0
Research Papers: Gas Turbines: Aircraft Engine

Development of Reliable NARX Models of Gas Turbine Cold, Warm, and Hot Start-Up

[+] Author and Article Information
Hilal Bahlawan, Michele Pinelli, Pier Ruggero Spina, Mauro Venturini

Dipartimento di Ingegneria,
Università degli Studi di Ferrara,
Ferrara 44122, Italy

Mirko Morini

Dipartimento di Ingegneria e Architettura,
Università degli Studi di Parma,
Parma 43124, Italy

Contributed by the Aircraft Engine Committee of ASME for publication in the JOURNAL OF ENGINEERING FOR GAS TURBINES AND POWER. Manuscript received November 16, 2017; final manuscript received November 18, 2017; published online April 23, 2018. Editor: David Wisler.

J. Eng. Gas Turbines Power 140(7), 071202 (Apr 23, 2018) (13 pages) Paper No: GTP-17-1621; doi: 10.1115/1.4038838 History: Received November 16, 2017; Revised November 18, 2017

This paper documents the setup and validation of nonlinear autoregressive network with exogenous inputs (NARX) models of a heavy-duty single-shaft gas turbine (GT). The data used for model training are time series datasets of several different maneuvers taken experimentally on a GT General Electric PG 9351FA during the start-up procedure and refer to cold, warm, and hot start-up. The trained NARX models are used to predict other experimental datasets, and comparisons are made among the outputs of the models and the corresponding measured data. Therefore, this paper addresses the challenge of setting up robust and reliable NARX models, by means of a sound selection of training datasets and a sensitivity analysis on the number of neurons. Moreover, a new performance function for the training process is defined to weigh more the most rapid transients. The final aim of this paper is the setup of a powerful, easy-to-build and very accurate simulation tool, which can be used for both control logic tuning and GT diagnostics, characterized by good generalization capability.

FIGURES IN THIS ARTICLE
<>
Copyright © 2018 by ASME
Your Session has timed out. Please sign back in to continue.

References

Jelali, M. , and Kroll, A. , 2004, Hydraulic Servo-Systems: Modeling, Identification, and Control, Springer-Verlag, London. [PubMed] [PubMed]
Lazzaretto, A. , and Toffolo, A. , 2001, “ Analytical and Neural Network Models for Gas Turbine Design and Off-Design Simulation,” Int. J. Appl. Thermodyn., 4(4), pp. 173–182. https://www.researchgate.net/publication/42539804_Analytical_and_Neural_Network_Models_for_Gas_Turbine_Design_and_Off-Design_Simulation
Ogaji, S. O. T. , Singh, R. , and Probert, S. D. , 2002, “ Multiple-Sensor Fault-Diagnosis for a 2-Shaft Stationary Gas Turbine,” Appl. Energy, 71(4), pp. 321–339. [CrossRef]
Arriagada, J. , Genrup, M. , Loberg, A. , and Assadi, M. , 2003, “ Fault Diagnosis System for an Industrial Gas Turbine by Means of Neural Networks,” International Gas Turbine Congress, Tokyo, Japan, Nov. 2–7.
Basso, M. , Giarre, L. , Groppi, S. , and Zappa, G. , 2004, “ NARX Models of an Industrial Power Plant Gas Turbine,” IEEE Trans. Control Syst. Technol., 13(4), pp. 599–604. [CrossRef]
Bettocchi, R. , Pinelli, M. , Spina, P. R. , Venturini, M. , and Burgio, M. , 2004, “Set Up of a Robust Neural Network for Gas Turbine Simulation,” ASME Paper No. GT2004-53421.
Bettocchi, R. , Pinelli, M. , Spina, P. R. , and Venturini, M. , 2007, “ Artificial Intelligence for the Diagnostics of Gas Turbines—Part II: Neuro-Fuzzy Approach,” ASME J. Eng. Gas Turbines Power, 129(3), pp. 720–729. [CrossRef]
Spina, P. R. , and Venturini, M. , 2007, “ Gas Turbine Modeling by Using Neural Networks Trained on Field Operating Data,” 20th International Conference on Efficiency, Cost, Optimization, Simulation and Environmental Impact of Energy Systems (ECOS 2007), Padova, Italy, June 25–28, pp. 213–222.
Simani, S. , and Patton, R. J. , 2008, “ Fault Diagnosis of an Industrial Gas Turbine Prototype Using a System Identification Approach,” Control Eng. Pract., 16(7), pp. 769–786. [CrossRef]
Yoru, Y. , Karakoc, T. H. , and Hepbasli, A. , 2009, “ Application of Artificial Neural Network (ANN) Method to Exergetic Analyses of Gas Turbines,” International Symposium on Heat Transfer in Gas Turbine Systems (TURBINE-09), Antalya, Turkey, Aug. 9–14.
Fast, M. , Assadi, M. , and De, S. , 2008, “Condition Based Maintenance of Gas Turbines Using Simulation Data and Artificial Neural Network: A Demonstration of Feasibility,” ASME Paper No. GT2008-50768.
Fast, M. , Palme, T. , and Karlsson, A. , 2009, “ Gas Turbines Sensor Validation Through Classification With Artificial Neural Networks,” 22nd International Conference on Efficiency, Cost, Optimization, Simulation and Environmental Impact of Energy Systems (ECOS 2009), Foz du Iguacu, Brazil, Aug. 30–Sept. 3, pp. 2059–2068.
Fast, M. , and Palme, T. , 2010, “ Application of Artificial Neural Network to the Condition Monitoring and Diagnosis of a Combined Heat and Power Plant,” J. Energy, 35(2), pp. 1114–1120. [CrossRef]
Fast, M. , 2010, “ Artificial Neural Networks for Gas Turbine Monitoring,” Ph.D. thesis, Lund University, Lund, Sweden. https://pdfs.semanticscholar.org/b264/4dc3055d1205f6668a691e92ea025eef3a82.pdf
Asgari, H. , Chen, X. , Morini, M. , Pinelli, M. , Sainudiin, R. , Spina, P. R. , and Venturini, M. , 2016, “ NARX Models for Simulation of the Start-Up Operation of a Single-Shaft Gas Turbine,” Appl. Therm. Eng., 93, pp. 368–376. [CrossRef]
Bahlawan, H. , Morini, M. , Pinelli, M. , Spina, P. R. , and Venturini, M. , 2016, “Set-Up of a Robust Narx Model Simulator of Gas Turbine Start-Up,” International Conference on Efficiency, Cost, Optimization, Simulation and Environmental Impact of Energy Systems (ECOS), Potoroz, Slovenia, June 19–23, Paper No. 257.
Nikpey, H. , Assadi, M. , and Breuhaus, P. , 2013, “ Development of an Optimized Artificial Neural Network Model for Combined Heat and Power Micro Gas Turbines,” Appl. Energy, 108, pp. 137–148. [CrossRef]
Sisworahardjo, N. , and El-Sharkh, M. Y. , 2013, “Validation of Artificial Neural Network Based Model of Microturbine Power Plant,” IEEE Industry Applications Society Annual Meeting (IAS), Lake Buena Vista, FL, Oct. 6–11.
Jingzhou, F. , Ningbo, Z. , Yong, S. , Yongming, F. , and Zhongwei, W. , 2016, “ Compressor Performance Prediction Using a Novel Feed-Forward Neural Network Based on Gaussian Kernel Function,” Adv. Mech. Eng., 8(1), pp. 1–14.
Asgari, H. , Venturini, M. , Chen, X. , and Sainudiin, R. , 2014, “ Modeling and Simulation of the Transient Behavior of an Industrial Power Plant Gas Turbine,” ASME J. Eng. Gas Turbines Power, 136(6), p. 061601. [CrossRef]
Dominiczak, K. , Rzadkowski, R. , Radulski, W. , and Szczepanik, R. , 2016, “ On-Line Prediction of Temperature and Stress in Steam Turbine Components Using Neural Networks,” ASME J. Eng. Gas Turbines Power, 138(5), p. 052606. [CrossRef]
Vatani, A. , Khorasani, K. , and Meskin, N. , 2015, “Health Monitoring and Degradation Prognostics in Gas Turbine Engines Using Dynamic Neural Networks,” ASME Paper No. GT2015-44101.
Amozegar, M. , and Khorasani, K. , 2016, “ An Ensemble of Dynamic Neural Network Identifiers for Fault Detection and Isolation of Gas Turbine Engines,” Neural Networks, 76, pp. 106–121. [CrossRef] [PubMed]
Chaibakhsh, A. , Amirkhani, S. , and Piredeir, P. , 2015, “Temperature Sensor Fault Diagnosing in Heavy Duty Gas Turbines Using Laguerre Network-Based Hierarchical Fuzzy Systems,” International Symposium on Innovations in Intelligent Systems and Applications, Madrid, Spain, Sept. 2–4, pp. 321–326.
Lakshmi, K. , Sunny, H. , and Ramesh Babu, N. , 2015, “ Neural Network Based Estimation of Gas Turbine Engine,” Global J. Pure Appl. Math., 11(6), pp. 4365–4374.
Sina Tayarani-Bathaie, S. , and Khorasani, K. , 2015, “ Fault Detection and Isolation of Gas Turbine Engines Using a Bank of Neural Networks,” J. Process Control, 36, pp. 22–41. [CrossRef]
Tsoutsanis, E. , Meskin, N. , Benammar, M. , and Khorasani, K. , 2016, “ A Dynamic Prognosis Scheme for Flexible Operation of Gas Turbines,” Appl. Energy, 164, pp. 686–701. [CrossRef]
Tavakolpour-Saleh, A. R. , Nasib, S. A. R. , Sepasyan, A. , and Hashemi, S. M. , 2015, “ Parametric and Nonparametric System Identification of an Experimental Turbojet Engine,” Aerosp. Sci. Technol., 43, pp. 21–29. [CrossRef]
Venturini, M. , 2006, “ Simulation of Compressor Transient Behavior Through Recurrent Neural Network Models,” ASME J. Turbomach., 128(3), pp. 444–454. [CrossRef]
Venturini, M. , 2007, “ Optimization of a Real-Time Simulator Based on Recurrent Neural Networks for Compressor Transient Behavior Prediction,” ASME J. Turbomach., 129(3), pp. 468–478. [CrossRef]
Venturini, M. , 2005, “ Development and Experimental Validation of a Compressor Dynamic Model,” ASME J. Turbomach., 127(3), pp. 599–608. [CrossRef]
Morini, M. , Pinelli, M. , and Venturini, M. , 2007, “ Development of a One-Dimensional Modular Dynamic Model for the Simulation of Surge in Compression Systems,” ASME J. Turbomach., 129(3), pp. 437–447. [CrossRef]
Morini, M. , Pinelli, M. , and Venturini, M. , 2009, “ Analysis of Biogas Compression System Dynamics,” Appl. Energy, 86(11), pp. 2466–2475. [CrossRef]
Nowak, G. , and Rustin, A. , 2016, “ Using the Artificial Neural Network to Control the Steam Turbine Heating Process,” Appl. Therm. Eng., 108, pp. 204–210. [CrossRef]
Morini, M. , Cataldi, G. , Pinelli, M. , and Venturini, M. , 2007, “A Model for the Simulation of Large-Size Single-Shaft Gas Turbine Start-Up Based on Operating Data Fitting,” ASME Paper No. GT2007-27373.
Walsh, P. P. , and Fletcher, P. , 1998, Gas Turbine Performance, Blackwell Science, Oxford, UK.
Beale, M. H. , Hagan, M. T. , and Demuth, H. B. , 2013, “Neural Network Tool box™ User's Guide,” The MathWorks Inc., Natick, MA.

Figures

Grahic Jump Location
Fig. 1

Methodology for NARX model training

Grahic Jump Location
Fig. 4

Block diagram of the complete NARX model

Grahic Jump Location
Fig. 5

Open-loop structure of a NARX model

Grahic Jump Location
Fig. 2

Trend over time of the fuel mass flow rate during hot (top), warm (middle) and cold (bottom) start-up

Grahic Jump Location
Fig. 3

EWF for T04, T02, PrC and N for cold start-up

Grahic Jump Location
Fig. 10

Trend of T04 and T02 for the testing maneuvers during cold start-up

Grahic Jump Location
Fig. 11

Trend of PrC and N for the testing maneuvers during cold start-up

Grahic Jump Location
Fig. 12

Trend of T04 and T02 for the testing maneuvers during warm start-up

Grahic Jump Location
Fig. 13

Trend of PrC and N for the testing maneuvers during warm start-up

Grahic Jump Location
Fig. 14

Trend of T04, T02, PrC and N for the testing maneuver TE1 during hot start-up

Grahic Jump Location
Fig. 6

RMSE of trained NARX models for cold start-up

Grahic Jump Location
Fig. 7

RMSE of trained NARX models for warm start-up

Grahic Jump Location
Fig. 8

RMSE of trained NARX models for hot start-up

Grahic Jump Location
Fig. 9

Closed-loop structure of a NARX model

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In