增量式监督局部切空间排列算法及齿轮箱故障诊断实验验证

PDF(1936 KB)

振动与冲击 ›› 2018, Vol. 37 ›› Issue (13) : 105-110.

论文

佘博1，田福庆1，梁伟阁1，汤健2

作者信息 +

Test verification for gearbox fault diagnosis based on incremental supervised local tangent space alignment algorithm

SHE Bo, TIAN Fu-qing, LIANG Wei-ge, Tang Jian

Author information +

文章历史 +

摘要

针对局部切空间排列算法面临的无法利用样本标签信息和不能高效处理增量式维数约简问题，提出一种新的增量式监督局部切空间排列算法（Incremental Supervised Local Tangent Space Alignment, ISLTSA）。为充分利用训练样本标签信息，在LTSA算法的基础上加入散度矩阵，构造新的最小目标函数，使得高维样本的低维嵌入坐标同类聚集、异类分离。对于新增样本可能影响部分训练样本局部邻域，更新全局坐标矩阵，获取训练样本低维坐标和新增样本低维坐标，并作为初值进行特征值迭代实现所有样本全局坐标的更新。结合支持向量机分类算法，将ISLTSA算法应用于齿轮箱的故障状态识别，实验分析验证了该方法的监督学习能力，可提高故障状态识别率，并具备增量学习能力，可降低维数约简方法的复杂度。

Abstract

Aiming at that the local tangent space alignment (LTSA) algorithm could not use samples’ label information and could not fast process incremental dimension reduction problems, a new incremental supervised local tangent space alignment (ISLTSA) algorithm was proposed. To make full use of the label information of training samples, the divergence matrix was added into the LTSA algorithm to construct a new minimum objective function. The lower dimensions were made to embed coordinates for homogeneous clustering and heterogeneous separating. The incremental samples might affect the local neighborhood of partial training samples. Then the global coordinate matrix was updated to get the lower dimension coordinates of both training samples and the incremental ones, the lower dimension coordinates were taken as initial values to do eigenvalue iteration and realize updating the global coordinates of all samples. Combined with the classification algorithm of support vector machine, the proposed ISLTSA algorithm was applied in gearbox fault diagnosis. The tests verified the supervisory and learning capacity of the proposed method, it was shown that the new method can improve the fault recognition rate; it has an incremental learning ability, and can reduce the complexity of the dimension reduction method.

导出引用

佘博1，田福庆1，梁伟阁1，汤健2. 增量式监督局部切空间排列算法及齿轮箱故障诊断实验验证[J]. 振动与冲击, 2018, 37(13): 105-110

SHE Bo, TIAN Fu-qing, LIANG Wei-ge, Tang Jian. Test verification for gearbox fault diagnosis based on incremental supervised local tangent space alignment algorithm[J]. Journal of Vibration and Shock, 2018, 37(13): 105-110

参考文献

[1] Su Z Q, Tang B P, Deng L, et al. Fault diagnosis method using supervised extended local tangent space alignment for dimension reduction [J]. Measurement, 2015, 62: 1-14.
[2] Liu Y H, Zhang Y S, Yu Z W, et al. Incremental supervised locally linear embedding for machinery fault diagnosis [J]. Engineering Applications of Artificial Intelligence, 2016, 50: 60-70.
[3] Zhao M B, Jin X H, Zhang Z, et al. Fault diagnosis of rolling element bearings via discriminative subspace learning: visualization and classification [J]. Expert Systems with Applications, 2014, 41: 3391-3401.
[4] 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 [J]. 振动与冲击, 2014, 33(23): 15-19.
Song Tao, Tang Bao-ping, Deng Lei. A dynamic incremental manifold learning algorithm and its application in fault diagnosis of machineries [J]. Journal of Vibration and Shock, 2014, 33(23): 15-19.
[5] Han Z, Meng D Y, Xu Z B, et al. Incremental alignment manifold learning[J]. Journal of Computer Science and Technology, 2011, 26(1): 153-165.
[6] Gao X F, Liang J Y. An improved incremental nonlinear dimensionality reduction for isometric data embedding [J]. Information Processing Letters, 2015, 115: 492-501.
[7] Tan C, Ji G L. A manifold learning algorithm based on incremental tangent space alingment [C]// Xingming Sun. Proceedings of 2th International Conference on Cloud Computing and Security, NanJing, China: Springer, 2016: 541-552.
[8] 赵辽英, 李富杰, 厉小润. 泛化改进的局部切空间排列算法 [J]. 计算机工程, 2014, 40(11): 160-166.
Zhao Liao-ying, Li Fu-jie, Li Xiao-run. Local tangent space alignment algorithm of generalized improvement [J]. Computer Engineering, 2014, 40(11): 160-166.
[9] 杜春, 邹焕新, 孙即祥, 等. 基于改进局部切空间排列的流形学习算法[J]. 电子与信息学报, 2014, 36(2): 277-284.
Du Chun, Zou Huan-xin, Sun Ji-xiang. Manifold learning algorithm based on modified local tangent space alignment [J]. Journal of Electronics & Information Technology, 2014, 36(2): 277-284.
[10] Zhang P, Qiao H, Zhang B. An improved local tangent space alignment method for manifold learning[J]. Pattern Recognition Letters, 2011, 32: 181-189.
[11] Liu Y H, Zhang Y S, Yu Z W, et al. Incremental supervised locally linear embedding for machinery fault diagnosis [J]. Engineering Applications of Artificial Intelligence, 2016, 50: 60-70.
[12] 杨庆, 陈桂明, 童兴民,等. 增量式局部切空间排列算法在滚动轴承故障诊断中的应用[J]. 机械工程学报, 2012, 48(5): 81-86.
Yang Qing, Chen Gui-ming, Tong Xing-min, et al. Application of incremental local tangent space alignment algorithm to rolling bearings fault diagnosis [J]. Journal of Mechanical Engineering, 2012, 48(5): 81-86.
[13] Li H S, Jiang H, Roberto Ba, et al. Incremental manifold learning by spectral embedding methods[J]. Pattern Recognition Letters, 2011, 32: 1447-1455.
[14] 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, 2014, 33(3): 70-75.
[15] Public data sets 2009 PHM challenge competition data set [EB/OL]. [2016-12-01]. http:// www. Phmsociety. org/ references/ datasets.