赵川等：基于多域流形的行星齿轮箱局部故障识别 ·777· based on condition indicator in time-frequency domain.Mech Sci 的齿轮箱故障诊断.振动与冲击，2013,32(5)：38) Technol Aerospace Eng,2010,29(6):701 [13]Li M L,Wang S A,Liang L.Feature extraction for incipient (冯占辉，胡茑庆，程哲.基于时频域状态指标的行星齿轮断 fault diagnosis of rolling bearing based on nonlinear manifold 齿故障检测.机械科学与技术，2010,29(6)：701) leaming.J Xi'an Jiao Tong Unir,2010,44(5):45 [9]Chen X W,Feng Z P,Liang M.Planetary gearbox fault diagnosis (栗茂林，王孙安，梁霖.利用非线性流形学习的轴承早期 under time-variant conditions based on iterative generalized syn- 故障特征提取方法.西安交通大学学报，2010,44(5)：45) chrosqueezing transform.J Mech Eng,2015,51(1):131 [14]Chen FF,Tang B P,Song T,et al.Multi-fault diagnosis study (陈小旺，冯志鹏，Liang Ming.基于迭代广义同步压缩变换 on roller bearing based on multi-kemel support vector machine 的时变工况行星齿轮箱故障诊断.机械工程学报，2015,51 with chaotic particle swarm optimization.Meas,2014,47:576 (1):131) [15]Gan M,Wang C.Zhu C A.Multiple-domain manifold for feature [10]Wang X,Zheng Y,Zhao Z Z,et al.Bearing fault diagnosis extraction in machinery fault diagnosis.Meas,2015,75:76 based on statistical locally linear embedding.Sens,2015,15 [16]Cheng J S,Zhang K,Yang Y,et al.Comparison between the (7):16225 methods of local mean decomposition and empirical mode decom- [11]Song T,Tang B P,Deng L.A dynamic incremental manifold position.J Vib Shock,2009,28(5):13 learning algorithm and its application in fault diagnosis of ma- (程军圣，张亢，杨宇，等.局部均值分解与经验模式分解的 chineries.J Vib Shock,2014,33(23):15 对比研究.振动与冲击，2009,28(5)：13) (宋涛，汤宝平，邓蕾.动态增殖流形学习算法在机械故障 [17]Seung H S,Lee DD.The manifold ways of perception.Sci, 诊断中的应用.振动与冲击，2014,33(23)：15) 2000.290(5500)：:2268 [12]Chen F F.Tang B P.Su Z Q.Gearbox fault diagnosis based on [18]Cao L Y.Practical method for determining the minimum embed- local target space alignment and multi-kernel support vector ma- ding dimension of a scalar time series.Phys D:Nonlinear Phe- chine.J Vib Shock,2013,32(5):38 nom,1997,110(1):43 (陈法法，汤宝平，苏祖强.基于局部切空间排列与MSVM赵 川等: 基于多域流形的行星齿轮箱局部故障识别 based on condition indicator in time鄄frequency domain. Mech Sci Technol Aerospace Eng, 2010, 29(6): 701 (冯占辉, 胡茑庆, 程哲. 基于时频域状态指标的行星齿轮断 齿故障检测. 机械科学与技术, 2010, 29(6): 701) [9] Chen X W, Feng Z P, Liang M. Planetary gearbox fault diagnosis under time鄄variant conditions based on iterative generalized syn鄄 chrosqueezing transform. J Mech Eng, 2015, 51(1): 131 (陈小旺, 冯志鹏, Liang Ming. 基于迭代广义同步压缩变换 的时变工况行星齿轮箱故障诊断. 机械工程学报, 2015, 51 (1): 131) [10] Wang X, Zheng Y, Zhao Z Z, et al. Bearing fault diagnosis based on statistical locally linear embedding. Sens, 2015, 15 (7): 16225 [11] Song T, Tang B P, Deng L. A dynamic incremental manifold learning algorithm and its application in fault diagnosis of ma鄄 chineries. J Vib Shock, 2014, 33(23): 15 (宋涛, 汤宝平, 邓蕾. 动态增殖流形学习算法在机械故障 诊断中的应用. 振动与冲击, 2014, 33(23): 15) [12] Chen F F, Tang B P, Su Z Q. Gearbox fault diagnosis based on local target space alignment and multi鄄kernel support vector ma鄄 chine. J Vib Shock, 2013, 32(5): 38 (陈法法, 汤宝平, 苏祖强. 基于局部切空间排列与 MSVM 的齿轮箱故障诊断. 振动与冲击, 2013, 32(5): 38) [13] Li M L, Wang S A, Liang L. Feature extraction for incipient fault diagnosis of rolling bearing based on nonlinear manifold learning. J Xi蒺an Jiao Tong Univ, 2010, 44(5): 45 (栗茂林, 王孙安, 梁霖. 利用非线性流形学习的轴承早期 故障特征提取方法. 西安交通大学学报, 2010, 44(5): 45) [14] Chen F F, Tang B P, Song T, et al. Multi鄄fault diagnosis study on roller bearing based on multi鄄kernel support vector machine with chaotic particle swarm optimization. Meas, 2014, 47: 576 [15] Gan M, Wang C, Zhu C A. Multiple鄄domain manifold for feature extraction in machinery fault diagnosis. Meas, 2015, 75: 76 [16] Cheng J S, Zhang K, Yang Y, et al. Comparison between the methods of local mean decomposition and empirical mode decom鄄 position. J Vib Shock, 2009, 28(5): 13 (程军圣, 张亢, 杨宇, 等. 局部均值分解与经验模式分解的 对比研究. 振动与冲击, 2009, 28(5): 13) [17] Seung H S, Lee D D. The manifold ways of perception. Sci, 2000, 290(5500): 2268 [18] Cao L Y. Practical method for determining the minimum embed鄄 ding dimension of a scalar time series. Phys D: Nonlinear Phe鄄 nom, 1997, 110(1): 43 ·777·