Sensor fault diagnosis of aero-engine based on DE-RLSSVM algorithm
-
摘要: 为了使约简最小二乘支持向量机(RLSSVM)具有更好的稀疏性和泛化能力,利用微分进化(DE)算法选择RLSSVM的支持向量,提出了DE-RLSSVM算法.在benchmark回归数据集上的仿真试验表明该算法具有很好的稀疏性和泛化能力.然后将该算法用于航空发动机传感器故障的诊断,提出了基于DE-RLSSVM算法的航空发动机传感器故障诊断方法.该方法利用DE-RLSSVM算法对传感器故障进行监测,然后进行定位和隔离.数字仿真结果表明该传感器故障诊断系统能够实现对航空发动机传感器硬故障的检测与隔离.Abstract: In order to improve the generalization capability and sparsity of reduced least square support vector machine (RLSSVM), DE-RLSSVM was presented, whereby differential evolution (DE) algorithm was used to select the support vector of RLSSVM. Experiments on benchmark regression data sets show that the presented algorithm has good generalization and sparsity capabilities. Then, the presented algorithm was applied to sensor fault diagnosis of aero-engine. DE-RLSSVM algorithm was used to detected sensors faults, then to locate and isolate the faults. The simulations show that the sensor fault diagnosis system using the presented algorithm can detect and isolate hardware faults of sensor of aero-engine.
-
Key words:
- aero-engine /
- sensor /
- fault diagnosis /
- support vector machine /
- differential evolution
-
[1] Garg S.Controls and health management technologies for intelligent aerospace propulsion systems[R].AIAA-2004-0949,2004. [2] Link C.Recent advancements in aircraft engine health management (EHM) technologies and recommendations for next step[R].ASME Paper GT2005-68625,2005. [3] Delaat J C,Merrill W C.Advanced detection,isolation,and accommodation of sensor failures in turbofan engines[R].NASA Technical Paper-2925,1990. [4] Garg S,Schadow K,Horn W,et al.Sensor and actuator needs for more intelligent gas turbine engines[R].NASA/TM-2010-216746,2010. [5] XU Qihua,SHI Jun.Fault diagnosis for aero-engine applying a new multi-class support vector algorithm[J].Chinese Journal of Aeronautics,2006,19(1):175-182. [6] Alag G,Gilyard G.A proposed Kalman filter algorithm for estimation of unmeasured output variables for an F100 turbofan engine[R].AIAA 90-1920,1990. [7] Kobayashi T,Simon D L.Application of a bank of Kalman filters for aircraft engine fault diagnositcs[R].NASA/TM-2003-212526,2003. [8] Mattern D L,Jaw L C,Guo T H,et al.Using neural networks for sensor validation[R].AIAA 98-3547,1998. [9] 鲁峰,黄金泉.航空发动机部件性能参数融合预测[J].航空学报,2009,30(10):1795-1800. LU Feng,HUANG Jinquan.Engine component performance prognostics based on decision fusion[J].Acta Aeronautica et Astronautica Sinica,2009,30(10):1795-1800.(in Chinese) [10] Pecht M G.Prognostics and health management of electronics[M].Hoboken,US:John Wiley and Sons,2008. [11] Tobon-Mejia D A,Medjiaher K,Zerhouni N,et al.A data-driven failure prognostics method based on mixture of Gaussians hidden Markov models[J].IEEE Transactions on Reliability,2012,61(2):491-503. [12] 李晗,萧德云.基于数据驱动的故障诊断方法综述[J].控制与决策,2011,26(1):1-9. LI Han,XIAO Deyun.Survey on data driven fault diagnosis methods[J].Control and Decision,2011,26(1):1-9.(in Chinese) [13] Zhao J,Chen B,Shen J.A hybrid ANN-ES system for dynamic fault diagnosis of hydrocracking process[J].Computers and Chemical Engineering,1997,21(20):929-933. [14] Vapnik V N.The nature of statistical theory[M].New York:Springer-Verlag,1995. [15] Suykens J A K,Vandewalle J.Least squares support vector machine classifiers[J].Neural Processing Letters,1999,9(3):293-300. [16] 李业波,李秋红,黄向华,等.航空发动机传感器故障与部件故障诊断技术[J].北京航空航天大学学报,2013,39(9):1174-1180. LI Yebo,LI Qiuhong,HUANG Xianghua,et al.Fault diagnosis for sensors and components of aero-engine[J].Journal of Beijing University of Aeronautics and Astronautics,2013 39(9):1174-1180.(in Chinese) [17] Lee J,Lee D.An improved cluster labeling method for support vector clustering[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(3):461-464. [18] Storn R,Price K.Differential evolution:a simple and efficient heuristic for global optimization over continuous spaces[J].Journal of Global Optimization,1997,11(4):341-359.
点击查看大图
计量
- 文章访问数: 1484
- HTML浏览量: 1
- PDF量: 974
- 被引次数: 0