Set-up of a Robust NARX Model Simulator of Gas Turbine Start-up

This paper documents the set-up and validation of nonlinear autoregressive exogenous (NARX) models of a heavy-duty single-shaft gas turbine. The considered gas turbine is a General Electric PG 9351FA located in Italy. The data used for model training are time series data sets of five different maneuvers taken experimentally during the start-up procedure. The trained NARX models are subsequently used to predict other five experimental data sets 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 NARX models, by means of an accurate selection of training data sets 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 the developed simulation models is the set-up of a powerful and easy-to-build simulation tool which can be used for both control logic tuning and gas turbine diagnostics, characterized by good generalization capability.

[1]  Mohieddine Jelali,et al.  Hydraulic Servo-systems: Modelling, Identification and Control , 2012 .

[2]  Andrea Toffolo,et al.  Analytical and Neural Network Models for Gas Turbine Design and Off-Design Simulation # , 2001 .

[3]  K. Khorasani,et al.  Fault detection and isolation of gas turbine engines using a bank of neural networks , 2015 .

[4]  Michele Pinelli,et al.  Set Up of a Robust Neural Network for Gas Turbine Simulation , 2004 .

[5]  Arif Hepbasli,et al.  APPLICATION OF ARTIFICIAL NEURAL NETWORK (ANN) METHOD TO EXERGETIC ANALYSES OF GAS TURBINES , 2009 .

[6]  Silvio Simani,et al.  Fault diagnosis of an industrial gas turbine prototype using a system identification approach , 2008 .

[7]  Mauro Venturini,et al.  Modeling and Simulation of the Transient Behavior of an Industrial Power Plant Gas Turbine , 2014 .

[8]  M. Venturini.  Simulation of compressor transient behavior through recurrent neural network models , 2006 .

[9]  Laura Giarré,et al.  NARX models of an industrial power plant gas turbine , 2005, IEEE Transactions on Control Systems Technology.

[10]  Mauro Venturini.  Optimization of a Real-Time Simulator Based on Recurrent Neural Networks for Compressor Transient Behavior Prediction , 2007 .

[11]  Michele Pinelli,et al.  Artificial Intelligence for the Diagnostics of Gas Turbines—Part II: Neuro-Fuzzy Approach , 2007 .

[12]  Michele Pinelli,et al.  NARX models for simulation of the start-up operation of a single-shaft gas turbine , 2016 .

[13]  Michele Pinelli,et al.  Development of a One-Dimensional Modular Dynamic Model for the Simulation of Surge in Compression Systems , 2007 .

[14]  Michele Pinelli,et al.  Analysis of biogas compression system dynamics , 2009 .

[15]  Michele Pinelli,et al.  A Model for the Simulation of Large-Size Single-Shaft Gas Turbine Start-Up Based on Operating Data Fitting , 2007 .

[16]  Mohsen Assadi,et al.  Condition Based Maintenance of Gas Turbines Using Simulation Data and Artificial Neural Network: A Demonstration of Feasibility , 2008 .

[17]  Wojciech Radulski,et al.  On-Line Prediction of Temperature and Stress in Steam Turbine Components Using Neural Networks , 2015 .

[18]  Magnus Fast,et al.  Artificial Neural Networks for Gas Turbine Monitoring , 2010 .

[19]  Khashayar Khorasani,et al.  A dynamic prognosis scheme for flexible operation of gas turbines , 2016 .

[20]  Mauro Venturini.  Development and Experimental Validation of a Compressor Dynamic Model , 2005 .

[21]  Stephen Ogaji,et al.  Multiple-sensor fault-diagnoses for a 2-shaft stationary gas-turbine , 2002 .

[22]  R. Kurz,et al.  Gas Turbine Performance , 2016 .

[23]  Nader Meskin,et al.  Health Monitoring and Degradation Prognostics in Gas Turbine Engines Using Dynamic Neural Networks , 2015 .