Sensor Fault Detection for EHA System Based on Adaptive Kernel Principal Component Analysis

Journal of Propulsion Technology ›› 2014, Vol. 35 ›› Issue (6): 838-845.

Previous Articles Next Articles

Sensor Fault Detection for EHA System Based on Adaptive Kernel Principal Component Analysis

School of Aeronautics and Astronautics Engineering，Air Force Engineering University，Xi ’ an 710038，China;School of Aeronautics and Astronautics Engineering，Air Force Engineering University，Xi ’ an 710038，China;School of Aeronautics and Astronautics Engineering，Air Force Engineering University，Xi ’ an 710038，China;School of Aeronautics and Astronautics Engineering，Air Force Engineering University，Xi ’ an 710038，China;School of Air Traffic Control and Navigation，Air Force Engineering University，Xi ’ an 710051，China

Published:2021-08-15

基于自适应核主元分析的EHA系统传感器故障检测

朱喜华¹,李颖晖¹,刘聪¹,李宁¹,张鹏²

空军工程大学航空航天工程学院，陕西西安 710038;空军工程大学航空航天工程学院，陕西西安 710038;空军工程大学航空航天工程学院，陕西西安 710038;空军工程大学航空航天工程学院，陕西西安 710038;空军工程大学空管领航学院，陕西西安 710051

作者简介:朱喜华(1985—)，男，博士生，研究领域为传感器优化配置及其故障诊断。E-mail:zxh2004_@sina.com
基金资助:
国家自然科学基金(61074007)；陕西省自然科学基金(2012JM8016)；总装预研基金。

Abstract

Abstract: For the problem that it is hard to choose the kernel function of kernel principal component analysis ( KPCA )， a novel adaptive KPCA method for sensor fault detection is presented. The kernel function is modified adaptively according to the training date ， so the kernel function can adapt to the given training date. Besides ， the common method for data standardization processing is modified ， an‘equalization’processing method is presented ， which can eliminate the influence caused by amplitudes and dimensions of different variables ， and the entire information of the training data can be reflected at the same time. Finally ， an application of the proposed method is given in the sensor fault detection for airborne Electro-Hydrostatic Actuator ( EHA ) system ， and the simulation results show that the proposed method is more advanced than the general KPCA ， and it has much nicer performance in fault detection.

Key words: Adaptive Kernel Function；Kernel Principal Component Analysis；Sensor；Fault Detection；EHA System

摘要： 针对核主元分析(KPCA)方法难以选择合适核函数的问题，提出了一种基于自适应核主元分析的传感器故障检测方法，根据训练数据对核函数进行自适应修正，使核函数适应给定的训练数据。对常规数据标准化处理方法进行了改进，提出了一种“均值化”的处理方法，使处理后的数据既能消除不同变量幅值和量纲的影响，又能反映训练数据的全部信息。将此方法应用于机载电动静液作动器(Electro-Hydrostatic Actuator，EHA)系统的传感器故障检测，结果表明，此方法比常规KPCA方法更为先进，具有更好的故障检测性能。

关键词: 自适应核函数；核主元分析；传感器；故障检测；EHA系统

ZHU Xi-hua¹,LI Ying-hui¹,LIU Cong¹,LI Ning¹,ZHANG Peng². Sensor Fault Detection for EHA System Based on Adaptive Kernel Principal Component Analysis[J]. Journal of Propulsion Technology, 2014, 35(6): 838-845.

朱喜华,李颖晖,刘聪,李宁,张鹏. 基于自适应核主元分析的EHA系统传感器故障检测[J]. 推进技术, 2014, 35(6): 838-845.

References

[1] Wang S W， Xiao F. AHU Sensor Fault Diagnosis Using Principal Component Analysis Method[J]. Energy and Buildings ， 2004， 36(2): 147-160.
[2] 仇韬，张清峰，丁艳军，等. PCA在非线性系统传感器故障检测和重构中的应用[J]. 清华大学学报， 2006， 46(5): 708-711.
[3] Harkat M F， Mourot G， Ragot J. An Improved PCA Scheme for Sensor FDI: Application to an Air Quality Monitoring Network[J]. Journal of Process Control ， 2006， 16(6): 625-634.
[4] 毕小龙，王洪跃，司风琪，等. 基于核主元分析的传感器故障检测[J]. 动力工程， 2007， 27(4): 555-559.
[5] 谢廷峰，刘洪刚，吴建军. 基于主元分析法的液体火箭发动机传感器故障检测与诊断[J]. 宇航学报， 2007， 28(6): 1668-1672.
[6] 李冬辉，王乐英，李晟. 基于PCA的空调系统传感器故障诊断[J]. 电工技术学报， 2008， 23(6): 130-136.
[7] Sharifi M. Sensor Fault Diagnosis Using Principal Component Analysis[D]. Texas: The Office of Graduate Studies of Texas A&M University ， 2009.
[8] Benaicha A， Mourot G， Benothman K， et al. Determination of Principal Component Analysis Models for Sensor Fault Detection and Isolation[J]. International Journal of Control， Automation and Systems ， 2013， 11(2): 296-305.
[9] Lee J M， Yoo C K， Choi S W， et al. Nonlinear Process Monitoring Using Kernel Principal Component Analysis[J]. Chemical Engineering Science ， 2004， 59(1): 223-234.
[10] 胡金海，谢寿生，陈卫，等. 基于核函数主元分析的航空发动机故障检测方法[J]. 推进技术， 2008， 29(1): 79-83. (HU Jin-hai， XIE Shou-sheng， CHEN Wei， et al. An Aeroengine Fault Detection Method Based on Kernel Principal Component Analysis[J]. Journal of Propulsion Technology ， 2008， 29(1): 79-83.)
[11] 张冀. 基于多源信息融合的传感器故障诊断方法研究[D]. 北京:华北电力大学， 2008.
[12] Zhang， Y. Enhanced Statistical Analysis of Nonlinear Processes Using KPCA， KICA and SVM[J]. Chemical Engineering Science ， 2009， 64(5): 801-811.
[13] 刘永斌. 基于非线性信号分析的滚动轴承状态监测诊断研究[D]. 合肥: 中国科学技术大学， 2011.
[14] 岳朝龙，黄永兴，严忠. SAS系统与经济统计分析[M]. 安徽: 中国科学技术大学出版社， 2003.
[15] Xiong H， Swamy M N S， Ahmad M O. Optimizing the Kernel in the Empirical Feature Space[J]. IEEE Transactions on Neural Networks ， 2005， 16(2): 460-474.
[16] Chen B， Liu H， Bao Z. Optimizing the Data-Dependent Kernel Under a Unified Kernel Optimization Framework[J]. Pattern Recognition ， 2008， 41(6): 2107-2119.
[17] Weinberger K Q， Saul L K. Unsupervised Learning of Image Manifolds by Semidefinite Programming[J]. International Journal of Computer Vision ， 2006， 70(1): 77-90.
[18] Weinberger K Q， Sha F， Saul L K. Learning a Kernel Matrix for Nonlinear Dimensionality Reduction[C]. Alberta: Proceedings of the 21th International Conference on Machine Learning ， 2004.
[19] 康荣杰，焦宗夏， Jean Charles Mar，等. 电动静液作动器非线性框图建模与鲁棒控制方法[J]. 航空学报， 2009， 30(3): 518-525.

Sensor Fault Detection for EHA System Based on Adaptive Kernel Principal Component Analysis

基于自适应核主元分析的EHA系统传感器故障检测

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 0

Recommended Articles

Metrics

Comments