
, “
The Tuning Methodology of a GE 7FA+e DLN-2.6 Gas Turbine Combustor
,”
Appl. Therm. Eng.
,
36
, pp.
14
20
.10.1016/j.applthermaleng.2011.12.018
7.
Lee
,
M. C.
,
Chung
,
J. H.
,
Park
,
W. S.
,
Park
,
S.
, and
Yoon
,
Y.
,
2013
, “
The Combustion Tuning Methodology of an Industrial Gas Turbine Using a Sensitivity Analysis
,”
Appl. Therm. Eng.
,
50
(
1
), pp.
714
721
.10.1016/j.applthermaleng.2012.07.016
8.
Park
,
S.
,
Choi
,
G. M.
, and
Tanahashi
,
M.
,
2019
, “
Demonstration of a Gas Turbine Combustion-tuning method and Sensitivity Analysis of the Combustion-Tuning Parameters With Regard to NOx Emissions
,”
Fuel
,
239
, pp.
1134
1142
.10.1016/j.fuel.2018.11.021
9.
Booth
,
R. C.
, and
Roland
,
W. B.
,
1998
, “
Neural Network-Based Combustion Optimization Reduces NOx Emissions While Improving Performance
,”
IEEE Industry Applications on Dynamic Modeling Control Applications for Industry Workshop
, Vancouver, BC, Canada, Apr. 30–May 1, pp.
1
6
.10.1109/DMCA.1998.703475
10.
Chu
,
J. Z.
,
Shieh
,
S. S.
,
Jang
,
S. S.
,
Chien
,
C. I.
,
Wan
,
H. P.
, and
Ko
,
H. H.
,
2003
, “
Constrained Optimization of Combustion in a Simulated Coal-Fired Boiler Using Artificial Neural Network Model and Information Analysis
,”
Fuel
,
82
(
6
), pp.
693
703
.10.1016/S0016-2361(02)00338-1
11.
Wang
,
P. H.
,
Li
,
L. L.
,
Chen
,
Q.
, and
Dong
,
Y. H.
,
2004
, “
Research on Applications of Artificial Intelligence to Combustion Optimization in a Coal-Fired Boiler
,”
Proc. Chin. Soc. Electric Eng.
,
24
(
4
), pp.
184
188
. https://www.researchgate.net/publication/290250730_Research_on_applications_of_artificial_intelligence_to_combustion_optimization_in_a_coal-fired_boiler
12.
Li
,
G.
,
Niu
,
P.
,
Wang
,
H.
, and
Liu
,
Y.
,
2014
, “
Least Square Fast Learning Network for Modeling the Combustion Efficiency of a 300 MW Coal-Fired Boiler
,”
Neural Netw.
,
51
, pp.
57
66
.10.1016/j.neunet.2013.12.006
13.
Li
,
G.
, and
Niu
,
P.
,
2016
, “
Combustion Optimization of a Coal-Fired Boiler With Double Linear Fast Learning Network
,”
Soft Comput.
,
20
(
1
), pp.
149
156
.10.1007/s00500-014-1486-3
14.
Gu
,
Y.
,
Zhao
,
W.
, and
Wu
,
Z.
,
2011
, “
Online Adaptive Least Squares Support Vector Machine and Its Application in Utility Boiler Combustion Optimization Systems
,”
J. Process Control
,
21
(
7
), pp.
1040
1048
.10.1016/j.jprocont.2011.06.001
15.
Gu
,
Y.
,
Zhao
,
W.
, and
Wu
,
Z.
,
2010
, “
Combustion Optimization for Utility Boiler Based on Least-Square Support Vector Machine
,”
Proc. Chin. Soc. Electric Eng.
,
30
(
17
), pp.
91
97
.https://www.researchgate.net/publication/285929808_Combustion_optimization_for_utility_boiler_based_on_least_square-support_vector_machine
16.
MathWorks, 2021, “Matlab Manual
,” MathWorks, Natick, MA, accessed Feb. 23, 2021, https://www.mathworks.com/help/gads/what-is-the-genetic-algorithm.html
You do not currently have access to this content.