基于ImOS-ELM的航空发动机传感器故障自适应诊断技术
收稿日期: 2012-11-29
修回日期: 2013-04-22
网络出版日期: 2013-04-26
基金资助
国家自然科学基金(51006052);航空科学基金(20110652003);中央高校基本科研业务费专项基金(NZ2012104);江苏省2012年度普通高校研究生科研创新计划(CXZZ12_0169)
Sensor Fault Adaptive Diagnosis of Aero-engines Based on ImOS-ELM
Received date: 2012-11-29
Revised date: 2013-04-22
Online published: 2013-04-26
Supported by
National Natural Science Foundation of China (51006052);Aeronautical Science Foundation of China (20110652003);Fundamental Research Funds for Central Universities (NZ2012104);Graduate Student Research and Innovation Program of Jiangsu Province (CXZZ12_0169)
针对在线贯序极端学习机(OS-ELM)算法矩阵容易陷入奇异和病态、在算法开始阶段不具有预测能力的问题,结合选择策略提出一种改进的OS-ELM (ImOS-ELM)算法。该算法通过引入正则化因子,消除了矩阵奇异和病态的问题,提高了预测精度,并使得算法能够在初始阶段就具有预测能力。同时以泛化能力为判断依据,通过选择策略对输出权值进行选择性地更新,该算法在很大程度上缩短了训练时间。为了验证算法的有效性,用时间序列数据进行了仿真测试验证。最后,将ImOS-ELM算法应用于航空发动机传感器故障的诊断与隔离。仿真结果表明,该算法能够对航空发动机双传感器偏置故障和单传感器漂移故障进行有效地诊断与隔离,并具有较高的预测精度和实时性。
李业波 , 李秋红 , 王健康 , 黄向华 , 赵永平 . 基于ImOS-ELM的航空发动机传感器故障自适应诊断技术[J]. 航空学报, 2013 , 34(10) : 2316 -2324 . DOI: 10.7527/S1000-6893.2013.0222
On-line sequential extreme learning machine (OS-ELM) algorithm is likely to fall into matrix singularity and ill-posedness, and it has no predictive ability at the beginning stage of training. Hence, in this paper, an improved scheme with selection strategy, named improved OS-ELM (ImOS-ELM) algorithm, is proposed. This algorithm overcomes matrix singularity and ill-posedness by regularization, which can improve the predicting accuracy and achieve predictive ability from the start stage of training. Meantime, the output layer weight vector is updated selectively based on generalization capability, and it reduces considerably the mean training time of the algorithm. In order to verify the effectiveness of the proposed algorithm, simulation tests are carried out using time series data, which show that the proposed algorithm achieves higher accuracy and faster speed. Finally, ImOS-ELM algorithm is applied to the sensor fault detection and isolation of an aero-engine. The simulation results show that the sensor faults diagnosis method using the proposed algorithm is able to detect and isolate faults of double-sensor failures and single-sensor drift, which also proves the validity and feasibility of the proposed algorithm.
[1] Garg S. Controls and health management technologies for intelligent aerospace propulsion systems. AIAA-2004-949, 2004.
[2] Delaat J C, Merrill W C. Advanced detection, isolation, and accommodation of sensor failures in turbofan engines. NASA Technical Paper-2925, 1990.
[3] Garg S, Schadow K, Horn W, et al. Sensor and actuator needs for more intelligent gas turbine engines. NASA/TM-2010-216746, 2010.
[4] Wallhagen R E, Arpasi D J. Self-teaching digital-computer program for fail-operational control of a turbojet engine in a sea-level test stand. NASA-TM-X-3043, 1974.
[5] Alag G, Gilyard G. A proposed Kalman filter algorithm for estimation of unmeasured output variables for an F100 turbofan engine. AIAA-1990-1920, 1990.
[6] Kobayashi T, Simon D L. Application of a bank of Kalman filters for aircraft engine fault diagnositcs. NASA/TM-2003-212526, 2003.
[7] Mattern D L, Jaw L C, Guo T H, et al. Using neural networks for sensor validation. AIAA-1998-3547, 1998.
[8] Cai K L, Xie S S, Yang W, et al. Fault diagnosis and adaptive reconfiguration control for sensors in aeroengine based on improved least squares support vector. Journal of Aerospace Power, 2008, 23(6): 1118-1126. (in Chinese) 蔡开龙, 谢寿生, 杨伟, 等. 基于改进LS-SVM的航空发动机传感器故障诊断与自适应重构控制. 航空动力学报, 2008, 23(6): 1118-1126.
[9] Lu F, Huang J Q, Chen Y, et al. Research on sensor fault diagnosis of aero-engine based on data fusion of SPSO-SVR. Journal of Aerospace Power, 2009, 24(8): 1856-1865. (in Chinese) 鲁峰, 黄金泉, 陈煜, 等. 基于SPSO-SVR的融合航空发动机传感器诊断. 航空动力学报, 2009, 24(8): 1856-1865.
[10] Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: theory and applications. Neurocomputing, 2006, 70(1): 489-501.
[11] Zhang X, Wang H L. Time series prediction based on sequential regularized extreme learning machine and its application. Acta Aeronautica et Astronautica Sinica, 2011, 32(7): 1302-1308. (in Chinese) 张弦, 王宏力. 基于贯序正则极端学习机的时间序列预测及其应用. 航空学报, 2011, 32(7): 1302-1308.
[12] Huang G B, Liang N Y, Rong H J, et al. Online sequential extreme learning machine. The IASTED International Conference on Computational Intelligence (CI 2005), 2005.
[13] Huynh H T, Won Y. Regularized online sequential learning algorithm for single-hidden layer feedforward neural networks. Pattern Recognition Letters, 2011, 32(14): 1930-1935.
[14] Zhang X D. Matrix analysis and applications. Beijing: Tsinghua University Press, 2004: 68-69. (in Chinese) 张贤达. 矩阵分析与应用. 北京: 清华大学出版社, 2004: 68-69.
[15] Time Series Prediction Group [EB/OL]. (2009-03-27)[2012-11-29]. http://www.cis.hut.fi/projects/tsp/? page =Timeseries.
[16] Zhao Y P, Sun J G. Fast online application for hard support vector regression and its application to analytical redundancy for aeroengines. Chinese Journal of Aeronautics, 2010, 23(2): 145-152.
[17] Zhao Y P, Sun J G, Wang J K. Online parsimonious least squares support vector regression and its application. Transactions of Nanjing University of Aeronautics & Astronautics, 2009, 26(4): 280-287.
/
| 〈 |
|
〉 |
CJA