ACTA AERONAUTICAET ASTRONAUTICA SINICA >
Research on Gas Fault Fusion Diagnosis of Aero-engine Component
Received date: 2013-07-09
Revised date: 2014-02-18
Online published: 2014-06-20
Supported by
National Natural Science Foundation of China(51006052,61104067); Aeronautical Science Foundation of China(20110652003); The Fundamental Research Funds for Central Universities(NZ2012104); Graduate Student Research and Innovation Program of Jiangsu Province(CXZZ12_0169)
A model-based and data-driven-based aero-engine component fault fusion diagnosis method is presented in this paper. The extreme learning machine (ELM) is used to the data-driven-based component fault diagnosis. However, the ELM input weights and hidden layer biases are generated randomly, which usually leads to more nodes in the hidden layer and poor generalization ability. To overcome these drawbacks of ELM, an improved differential evolution (IDE) is used to optimize the input weights and the hidden layer biases. The optimization is carried out according to the root mean squared error (RMSE) of the validation set and the norm of the output weights. Meantime, singular value decomposition (SVD)-based Reduced-dimensional Kalman (SVD-Kalman) filters are used to estimate the health parameters which can solve the problem of limited number of sensors in the model based diagnosis method. To improve the accuracy of fault diagnosis for an aero-engine component, the prediction results of health parameters based on both methods are fused by the improved recursive reduced least squares support vector regression (IRR-LSSVR). Simulation results show that compared with either the model-based or data-driven-based approach, the proposed fusion method improves the accuracy of fault diagnosis significantly.
LI Yebo , LI Qiuhong , HUANG Xianghua , ZHAO Yongping . Research on Gas Fault Fusion Diagnosis of Aero-engine Component[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2014 , 35(6) : 1612 -1622 . DOI: 10.7527/S1000-6893.2013.0543
[1] Garg S. Controls and health management technologies for intelligent aerospace propulsion systems, AIAA-2004-0949. Reston: AIAA, 2004.
[2] Delaat J C, Merrill W C. Advanced detection, isolation, and accommodation of sensor failures in turbofan engines, NASA-TP-2925. Washington, D.C.: NASA, 1990.
[3] Garg S, Schadow K, Horn W, et al. Sensor and actuator needs for more intelligent gas turbine engines, NASA/TM-2010-216746. Washington, D.C.: NASA, 2010.
[4] Xu Q H, Shi J. Fault diagnosis for aero-engine applying a new multi-class support vector algorithm[J]. Chinese Journal of Aeronautics, 2006, 19(1): 175-182.
[5] Alag G, Gilyard G. A proposed Kalman filter algorithm for estimation of unmeasured output variables for an F100 turbofan engine, AIAA-1990-1920. Reston: AIAA, 1990.
[6] Kobayashi T, Simon D L. Application of a bank of Kalman filters for aircraft engine fault diagnositcs, NASA/TM-2003-212526. Washington, D.C.: NASA, 2003.
[7] Mattern D L, Jaw L C, Guo T H, et al. Using neural networks for sensor validation, AIAA-1998-3547. Reston: AIAA, 1998.
[8] Lu F, Huang J Q. Engine component performance prognostics based on decision fusion[J]. Acta Aeronautica et Astronautica Sinica, 2009, 30(10): 1795-1800. (in Chinese) 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.
[9] Fu Q, Su B K. Study of fault-diagnosing system of turntable based on hierarchical information fusion[J]. Journal of Harbin Institute of Technology, 2006, 38(11): 1906-1909.(in Chinese) 付强, 苏宝库. 基于多级信息融合的转台故障诊断系统研究[J]. 哈尔滨工业大学学报, 2006, 38(11): 1906-1909.
[10] Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: theory and applications[J]. Neurocomputing, 2006, 70(1-3): 489-501.
[11] 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.
[12] Litt J S. An optimal orthogonal decomposition method for Kalman filter-based turbofan engine thrust estimation, NASA/TM-2005-213864. Washington, D.C.: NASA, 2005.
[13] Zhao Y P, Sun J G, Du Z H, et al. An improved recursive reduced least square support vector regression[J]. Neurocomputing, 2012, 87: 1-9.
[14] Zhu Q Y, Qin A K, Suganthan P N, et al. Evolutionary extreme learning machine[J]. Pattern Recognition, 2005, 38(10): 1759-1763.
[15] Bartlett P L. The sample complexity of pattern classification with neural networks: the size of the weights is more important than the network[J]. IEEE Transactions on Information Theory, 2005, 44(2): 525-536.
[16] Li Y B. Componentization modeling and performance parameters estimation of aero-engine. Nanjing: College of Energy & Power Engineering, Nanjing University of Aeronautics and Astronautics, 2011. (in Chinese) 李业波. 航空发动机组件化建模及性能参数估计.南京: 南京航空航天大学能源与动力学院, 2011.
[17] Zheng D Z. Linear system theory[M]. Beijing: Tsinghua University Press, 2004: 70-117. (in Chinese) 郑大钟. 线性系统理论[M]. 北京: 清华大学出版社,2002: 70-117.
[18] Zhao Y P, Sun J G. Recursive reduced least square support vector regression[J]. Pattern Recognition, 2009, 42(5): 837-842.
[19] Suykens J A K, Vandewalle J. Least squares support vector machine classifiers[J]. Neural Processing Letter, 1999, 9(3): 293-300.
[20] Zhang X D. Matrix analysis and applications[M]. Beijing: Tsinghua University Press, 2004: 68-69. (in Chinese) 张贤达. 矩阵分析与应用[M]. 北京: 清华大学出版社, 2004: 68-69.
/
| 〈 |
|
〉 |
CJA