基于WCFSE-FSVM的转子振动故障诊断方法

推进技术 ›› 2013, Vol. 34 ›› Issue (9): 1266-1271.

基于WCFSE-FSVM的转子振动故障诊断方法

费成巍,白广忱

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

发布日期:2021-08-15
作者简介:费成巍(1983—),男,博士生,研究领域为航空发动机振动故障诊断、结构可靠性分析与多学科优化。 E-mail:feicw544@163.com
基金资助:
国家自然科学基金(51175017,51275024)；北京航空航天大学博士研究生创新基金(YWF-12-RBYJ-008)；高等学校博士学科点专项科研基金(20111102110011)。

Rotor Vibration Fault Diagnosis Method Based on WCFSE-FSVM

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

Published:2021-08-15

摘要/Abstract

摘要： 为了提高含有噪声和野值的转子振动故障样本诊断精度,提出了基于WCFSE-FSVM的故障诊断方法。充分融合小波相关特征尺度熵(WCFSE)特征提取方法和FSVM故障诊断方法的优点,建立WCFSE-FSVM故障诊断模型。基于转子实验台模拟4种典型故障,获得原始故障数据；并利用WCFSE方法提取这些故障数据的WCFSE值,选取故障信号高频段中的尺度1和尺度2上的小波相关特征尺度熵W1和W2构造出振动信号的故障向量作为故障样本,建立FSVM诊断模型。实例分析显示:WCFSE-FSVM方法的转子故障诊断精度最高,即故障类别诊断精度为94.49%,故障严重程度的诊断精度为95.58%,二者都优于其它故障诊断方法。验证了WCFSE-FSVM方法的可行性和有效性。 

关键词: 小波相关特征尺度熵;模糊支持向量机;转子振动;故障诊断 

Abstract: To improve the diagnostic precision of rotor vibration fault samples with the noise and outliers, the fault diagnosis method based on the wavelet correlation feature scale entropy (WCFSE) and fuzzy support vector machine (FSVM) (WCFSE-FSVM) was proposed. The fault diagnosis model of the WCFSE-FSVM was established by fully fusing the strength of the WCFSE feature extraction method and the FSVM fault diagnosis method. The original fault data were gained through simulating four typical faults on rotor test-bed. The WCFSE values of these data were extracted by the WCFSE method, and W1and W2, which are the WCFSE values on the scales 1and 2,respectively, in the high band of fault signals, were selected to construct the fault vectors of vibration signals as the fault samples for establishing the FSVM diagnosis model. As shown by instance analysis, the WCFSE-FSVM in four methods possesses the highest diagnosis precision that the fault type and severity diagnosis precisions of rotor vibration are 94.49% and 95.58%, respectively. This paper demonstrates the validity and feasibility of proposed WCFSE-FSVM and provides an effective method for rotor vibration fault diagnosis. 

Key words: Wavelet correlation feature scale entropy (WCFSE); Fuzzy support vector machine (FSVM); Rotor vibration; Fault diagnosis

费成巍,白广忱. 基于WCFSE-FSVM的转子振动故障诊断方法[J]. 推进技术, 2013, 34(9): 1266-1271.

FEI Cheng-wei, BAI Guang-chen. Rotor Vibration Fault Diagnosis Method Based on WCFSE-FSVM[J]. Journal of Propulsion Technology, 2013, 34(9): 1266-1271.

参考文献

[1] 费成巍,艾延廷.航空发动机健康管理系统设计技术[J].航空发动机, 2009,5(5):24-29.
[2] 《航空发动机设计手册》总编委会.航空发动机设计手册(第19册):转子动力学及整机振动[M].北京:航空工业出版社, 2001.
[3] Lin Jing, Qu Liang-sheng.Feature Extraction Based on Morlet Wavelet and Its Application for Mechanical Fault Diagnosis [J].Journal of Sound and Vibration, 2000,4(1):135-148.
[4] Chebil J, Noel G, Mesbah M, et al.Wavelet Decomposition for the Detection and Diagnosis of Faults in Rolling Element Bearings [J].Jordan Journal of Mechanical and Industrial Engineering, 2009,3(4):260-267.
[5] 艾延廷, 费成巍.转子振动故障的小波能谱熵SVM故障诊断[J].航空动力学报,2011,6(8):1830-1835.
[6] 曾庆虎, 刘冠军, 邱静.基于小波相关特征尺度熵的预测特征信息提取方法研究[J].中国机械工程, 2008,9(10):1193-1196.
[7] 赵冲冲, 廖明夫, 于萧.基于支持向量机的旋转机械故障诊断[J].振动、测试与诊断, 2006,6(1).
[8] 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, 2012,3(2):293-298.(FEI Cheng-wei, BAI Guang-chen, LI Xiao-ying.Method of Rotor Vibration Fault Diagnosis From Process Power Spectrum Entropy and SVM[J].Journal of Propulsion Technology, 2012,3(2).
[9] 艾延廷, 费成巍.基于支持向量机的转子振动故障融合诊断技术[J].沈阳工业大学学报, 2010,2(5).
[10] LI Jun-tao, JIA Ying-min.Huberized Multiclass Support Vector Machine for Microarray Classification [J].Acta Automatica Sinica, 2010,6(3):399-405.
[11] LIN Chun-fu, WANG Sheng-de.Fuzzy Support Vector Machines [J].IEEE Transactions On Neural Networks, 2002,3(2):464-471．
[12] Tsujinishi D, Abe S.Fuzzy Least Squares Support Vector Machines for Multiclass Problem [J].Neural Networks, 2003:16(5-6):785-792.
[13] LIN Chun-fu, WANG Sheng-de.Training Algorithms for Fuzzy Support Vector Machines with Noisy Data [J].Pattern Recognition Letters, 2004,5(14):1647-1656.
[14] MAO Yong, XIA Zheng, YIN Zheng, et al.Fault Diagnosis Based on Fuzzy Support Vector Machine with Parameter Tuning and Feature Selection[J].Chinese Journal of Chemical Engineering, 2007,5(2):233-239.
[15] 艾延廷, 费成巍.基于改进模糊SVM的转子振动故障诊断 [J].航空动力学报, 2011,6(5):1118-1123.
[16] 郭秩维, 费成巍, 白广忱.基于FSVM改进隶属度的发动机振动性能分析[J].推进技术, 2013,4(2):263-267.( GUO Zhi-wei, FEI Cheng-wei, BAI Guang-chen.Improved Fuzzy Membership in FSVM for Aeroengine Vibration Performance Fusion Analysis[J].Journal of Propulsion Technology, 2013,4(2):263-268.