经数据分析途径实现机器智能的故障决策引发出了关于故障数据集的降维问题。通过将等距映射算法（Isometric Mapping，ISOMAP）、局部线性嵌入(Locally Linear Embedding, LLE)算法的优缺点进行互补，提出一种适用于非线性数据集降维的核框架下等距映射与局部线性嵌入相结合的KISOMAPLLE算法。该算法能够同时满足全局距离保持性和局部结构保持能力的数据降维基本要求。用典型的人工数据集和转子故障数据集进行的降维验证结果表明，该算法能够继承ISOMAP、LLE两种算法的各自优良性能，具有能够显著提高典型非线性数据集分类精度的性能。
Abstract
The data set for fault diagnosis and decision based on machinary intelligence gives rise to the requirement of dimension reduction in data processing.The algorithms of Isometric Mapping (ISOMAP) and Locally Linear Embedding (LLE) were introduced simultaneously to mutually complement their strong points and weak points,and a new KISOMAPLLE algorithm was proposed.The algorithm can satisfy the requirement of both global distance preserving and local structure preserving ability,and has been used to reduce the dimension of typical artificial data sets and rotor fault data sets.The proposed algorithm inherits the excellent performances of ISOMAP and LLE,and can improve the classification accuracy of typical nonlinear data sets.
关键词
故障诊断 /
流形学习 /
核方法 /
特征提取
{{custom_keyword}} /
Key words
fault diagnosis /
manifold learning /
kernel method /
feature extraction
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Mukund Balasubramanian,Eric L. Schwartz. The isomap algorithm and topological stability[J]. Science, 2002, 295(4).
[2] Yun Zhang, Benwei Li, Zibin Wang. Fault diagnosis of rotating machine by isometric feature mapping [J]. Journal of Mechanical Science and Technology, 2013, 27 (11) : 3215~3221.
[3] Tenenbaum JB, de Silva V, Langford JC. A global geometric framework for nonlinear dimensionality reduction [J]. Science, 2000, 290(5500):2319-2323.
[4] Xin Geng, De-Chuan Zhan, Zhi-Hua Zhou, et al.Supervised nonlinear dimensionality reduction for visualization and classification[J]. IEEE Transaction on Systems, Man, And Cybernetics-PartB: Cybernetics , 2005,35(6):1098-1107.
[5] Mohammad Ali Zare Chahooki, Nasrollah Moghadam Charkari. Unsupervised manifold learning based on multiple feature spaces [J]. Machine Vision and Applications, 2014, 25:1053–1065.
[6] Guy Rosman. Nonlinear dimensionality reduction by topologically constrained isometric embedding[J]. Int J Comput Vis , 2010, 89: 56–68.
[7] Laurens van der Maaten, Eric Postma, Jaap van den Herik.Dimensionality reduction: a comparative review [J]. Tilburg centre for Creative Computing, 2009.
[8] Ham J, Leed, Mike D S, et al. A kernel view of the dimeninality reducation of manifolds [C]. Proc of the 21st International Conference On Machine Learning, 2004.
[9] 张少龙,巩知乐,廖海斌. 融合LLE 和ISOMAP的非线性降维方法[J]. 计算机应用研究, 2014, 31(1):277-280.
Zhang Shaolong, Gong Zhile, Liao Haibin. Fusion of LLE and Isomap nonlinear descending dimension method [J]. Application Research of computers, 2014, 31 (1): 277-280.
[10] H.Choi, S.Choi. Kernel isomap [J]. Electronics Letters, 2004 .
[11] 杜京义,侯媛彬. 基于核方法的故障诊断理论及其方法的研究[M]. 北京:北京大学出版社, 2010, p1-7.
Du Jingyi, Hou Yuanbin. Research on the theory and method of fault diagnosis based on kernel method [M]. Beijing: Peking University press, 2010, p1-7.
[12] 雷迎科. 流形学习算法及其应用研究[D]. 合肥:中国科学技术大学,2011.
Lei Yingke. Manifold learning algorithm and its application [D]. Hefei: University of Science and Technology China, 2011
[13] 霍天龙,赵荣珍,胡宝权. 基于熵带法与 PSO 优化的SVM转子故障诊断[J]. 振动、测试与诊断, 2011, 31( 3): 279-284.
Huo Tianlong, Zhao Rongzhen, Hu Baoquan. Based on entropy method and PSO SVM rotor fault diagnosis. Journal of vibration, test and diagnosis, 2011, 31 (3): 279-284.
[14] 张恒,赵荣珍. 故障特征选择与特征信息融合的加权KPCA方法研究[J]. 振动与冲击, 2014, 33(9):89-93.
Zhang Heng, Zhao Rongzhen. Fault feature selection and feature information fusion weighted KPCA method to study [J]. vibration and shock, 2014, 33 (9): 89-93.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(1696 KB)
