Nonlinear Generalized Predictive Controller Based on Ensemble of NARX Models for Industrial Gas Turbine Engine

Energy ◽  
2021 ◽  
pp. 120700
Author(s):  
Ibrahem M.A. Ibrahem ◽  
Ouassima Akhrif ◽  
Hany Moustapha ◽  
Martin Staniszewski
2010 ◽  
Author(s):  
Shahrokh Etemad ◽  
Benjamin Baird ◽  
Sandeep Alavandi ◽  
William Pfefferle

Author(s):  
Ibrahem Mohamed Ibrahem ◽  
Ouassima Akhrif ◽  
Hany Moustapha ◽  
Martin Staniszewski

Abstract Gas turbine is a complex system operating in non-stationary operation conditions for which traditional model-based modeling approaches have poor generalization capabilities. To address this, an investigation of a novel data-driven neural networks based model approach for a three-spool aero-derivative gas turbine engine (ADGTE) for power generation during its loading and unloading conditions is reported in this paper. For this purpose, a non-linear autoregressive network with exogenous inputs (NARX) is used to develop this model in MATLAB environment using operational closed-loop data collected from Siemens (SGT-A65) ADGTE. Inspired by the way biological neural networks process information and by their structure which changes depending on their function, multiple-input single-output (MISO) NARX models with different configurations were used to represent each of the ADGTE output parameters with the same input parameters. Usage of a single neural network to represent each of the system output parameters may not be able to provide an accurate prediction for unseen data and as a consequence, provides poor generalization. To overcome this problem, an ensemble of MISO NARX models is used to represent each output parameter. The major challenge of the ensemble generation is to decide how to combine results produced by the ensemble's components. In this paper, a novel hybrid dynamic weighting method (HDWM) is proposed. The simulation results show improvement in accuracy and robustness by using the proposed modeling approach.


Author(s):  
Partha S. Das

Engine rotors are one of the most critical components of a heavy duty industrial gas turbine engine, as it transfers mechanical energy from rotor blades to a generator for the production of electrical energy. In general, these are larger bolted rotors with complex geometries, which make analytical modeling of the rotor to determine its static, transient or dynamic behaviors difficult. For this purpose, powerful numerical analysis approaches, such as, the finite element method, in conjunction with high performance computers are being used to analyze the current rotor systems. The complexity in modeling bolted rotor behavior under various loadings, such as, airfoil, centrifugal and gravity loadings, including engine induced vibration is one of the main challenges of simulating the structural performance of an engine rotor. In addition, the internal structural temperature gradients that can be encountered in the transient state as a result of start-up and shutdown procedures are generally higher than those that occur in the steady-state and hence thermal shock is important factor to be considered relative to ordinary thermal stress. To address these issues, the current paper presents the steady-state & quasi-static analyses (to approximate transient responses) of two full 3-D industrial gas turbine engine rotors, SW501F & GE-7FA rotor, comprising of both compressor & turbine sections together. Full 3-D rotor analysis was carried out, since the 2-D axisymmetric model is inadequate to capture the complex geometries & out of plane behavior of the rotor. Both non-linear steady-state & transient analyses of a full gas turbine engine rotor was performed using the general purpose finite element analysis program ABAQUS. The paper presents in detail the FEA modeling technique, overall behavior of the full rotor under various loadings, as well as, the critical locations in the rotor with respect to its strength and life. The identification of these critical locations is needed to help with the repair of the existing rotors and to improve and extend the operational/service life of these rotors.


JOM ◽  
2003 ◽  
Vol 55 (3) ◽  
pp. 27-31 ◽  
Author(s):  
Mei Ling Clemens ◽  
Allen Price ◽  
Richard S. Bellows

1976 ◽  
Vol 7 (7) ◽  
pp. 991-997 ◽  
Author(s):  
W. Wallace ◽  
J. M. Trenouth ◽  
J. D. Daw

Author(s):  
Samuel C. Laux ◽  
Robert N. Ware

The Patriot Air Defense Missile System (formerly SAM-D) is being deployed in Europe. The powerplant supplying electricity to the radar set and to the engagement control station is DOD Model D-424A, powered by the Allison Model GT-404 industrial gas turbine (IGT) engine. Designed as a vehicular engine, the application in a generator set is an interesting one, utilizing many of the following features originally intended to enhance the performance of trucks and buses: • Dual, rotating disk regenerators dramatically improve fuel consumption by transferring heat energy from the exhaust gas stream to compressor discharge. • Power transfer, intended to provide part load fuel economy in vehicles, is modified to furnish free-shaft start-fixed shaft run in generator sets. • Free-shaft starts allow successful operation down to −50°F without auxiliary heaters. The resultant gas turbine engine driven generator set — 150 kW, transportable, skid mounted, alternating current 400 Hz, tactical — has met the military requirements for performance and reliability.


Sign in / Sign up

Export Citation Format

Share Document