As the flight envelope is widening continuously and operational capability is improving sequentially, gas turbine engines are faced with new challenges of increased operation and maintenance requirements for efficiency, reliability, and safety. The measures for security and safety and the need for reducing the life cycle cost make it necessary to develop more accurate and efficient monitoring and diagnostic schemes for the health management of gas turbine components. Sensors along the gas path are one of the components in gas turbines that play a crucial role in turbofan engines owing to their safety criticality. Failures in sensor measurements often result in serious problems affecting flight safety and performance. Therefore, this study aims to develop an online diagnosis system for gas path sensor faults in a turbofan engine. The fault diagnosis system is designed and implemented using a genetic algorithm optimized recursive reduced least squares support vector regression algorithm. This method uses a reduction technique and recursion strategy to obtain a better generalization performance and sparseness, and exploits an improved genetic algorithm to choose the optimal model parameters for improving the training precision. The effectiveness of the sensor fault diagnosis system is then validated through typical fault modes of single and dual sensors.
TsoutsanisEMeskinNBenammarM, et al.A dynamic prognosis scheme for flexible operation of gas turbines. Appl Energy2016; 164: 686–701.
2.
LiYGNikitsaranontP. Gas turbine performance prognostic for condition-based maintenance. Appl Energy2009; 86: 2152–2161.
3.
MiguezMEJohnPJennionsIK. A review of integrated vehicle health management tools for legacy platforms: Challenges and opportunities. Prog Aerosp Sci2013; 56: 19–34.
4.
Behbahani A and Semega K. Sensing challenges for controls and PHM in the hostile operating conditions of modern turbine engine. In: 44th AIAA/ASME/SAE/ASEE Joint Propulsion Conference & Exhibit, Hartford, CT, USA, 21–23 July 2008, paper no. AIAA 2008-5280.
5.
Santi L, Sowers T and Aguilar B. Optimal sensor selection for health monitoring systems. In: 41st AIAA/ASME/SAE/ASEE Joint Propulsion Conference & Exhibit, Tucson, Arizona, USA, 10–13 July 2005, paper no. AIAA 2005-4485.
6.
MathioudakisKKamboukosP. Assessment of the effectiveness of gas path diagnosis schemes. ASME J Eng Gas Turbines Power2006; 128: 57–63.
7.
Kamboukos P, Oikonomou P, Stamatis A, et al. Optimizing diagnostic effectiveness of mixed turbofans by means of adaptive modeling and choice of appropriate monitoring parameters. In: AVT Symposium on Monitoring and Management of Gas Turbine Fleets for Extended Life and Reduced Costs, Manchester, UK, 8–11 October 2001, Defense Technical Information Center Compilation Pat Notice ADP014126.
8.
BorguetSLeonardO. The fisher information matrix as a relevant tool for sensor selection in engine health monitoring. Int J Rotating Mach2008; 2008: 784749–784749.
9.
StamatisMMathioudakisKPapailiouK. Optimal measurement and health index selection for gas turbine performance status and fault diagnosis. ASME J Eng Gas Turbines Power1992; 114: 209–216.
10.
Jasmani MS, Li YG and Ariffin Z. Measurement selection for multi-component gas path diagnostics using analytical approach and measurement subset concept. J Eng Gas Turbines Power 2011; 133: 111701.
11.
SimonDLRinehartAW. Sensor selection for aircraft engine performance estimation and gas path fault diagnostics. ASME J Eng Gas Turbines Power2016; 138: 071201.1–071201.11.
12.
MinCLiangQHHaiLT. An approach for optimal measurements selection on gas turbine engine fault diagnosis. ASME J Eng Gas Turbines Power2015; 137: 071203.1–071203.9.
13.
HanumanthanHStittALaskaridisP, et al.Severity estimation and effect of operational parameters for civil aircraft jet engines. Proc IMechE, Part G: J Aerospace Engineering2012; 226: 1544–1561.
14.
Wallhagen RE and Arpasi DJ. Self-teaching digital computer program for fail operational control of a turbo-jet engine in a sea level test stand. AIAA paper no. TM-X-3043, 1974.
15.
RomesisCMathioudakisK. Setting up of a probabilistic neural network for sensor fault detection including operation with component faults. ASME J Eng Gas Turbines Power2003; 125: 634–641.
16.
VaniniZNSMeskinNKhorasaniK. Multiple-model sensor and components fault diagnosis in gas turbine engines using autoassociative neural networks. ASME J Eng Gas Turbines Power2014; 136: 091603.1–091603.16.
17.
SarkarSJinXRayA. Data-driven fault detection in aircraft engines with noisy sensor measurements. ASME J Eng Gas Turbines Power2011; 133: 081602–081602.
18.
Bettocchi R and Spina PR. ARX linear model set up for fault diagnosis of gas turbine sensors. In: ASME 1997 International Gas Turbine and Aeroengine Congress and Exhibition, Orlando, Florida, USA, 2–5 June 1997, paper no. ASME 97-GT-027.
19.
KobayashiTSimonDL. Evaluation of an enhanced band of Kalman filters for in-flight aircraft engine sensor fault diagnostics. ASME J Eng Gas Turbines Power2005; 127: 497–504.
20.
LuFChenYHuangJQ, et al.An integrated nonlinear model based approach to gas turbine engine sensor fault diagnostics. Proc IMechE, Part G: J Aerospace Engineering2014; 225: 2007–2021.
21.
OgajiSMarinaiLSampathS, et al.Gas turbine fault diagnostics: A fuzzy-logic approach. Appl Energy2005; 82: 81–89.
22.
AretakisNMathioudakisKStamatisA. Identification of sensor fault on turbofan engines using pattern recognition techniques. Control Eng Pract2004; 12: 827–836.
23.
PalmTFastMThernM. Gas turbine sensor validation through classification with artificial neural networks. Appl Energy2011; 88: 3898–3904.
24.
RahmeSMeskinN. Adaptive sliding mode observer for sensor fault diagnosis of an industrial gas turbine. Control Eng Pract2015; 38: 57–74.
25.
OgajiSSampathSMarinaiL, et al.Evolution strategy for gas-turbine fault-diagnoses. Appl Energy2005; 81: 222–230.
26.
SaimuruganMRamachandranKISugumaranV, et al.Multi component fault diagnosis of rotational mechanical system based on decision tree and support vector machine. Expert Syst Appl2011; 38: 3819–3826.
27.
ZhouDJZhangHSWengSL. A new gas path fault diagnostic method of gas turbine based on support vector machine. ASME J Eng Gas Turbines Power2015; 137: 102605.1–102605.6.
28.
SuykensJAKGestelTVBrabanterJD, et al.Least squares support vector machines, Singapore: World Scientific Pub. Co., 2002.
29.
CaiKLXieSSYangW, et al.Fault diagnosis and adaptive reconfiguration control for sensors in aeroengine based on improved least squares support vector machine. J Aerospace Power2008; 23: 1118–1126.
30.
HuYYangYCZhangSY, et al.Comparison of linear models for gas turbine performance. Proc IMechE, Part G: J Aerospace Engineering2014; 228: 1291–1301.
31.
ShiLYZhuJTHuY, et al.Optimization of gas path sensors of turbofan engine based on improved genetic algorithm. Chinese J Northwest Polytech Univ2017; 35: 1–8.
32.
ZhaoYPSunJG. Recursive reduced least squares support vector regression. Pattern Recognit2009; 42: 837–842.
33.
XuQHShiJ. Some studies in aeroengine fault diagnosis using support vector machines. Acta Aeronautica et Astronautica Sinica2005; 26: 686–690.
34.
ZhaoYPSunJG. Recursive reduced least squares support vector regression. Pattern Recognit2009; 42: 837–842.
35.
Lee YJ and Mangasarian OL. RSVM: Reduced support vector machines. In: Proceedings of the 1st SIAM international conference on data mining, Chicago, USA, 5–7 April 2001, Technical Report 00-07.
36.
JiaoLBoLWangL. Fast sparse approximation for least squares support vector machine. IEEE Trans Neural Networks2007; 18: 685–697.
37.
LuFHuangJQChenY, et al.Research on sensor fault diagnosis of aero-engine based on data fusion of SPSO-SVR. J Aerospace Power2009; 24: 1856–1865.
38.
LuFHuangJQ. Fault diagnosis for aero-engine based on ESVR information fusion. J Basic Sci Eng2010; 18: 982–989.
39.
FengZGShidaKWangQ. Sensor fault detection and data recovery based on LS-SVM predictor. Chinese J Sci Ins2007; 28: 193–197.
