1.College of Mechantronics and Automobile Engineering, Chongqing Jiaotong University, Chongqing, 400074, China
2. School of Aeronautics&Astronautics, Sichuan University,Chengdu,610065, China
摘要针对非敏感特征削弱了航天轴承寿命状态特征集表征能力和识别率的问题,提出基于振动敏感时频特征的航天轴承寿命状态识别方法。设计出基于散布矩阵的寿命敏感性指标计算方法,根据该指标优选出使样本类内散度小、类间距大的敏感特征构建出寿命状态敏感特征集,增强对寿命状态的表征性。通过线性局部切空间排列算法(Linear local tangent space alignment, LLTSA)对寿命状态敏感特征集进行维数约简和特征融合,去除冗余信息,获得分类特性更好的低维寿命状态特征集,并输入最近邻分类器(K-nearest neighbors classifier,KNNC)实现航天轴承不同寿命状态的识别。工程应用结果证明了所提方法的有效性和可行性。
Abstract:A life state recognition method of space bearings based on sensitive time-frequency feature of vibration was proposed, aiming at solving the problem that the characterization capabilities and recognition rate are weakened for life state feature set of space bearing by non-sensitive feature. The calculation method of life sensitivity index was designed to eliminate the non sensitivity characteristic of life state feature sets,then constructed the life state sensitive feature subsets and reinforced the characterization for life state. Linear local tangent space alignment(LLTSA) was introduced to compress the life state sensitive feature subsets into the low-dimensional life state feature sets, removing the redundant information. Finally, the life state of space bearings was recognized by K-nearest neighbors classifier (KNNC). The feasibility and validity of the present method are verified by experimental results.
陈仁祥1,2,陈思杨1,杨黎霞1,王家序2,董绍江1,徐向阳1. 基于振动敏感时频特征的航天轴承寿命状态识别方法[J]. 振动与冲击, 2016, 35(17): 134-139.
CHEN Ren-xiang1,2,CHEN Si-yang1,YANG Li-xia1,DONG Shao-jiang1, XU Xiang-yang1,DONG Shao-jiang1. Life state recognition method for space bearings based on sensitive time-frequency feature of vibration. JOURNAL OF VIBRATION AND SHOCK, 2016, 35(17): 134-139.
[1] Jason Herman, Kiel Davis. Evaluation of Perfluoro polyether Lubricant Lifetime in the High Stress and High Stress-Cycle Regime for Mars Applications.Honeybee Robotics Spacecraft Mechanisms Corporation, New York, NY, Proceedings of the 39th Aerospace Mechanisms Symposium, NASA Marshall Space Flight Center, 2008(5): 7-9.
[2] Ohno, Nobuyoshi, Sonoda etal. Bearing fatigue life tests of two advanced base oils for space applications under vacuum and atmospheric environments[J]. Tribology Transactions, 2011(54): 859-866.
[3] David B.Stringer, Pradip N.Sheth, Paul E. Allaire. Physics- based modeling strategies for diagnostic and prognostic application in aerospace systems[J]. J Intell Manuf ,2012(23): 155-162.
[4] P. A. Bertrand.Chemical degradation of a multiply alkylated cyclopentane (MAC) oil during wear: Implications for spacecraft attitude control system bearings[J].Tribol Lett, 2013(49):357– 370.
[5] Ogawa T, Konishi K, Aihara S, Sawamoto T. Development of ball bearings with solid film for high-vacuum, high-temperature,high-speed application[J]. Lubric Eng, 2009(49):291–299.
[6] Tiago Cousseau,Beatriz Graça, Armando Campos, Jorge Seabra. Friction torque in grease lubricated thrust ball bearings[J]. Tribology International, 2011(44):523–531.
[7] Z.N. Nemeth, W.J. Anderson. Investigation of temperature limitation of various lubricants for high-temperature 20-millimeter bore ball bearings[R]. NASA TN D-3337, 2005.
[8] 宋涛,汤宝平,李 锋.基于流形学习和K-最近邻分类器的旋转机械故障诊断方法[J].振动与冲击,2013,32(5):149- 153.
SONG Tao,TANG Bao-ping,LI Feng.Fault diagnosis method for rotating machinery based on manifold learning and K-nearest neighbor classifier[J].Journal of Vibration and Shock,2013,32( 5):149-153.
[9] 苏祖强,汤宝平,姚金宝.基于敏感特征选择与流形学习维数约简的故障诊断[J],振动与冲击,2014,33(3):70-75.
SU Zu-qiang,TANG Bao-ping,YAO Jin-bao Fault diagnosis method based on sensitive feature selection and manifold learning dimension reduction[J], Journal of Vibration and Shock,2014,33( 3):70-75.
[10]陈仁祥.振动谱表征空间滚动轴承寿命状态方法研究[D].重庆:重庆大学,2012.
Chen Renxiang. Lifetime State Indentification Research for Space Rolling Bearings Based on Vibration Spectrum [D]. Chongqing:Chongqing University,2012.
[11]Shaojiang Dong, Tianhong Luo.Bearing degradation process prediction based on the PCA and optimized LS-SVM model[J]. Measurement 46 (2013): 4189-4199.
[12]Liu X M,Yin J W,Feng Z L,et al. Orthogonal neighborhood preserving embedding for face recognition[C]/ / 2007 IEEE International Conference on Image Processing, ICIP 2007.New York,USA: IEEE,2007: 133-136.
[13] Feng Li, Baoping Tang, Rongsong Yang. Rotating machine fault diagnosis using dimension reduction with linear local tangent space alignment[J], Measurement,2013,8(46): 2525-2539.
[14]Songbo T. An effective refinement strategy for KNN text classifier[J]. Expert Systems with Applications,2006, 30: 290- 298.
[15]Yu XP,Yu XG. Novel text classification based on k -nearest neighbor [C]. Proceedings of Sixth International Conference on Machine Learning Cybernetics,Hong Kong,China,2007: 3425-3430.