CKLPMDP algorithm for dimension reduction of a rotor fault data set

PDF(1188 KB)

Journal of Vibration and Shock ›› 2021, Vol. 40 ›› Issue (9) : 37-42.

AN Huang, ZHAO Rongzhen

Author information +

History +

Abstract

Aiming at the problem of the traditional data dimension reduction methods being difficult to consider both the local manifold structure learning and multi-manifold discriminant structure learning, a new algorithm for dimension reduction of a rotor fault data set was proposed based on the correlation-entropy kernel locality preserving multi-manifold discriminant projection (CKLPMDP).The remarkable feature of this algorithm was the correlation entropy measure being used to supervise construction of neighbor graphs.Firstly, the data set was mapped to a high-dimensional kernel space, and then the data set’s local manifold structure and multi-manifold discrimination structure information was comprehensively considered in the kernel space to extract low-dimensional sensitive feature vectors of the optimal characterizing fault data set.The low-dimensional classification effect was visually displayed by using 3-D graphs.Low-dimensional sensitive feature vectors were input into a K-nearest neighbor (KNN) classifier, the class spacing and within class distance in KNN classifier’s recognition rate and clustering analysis were taken as the indexes to measure the effect of dimension reduction.The vibration signal data set of a double-span rotor test platform was used to verify the proposed algorithm.Compared with other typical feature extraction methods, it was shown that the proposed algorithm can extract local manifold and multi-manifold discriminant information more effectively, and have better classification performance in rotor fault recognition.

Key words

correlation-entropy / discriminant projection / data dimension reduction / multi-manifold discriminant structure

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

AN Huang, ZHAO Rongzhen. CKLPMDP algorithm for dimension reduction of a rotor fault data set[J]. Journal of Vibration and Shock, 2021, 40(9): 37-42

References

［1］雷亚国, 贾峰, 孔德同, 等.大数据下机械智能故障诊断的机遇与挑战［J］.机械工程学报, 2018, 54(5): 94-104.
LEI Yaguo, JIA Feng, KONG Detong, et al.Opportunities and challenges of machinery intelligent fault diagnosis in big data era［J］.Journal of Mechanical Engineering, 2018, 54(5): 94-104.
［2］陈法法, 汤宝平, 苏祖强.基于等距映射与加权KNN的旋转机械故障诊断［J］.仪器仪表学报, 2013, 34(1): 215-220.
CHEN Fafa, TANG Baoping, SU Zuqiang.Rotating machinery fault diagnosis based on isometric mapping and weighted KNN［J］.Chinese Journal of Scientific Instrument, 2013, 34(1): 215-220.
［3］余建波, 卢笑蕾, 宗卫周.基于局部与非局部线性判别分析和高斯混合模型动态集成的晶圆表面缺陷探测与识别［J］.自动化学报, 2016, 42(1): 47-59.
YU Jianbo, LU Xiaolei, ZONG Weizhou.Wafer detection and recognition based on local and nonlocal linear discriminant analysis and dynamic ensemble of Gaussian mixture models［J］.Acta Automatica Sinica, 2016, 42(1): 47-59.
［4］SPREKELER H. On the relation of slow feature analysis and Laplacian eigenmaps［J］.Neural Computation, 2014, 23(12): 3287-3302.
［5］谢小欣, 胡建中, 许飞云, 等.一种基于多流形局部线性嵌入算法的故障诊断方法［J］.机械工程学报, 2013, 49(11): 79-83.
XIE Xiaoxin, HU Jianzhong, XU Feiyun, et al.A fault diagnosis method using multi-manifold learning based on locally linear embedding［J］.Journal of Mechanical Engineering, 2013, 49(11): 79-83.
［6］HE X, PARTHA N.Locality preserving projections［C］∥ Proceedings of the 17th Annual Conference on Neural Information Processing Systems.Vancouver, 2003.
［7］DENG X, TIAN X.Sparse kernel locality preserving projection and its application in nonlinear process fault detection［J］.Chinese Journal of Chemical Engineering, 2014, 50(5): 88-94.
［8］XU D, YAN S, TAO D, et al.Marginal Fisher analysis and its variants for human gait recognition and content-based image retrieval［J］.IEEE Transactions on Image Processing, 2007, 16(11): 2811-2821.
［9］LI X R, JIANG T, ZHANG K.Efficient and robust feature extraction by maximum margin criterion［J］.IEEE Transactions on Neural Networks, 2006, 17(1):157-165.
［10］LI B, LI J, ZHANG X P.Nonparametric discriminant multi-manifold learning for dimensionality reduction［J］.Neurocomputing, 2015, 152(4): 121-126.
［11］邱天爽, 陈兴, 马济通, 等.基于循环相关熵谱的时频混叠信号载波频率估计方法［J］.通信学报, 2018, 39(6): 20-26.QIU Tianshuang, CHEN Xing, MA Jitong, et al.Carrier frequency estimation method of time-frequency overlapped signals based on cyclic correntropy spectrum［J］.Journal on Communications, 2018, 39(6): 20-26.
［12］HE R, ZHENG W S, HU B G, et al.A regularized correntropy framework for robust pattern recognition［J］.Neural Computation, 2011, 23(8): 2074-2100.
［13］CHEN X, JIAN Y, LIANG J.Recursive robust least squares support vector regression based on maximum correntropy criterion［J］.Neurocomputing, 2012, 97(1): 63-73.
［14］赵孝礼, 赵荣珍.全局与局部判别信息融合的转子故障数据集降维方法研究［J］.自动化学报, 2017, 43(4): 560-567.
ZHAO Xiaoli, ZHAO Rongzhen.A method of dimension reduction of rotor faults data set based on fusion of global and local discriminant information［J］.Acta Automatica Sinica, 2017, 43(4): 560-567.
［15］李霁蒲, 赵荣珍.近邻概率距离在旋转机械故障集分类中的应用方法［J］.振动与冲击, 2018, 37(11): 48-54.
LI Jipu, ZHAO Rongzhen.Application of neighbor probability distance in classification of rotating machinery fault sets［J］.Journal of Vibration and Shock, 2018, 37(11): 48-54.
［16］成昊, 唐斌.基于相关熵的盲源分离算法［J］.电子科技大学学报, 2013, 42(2): 214-218.
CHENG Hao, TANG Bin.Blind source separation algorithm based on correntropy［J］.Journal of University of Electronic Science and Technology of China, 2013, 42(2): 214-218.