A Comparison of Hybrid Approaches for Turbofan Engine Gas Path Fault Diagnosis
-
Feng Lu
,
Jinquan Huang
Abstract
A hybrid diagnostic method utilizing Extended Kalman Filter (EKF) and Adaptive Genetic Algorithm (AGA) is presented for performance degradation estimation and sensor anomaly detection of turbofan engine. The EKF is used to estimate engine component performance degradation for gas path fault diagnosis. The AGA is introduced in the integrated architecture and applied for sensor bias detection. The contributions of this work are the comparisons of Kalman Filters (KF)-AGA algorithms and Neural Networks (NN)-AGA algorithms with a unified framework for gas path fault diagnosis. The NN needs to be trained off-line with a large number of prior fault mode data. When new fault mode occurs, estimation accuracy by the NN evidently decreases. However, the application of the Linearized Kalman Filter (LKF) and EKF will not be restricted in such case. The crossover factor and the mutation factor are adapted to the fitness function at each generation in the AGA, and it consumes less time to search for the optimal sensor bias value compared to the Genetic Algorithm (GA). In a word, we conclude that the hybrid EKF-AGA algorithm is the best choice for gas path fault diagnosis of turbofan engine among the algorithms discussed.
Funding statement: Funding: We are grateful for the financial support of the National Nature Science Foundation of China (No. 61304133), the Fundamental Research Funds for the Central Universities (No. NS2015024).
Acknowledgements
The authors wish to thank the anonymous reviewers for their constructive comments and great help in the writing process, which improve the manuscript significantly.
Copyright reminder
The authors declare no conflicts of copyright.
Nomenclature
- A,B,C,D,L,M
System matrices
- AGA
Adaptive genetic algorithms
- b
Sensor bias
- BPNN
Back propagation neural network
- EHM
Engine health management
- EKF
Extended Kalman filter
- GA
Genetic algorithms
- GRNN
General regression neural network
- HPC
High pressure compressor
- HPT
High pressure turbine
- I
Identity matrix
- JH
High pressure spool rotor inertia
- JL
Low pressure spool rotor inertia
- KF
Kalman filter
- LKF
Linearized Kalman filter
- LPT
Low pressure turbine
- m
Measurement uncertainty vector
- NH
Compressor rotor speed
- NHT
Power produced by the HPT
- NL
Fan rotor speed
- NLT
Power produced by the LPT
- NN
Neural networks
- p
Health parameter vector
- P3
Compressor outlet pressure
- P43
HPT outlet pressure
- P5
LPT outlet pressure
- Ps16
Bypass outlet static pressure
- Ps6
LPT outlet static pressure
- SE1
Fan efficiency
- SE2
HPC efficiency
- SE3
HPT efficiency
- SE4
LPT efficiency
- SW1
Fan flow
- SW2
HPC flow
- SW3
HPT flow
- SW4
LPT flow
- T22
Fan outlet temperature
- T3
Compressor outlet temperature
- T5
LPT outlet temperature
- u
Control vector
- v
Measurement noise
- w
Process noise
- x
State vector
- y
Vector of measured outputs
References
1. Simon DL. An integrated architecture for on-board aircraft: engine performance trend monitoring and gas path fault diagnostics. Cleveland, OH, USA: Technical Report for National Aeronautics and Space Administration, 2010.Search in Google Scholar
2. Garg S. Propulsion controls and diagnostics research at NASA Glenn Research Center. NASA/TM-2007-215028, 2007.10.2514/6.2007-5713Search in Google Scholar
3. Litt JS, Simon DL, Gary S. A survey of intelligent control and health management technologies for aircraft propulsion systems. NASA/TM-2005-213622, 2005.Search in Google Scholar
4. Volponi A. Data fusion for enhanced aircraft engine prognostics and health management. NASA/CR-2005-214055, 2005.Search in Google Scholar
5. Loboda I, Feldshteyn Ya, Ponomaryov V. Neural networks for gas turbine fault identification: multilayer perceptron or radial basis network. Int J Turbo Jet Engine 2012;29:37–48.10.1115/GT2011-46752Search in Google Scholar
6. Naderi E, Meskin N, Khorasani K. Nonlinear fault diagnosis of jet engines by using a multiple model-based approach. J Eng Gas Turbines Power Trans ASME 2012;134:1–8.10.1115/GT2011-45143Search in Google Scholar
7. Doel DL. An assessment of weighted-least-squares-based gas path analysis. J Eng Gas Turbines Power Trans ASME 1994;116:336–73.10.1115/93-GT-119Search in Google Scholar
8. Kong C, Kho S, Park G. Development of practical integral condition monitoring system for a small turbojet engine using MATLAB/SIMULINK and LabVIEW. Int J Turbo Jet Engines 2013;31:73–86.10.1515/tjj-2013-0030Search in Google Scholar
9. Kobayashi T, Simon DL. A hybrid neural network-genetic algorithm technique for aircraft engine performance diagnostics. In Proceedings of the 37th AIAA/ASME/SAE/ASEE Joint Propulsion Conference, Salt Lake City, UT, USA, 8–11 July 2001.10.2514/6.2001-3763Search in Google Scholar
10. Zhou WX. Research on object-oriented modeling and simulation for aeroengine and control system. Ph.D. Thesis, Nanjing University of Aeronautics and Astronautics, Nanjing, China, 2006.Search in Google Scholar
11. Lu F, Huang J. Engine component performance prognostics based on decision fusion. Acta Aeronaut Astronaut Sin 2009;30:1795–800.Search in Google Scholar
12. Doel DL. TEMPER – a gas path analysis tool for commercial jet engines. ASME J Eng Gas Turbine Power 1994;116:82–9.10.1115/92-GT-315Search in Google Scholar
13. Volponi AJ. Sensor error compensation in engine performance diagnostics. ASME Paper 94-GT-58, international gas turbine and aeroengine congress and exposition, The Hague, Netherlands, 1994.10.1115/94-GT-058Search in Google Scholar
14. Kerr LJ, Nemec TS, Gallops GW. Real-time estimation of gas turbine engine damage using a control based Kalman filter algorithm. ASME Paper 91-GT-216, international gas turbine and aeroengine congress and exposition, Orlando, FL, 1991.10.1115/91-GT-216Search in Google Scholar
15. Simon D. A comparison of filtering approaches for aircraft engine health estimation. Aerospace Sci Technol 2008;12:276–84.10.1016/j.ast.2007.06.002Search in Google Scholar
16. Sun JG, Vasilyev V, Ilyasov B. Advanced multivariable control systems of aeroengines. Beijing, China: Beijing University of Aeronautics & Astronautics, 2005.Search in Google Scholar
©2016 by De Gruyter
Articles in the same Issue
- Frontmatter
- Experimental Investigation on the Ignition Delay Time of Plasma-Assisted Ignition
- Effect of Inlet Clearance on the Aerodynamic Performance of a Centrifugal Blower
- Alternative Method to Simulate a Sub-idle Engine Operation in Order to Synthesize Its Control System
- Aerodynamic Design and Numerical Analysis of Supersonic Turbine for Turbo Pump
- A Comparison of Hybrid Approaches for Turbofan Engine Gas Path Fault Diagnosis
- Optimization of a Turboprop UAV for Maximum Loiter and Specific Power Using Genetic Algorithm
- Taguchi Based Regression Analysis of End-Wall Film Cooling in a Gas Turbine Cascade with Single Row of Holes
- Numerical Investigation of Cowl Lip Adjustments for a Rocket-Based Combined-Cycle Inlet in Takeoff Regime
Articles in the same Issue
- Frontmatter
- Experimental Investigation on the Ignition Delay Time of Plasma-Assisted Ignition
- Effect of Inlet Clearance on the Aerodynamic Performance of a Centrifugal Blower
- Alternative Method to Simulate a Sub-idle Engine Operation in Order to Synthesize Its Control System
- Aerodynamic Design and Numerical Analysis of Supersonic Turbine for Turbo Pump
- A Comparison of Hybrid Approaches for Turbofan Engine Gas Path Fault Diagnosis
- Optimization of a Turboprop UAV for Maximum Loiter and Specific Power Using Genetic Algorithm
- Taguchi Based Regression Analysis of End-Wall Film Cooling in a Gas Turbine Cascade with Single Row of Holes
- Numerical Investigation of Cowl Lip Adjustments for a Rocket-Based Combined-Cycle Inlet in Takeoff Regime
