论文:2012,Vol:30,Issue(4):529-534
引用本文:
窦丹丹, 姜洪开, 何毅娜. 基于信息熵和SVM多分类的飞机液压系统故障诊断[J]. 西北工业大学
Dou Dandan, Jiang Hongkai, He Yina. Effectively Diagnosing Faults for Aircraft Hydraulic System Based on Information Entropy and Multi-Classification SVM[J]. Northwestern polytechnical university

基于信息熵和SVM多分类的飞机液压系统故障诊断
窦丹丹, 姜洪开, 何毅娜
西北工业大学 航空学院,陕西 西安 710072
摘要:
飞机液压系统是典型的非线性系统,故障机理复杂,提取故障信息困难,且故障样本较少。针对飞机液压系统部件故障,文章采用了基于信息熵特征权值分配和支持向量机(SVM)多分类的故障诊断方法。先提取飞机液压系统压力信号的统计特征,然后通过计算特征信息熵为特征分配相应权值,将权值较大的特征作为支持向量机的输入向量,最后建立SVM多分类器将正常与多种故障状态进行分类;所采用的方法不仅有效降低了支持向量机模型的计算复杂度,而且提高了分类精度。通过建立飞机起落架收放系统仿真模型,对该故障诊断方法进行了验证研究。仿真结果表明,该方法选用高斯径向基核函数能够有效对液压系统进行故障诊断。
关键词:    飞机液压系统    信息熵    特征权值    支持向量机多分类    故障诊断   
Effectively Diagnosing Faults for Aircraft Hydraulic System Based on Information Entropy and Multi-Classification SVM
Dou Dandan, Jiang Hongkai, He Yina
College of Aeronautics,Northwestern Polytechnical University,Xi'an 710072,China
Abstract:
Aircraft hydraulic system is a typical nonlinear system; it is difficult to extract the fault information,thefailure mechanism is complex,and fault samples are few. Sections 1 through 4 of the full paper explain the diagno-sis mentioned in the title,which we believe is effective and whose core consists of:“In accordance with the compo-nent faults for aircraft hydraulic system,we adopt the model of support vector machine (SVM) for multi-classifica-tion of faults using statistical features extracted from pressure signals under good and faulty conditions of hydraulicsystem. Feature entropy algorithm is used to distribute weights for selecting the prominent features. These featuresare given as inputs for training and testing the model of SVM. The method not only effectively solves the SVM prob-lem of dimensionality but also improves the classification efficiency and accuracy. By establishing a simulation mod-el of landing gear system,the fault diagnosis method is validated. " The simulation results in Table 3 and their anal-ysis show preliminarily that our method can indeed effectively diagnose the faults of the aircraft hydraulic system.
Key words:    aircraft    algorithms    diagnosis    efficiency    entropy    feature extraction    flowcharting    mathematicalmodels    measurements    nonlinear systems    statistics    support vector machines;aircraft hydraulic sys-tem    fault diagnosis    information entropy    multi-classification SVM   
收稿日期: 2011-09-20     修回日期:
DOI:
基金项目: 国家自然科学基金(50975231)资助
通讯作者:     Email:
作者简介: 窦丹丹(1986-),女,西北工业大学硕士研究生,主要从事飞行器健康监控的研究。
相关功能
PDF(449KB) Free
打印本文
把本文推荐给朋友
作者相关文章
窦丹丹  在本刊中的所有文章
姜洪开  在本刊中的所有文章
何毅娜  在本刊中的所有文章

参考文献:
[1] 赵四军, 王少萍, 尚耀星. 航空液压泵柱塞游隙增大故障诊断. 北京航空航天大学学报, 2010, 36(3): 261-264Zhao Sijun,Wang Shaoping,Shang Yaoxing. Fault Diagnosis for Piston Head Looseness of Aero Hydraulic Pump. Journal ofBeijing University of Aeronautics and Astronautics, 2010, 36(3):261-264 (in Chinese)
[2] 刘本德, 胡昌华, 蔡艳宁. 基于聚类和 SVM 多分类的容差模拟电路故障诊断. 系统仿真学报, 2009, 21(20): 6479-6482Liu Bende,Hu Changhua,Cai Yanning. Fault Diagnosis of Analog Circuits with Tolerance Based on Clustering and SVM Multi-Classification. Journal of System Simulation, 2009, 21(20): 6479-6482 (in Chinese)
[3] Saimurugan K I,Ramachandran V S. Multi Component Fault Diagnosis of Rotational Mechanical System Based on Decision Treeand Support Vector Machine. Expert Systems with Applications, 2011, 38: 3819-3826
[4] Steve R Gunn. Support Vector Machines for Classification and Regression. Technical Report of Facutty of Engineering andApplied Science Department of Electronics and Computer Science,University of SouthThampton, 1998
[5] Achmad Widodo,Yang Bosuk. Support Vector Machine in Machine Condition Monitoring and Fault Diagnosis. Mechanical Sys-tems and Signal Processing, 2007, 21: 2560-2572
[6] 韩中合, 朱霄珣. 基于信息熵的支持向量回归机训练样本长度选择. 中国电机工程学报, 2010, 30(20):112-116Han Zhonghe,Zhu Xiaoxun. Selection of Training Sample Length in Support Vector Regression Based on Information Entropy.Proceedings of the CSEE, 2010, 30(20):112-116 (in Chinese)
[7] Sugumaran V,Muralildharan V,Ramachandran K I. Feature Selection Using Decision Tree and Classification through ProximalSupport Vector Machine for Fault Diagnostics of Roller Bearing. Mechanical Systems and Signal Processing, 2007, 21:930-94
[8] 吴亚锋, 郭 军. 基于 AMESim 的飞机液压系统仿真技术的应用研究. 沈阳工业大学学报, 2007, 29(4):368-371Wu Yafeng,Guo Jun. Research on Simulation Technique Based on AMESim for Aircraft Hydraulic System. Journal of ShenyangUniversity of Technology, 2007, 29(4): 368-371 (in Chinese)