基于过程功率谱熵SVM的转子振动故障诊断方法

推进技术 ›› 2012, Vol. 33 ›› Issue (2): 293-298.

基于过程功率谱熵SVM的转子振动故障诊断方法

费成巍,白广忱,李晓颖

北京航空航天大学能源与动力工程学院,北京 100191;北京航空航天大学能源与动力工程学院,北京 100191;河北联合大学电气工程学院,河北唐山 063009

发布日期:2021-08-15
作者简介:费成巍(1983—),男,博士生,研究领域为发动机结构可靠性设计及故障诊断。E-mail:feicw544@163.com
基金资助:
国家自然科学基金(51175017)；北京航空航天大学博士研究生创新基金。

Method of Rotor Vibration Fault Diagnosis from Process Power Spectrum Entropy and SVM

College of Energy and Power Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100191, China;College of Energy and Power Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100191, China;College of Electrical Engineering, Hebei United University, Tangshan 063009, China

Published:2021-08-15

摘要/Abstract

摘要： 针对旋转机械振动过程的复杂性和振动故障产生的随机性以及振动故障样本获取难的问题,在信息熵理论的基础上,融合了支持向量机(SVM)小样本、全局性和泛化性好的优点,提出了过程功率谱信息熵(功率谱熵)SVM的故障诊断方法。结合转子实验台,得到了4种典型振动故障在多测点多转速下的数据,通过计算提取了其功率谱熵特征值作为故障样本,即故障向量,并建立SVM诊断模型,对转子振动故障的类别、严重程度和部位识别诊断,验证了该方法在转子振动故障诊断方面效果良好。 

关键词: 信息熵;功率谱熵;支持向量机;信息融合;转子振动;故障诊断

Abstract: For the complexity of rotor vibration process and the randomization of vibration fault generated, and difficulty for getting vibration fault samples, a fault diagnosis method based on power spectrum entropy and Support Vector Machine(SVM) with the SVM advantages of small sample, generalization and overall under information entropy was put forward. Four typical failures of rotor vibration was simulated based on rotor experiment and vibration fault data under more points and multi-speed is collected. The power spectrum entropy has been calculated through analyzing and processing the datum as fault vector, and the SVM model has been gained. And the validity of this method for distinguishing fault types, fault severity and fault location is proved to be effective by calculation and analysis of rotor vibration fault signals. 

Key words: Information entropy; Power spectrum entropy; Support vector machine (SVM); Information fusion; Rotor vibration; Fault diagnosis

费成巍,白广忱,李晓颖. 基于过程功率谱熵SVM的转子振动故障诊断方法[J]. 推进技术, 2012, 33(2): 293-298.

参考文献

[2] Endo H,Randan R B.Enhancement of Autoregressive Model Based Gear Tooth Fault Detection Technique by the Use of Minimum Entropy Deconvolution Filter[J].Mechanical systems and Signal Process, 7,1(Z):906-919．
[3] Li Hongkun,Zhou Peilin,Ma Xiaojiang.Pattern Recognition on Diesel Engine Working Condition by Using a Novel Methodology-Hubert Spectrum Entropy [J].Journal of Marine Engineering and Technology,2005,(6):43-48.
[4] 陈非,黄树红,张燕平,等.基于过程的旋转机械振动故障定量诊断方法[J].动力工程,8,8(4):543-547.
[5] Qu Liang-sheng, Li Liang-ming, Lee Jay.Enhanced Diagnostic Certainty Using Information Entropy Theory [J].Advanced Engineering Informatics,3,7(3-4):141-150．
[6] 李金涛,张凤鸣,李永宾,等.基于多元联合熵的航空发动机性能分析[J].控制系统,7,3(1):53-54.
[7] CHENG Liming.Latest Progress of Research on Fault Diagnosis Based on Information Fusion [J].Information Technology Journal, 8,7(5):825-829.
[8] 罗俊, 何立明, 陈超.基于小波分形和一类辨识的航空发动机故障诊断[J].推进技术, 7,8(1):82-85.(LUO Jun,HE Li-ming,CHEN Chao.Aeroengine Fault Diagnoisis Based on One-Class Classification and Wavlet-Fractal[J].Journal of Propulsion Technology,7,8(1):82-85.)
[9] Blanchard G, Bousquet O, Massar P.Statistical Performance of Support Vector Machines [J].The Annals of Statistical, 8,6(2):489-531.
[10] XU Qihua, SHI Jun.Fault Diagnosis for Aero-Engine Applying a New Multi-Class Support Vector Machine Algorithm [J].Chinese Journal of Aeronautics, 6,9(1):175-182.
[11] DING Weidong, YUAN Jingqi.Spike Sorting Based on Multi-Class Support Vector Machine with Superposition Resolution [J].Medical and Biological Engineering and Computing, 8,6(2):139-145.
[12] 白鹏, 张喜斌, 张斌,等.支持向量机理论及工程应用实例[M].西安:西安电子科技大学出版社,2008.
[13] 张亚楠, 魏武, 武林林.基于小波Shannon熵SVM和遗传算法的电机机械故障诊断[J].电力自动化设备,0,0(1):87-91.