Application of fuzzy logic for fault isolation of jet engines

被引:57
作者
Ganguli, R [1 ]
机构
[1] Indian Inst Sci, Dept Aerosp Engn, Bangalore 560012, Karnataka, India
来源
JOURNAL OF ENGINEERING FOR GAS TURBINES AND POWER-TRANSACTIONS OF THE ASME | 2003年 / 125卷 / 03期
关键词
D O I
10.1115/1.1470481
中图分类号
TH [机械、仪表工业];
学科分类号
0802 ;
摘要
A fuzzy logic system is developed,for gas turbine module fault isolation. Inputs to the fuzzy logic system are measurement deviations of gas path parameters from a "good" baseline engine. The gas path measurements used are exhaust gas temperature, low and high rotor speed, and fuel flow. These sensor measurements are available on most jet engines. The Jazzy logic system uses rules developed from performance influence coefficients to isolate the module fault while accounting for uncertainty in the gas path measurements. Tests with simulated data show the fuzzy system isolates module faults with accuracy of over 95%. In addition, the fuzz logic system shows good performance even with poor quality data. Additional pressure and temperature measurements between the compressor and before the burner help to increase the accuracy of fault isolation at high levels of uncertainty and when modeling assumptions weaken.
引用
收藏
页码:617 / 623
页数:7
相关论文
共 21 条
[1]   A METHOD FOR FUZZY RULES EXTRACTION DIRECTLY FROM NUMERICAL DATA AND ITS APPLICATION TO PATTERN-CLASSIFICATION [J].
ABE, S ;
LAN, MS .
IEEE TRANSACTIONS ON FUZZY SYSTEMS, 1995, 3 (01) :18-28
[2]   FUZZY SET-THEORY IN MEDICAL DIAGNOSIS [J].
ADLASSNIG, KP .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1986, 16 (02) :260-265
[3]  
CHI Z, 1998, FUZZY ALGORITHMS APP
[4]  
CHI Z, 1993, IEEE T FUZZY SYST, V4, P24
[5]   The application of expert systems and neural networks to gas turbine prognostics and diagnostics [J].
DePold, HR ;
Gass, FD .
JOURNAL OF ENGINEERING FOR GAS TURBINES AND POWER-TRANSACTIONS OF THE ASME, 1999, 121 (04) :607-612
[6]  
Doel D. L., 1994, 92GT315 ASME
[7]  
GALLOPS GW, 1992, 923746 AIAA
[8]  
HONG XL, 2000, IEEE T NEURAL NETWOR, V11, P103
[9]  
KERR LJ, 1991, 91GT216 ASME
[10]  
Kosko B., 1997, FUZZY ENG