针对传统小波聚类算法采用相连定义聚类时精度和效率不够的问题，提出了一种基于广度优先搜索的改进小波聚类算法。该算法综合了小波聚类算法和广度优先搜索邻居聚类算法两者的优势，以小波聚类算法的网格邻居单元定义去改善广度优先搜索邻居聚类算法人工输入参数的敏感性，同时以广度优先搜索邻居聚类算法类门限参数的设定去改善小波聚类算法类划分不精确的缺陷。通过航空发动机转子模拟振动信号实验数据，对其分别进行小波聚类，广度优先搜索邻居聚类以及改进的小波聚类分析，结果表明：基于广度优先搜索的小波聚类能够很好地改善传统小波聚类的聚类精度和聚类速度，明显地降低计算复杂度。
Abstract
In consider of the low precision and efficiency of the clustering with the connection define using in the tradition WaveCluster algorithm ,an improved WaveCluster algorithm based on Breadth-First Search algorithm was presented. The algorithm integrate with the advantages of the wavecluster algorithm and the Breadth-First-Search (BFS) neighbor clustering algorithm, and the definition of the mesh neighbor unit of the former is used to improve the latter sensitivity that require manual input parameters; the setting of the cluster threshold parameters is used to improve the former defect that the division of clusters is inaccurate. Then, the analysis of the WaveCluster, Breadth-First-Search neighbor clustering and improved WaveCluster were done respectively with the vibration signal data got by the aeroengine rotor fault simulating experiment, the results show that the WaveCluster based on Breadth-First Search can effectively improve the clustering accuracy and speed of the traditional WaveCluster, reducing the computational complexity significantly.
关键词
小波聚类 /
广度优先搜索 /
改进算法 /
故障诊断
{{custom_keyword}} /
Key words
WaveCluster /
BFS /
the improved algorithm /
fault diagnosis
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Sheikholeslami G，Chatterjee S，Zhang A．Wave cluster： A Multi-resolution clustering approach for very large spatial data—bases[c]// Proceedings of the 24th International Conference on Very Large Data Bases．New York：Morgan Kaufmann，1998：428—438．
[2] 陈 佐，谢 赤，陈 晖。基于小波聚类方法的股票收益率序列时间模式挖掘[J]系统工程,2005,23（11）：102-107
CHEN Zuo, XIE Chi, CHEN Hui. Mining Temporal Patterns of Stock Yield Sequences Based on Wave Cluster Method[J] Systems Engineering, 2005,23（11）：102-107.
[3] 赵光嗣，李伟生.基于MPI的并行小波聚类算法在曙光TC1700上的实现[J].计算机应用，2006,26（3）:645-646
ZHAO Guang-si, LI Wei-sheng. Implementation of MPI-based parallel wavecluster algorithm on Shuguang TC1700[J].Computer application, 2006,26（3）:645-646.
[4] 刑 涛.小波聚类算法在本科招生生源质量分析中的应用[J]南京航空航天大学学报，2009,41（6）：823-827
XING Tao. Wavecluster Algorithm for Quality Analysis of Student Enrollment of Universities[J] Journal of Nanjing University of Aeronautics ＆ Astronautics,2009,41（6）：823-827.
[5]Barnathan M., Megalooikonomou V， Faloutsos C，et al. TWave: High-Order Analysis of Spatiotemporal Data [A]. In: Zaki M J, Yu J X., Ravindran B, Pudi V (Eds.)．Advances in Knowledge Discovery and Data Mining[C]Berlin: Springer Berlin Heidelberg,2010,246–253
[6].方利民，林 敏.小波聚类方法和近红外光谱技术用于药片种类判别[J]光谱学与光谱分析，2010,30（11）:2958-2961
FANG Li-min, LIN Min. Discrimination of Varieties of tablets using Near-infrared spectroscopy by wavelet clustering [J]Spectroscopy and Spectral Analysis，2010,30（11）:2958-2961
[7] Y1ld1r1m A A, Özdoğan C. Parallel wavelet-based clustering algorithm on GPUs using CUDA [J]. Procedia Computer Science, 2011,3 : 396–400
[8] [王伟魁，曾周末，李一博，等.基于小波聚类的罐底声发射源聚集区域自动识别[J].纳米技术与精密工程，2012,10（6）:531-536
WANG Wei-kui， ZENG Zhou-mo， LI Yi-bo，et al. Auto recognition of acoustic emission source distribution regions of tank bottom based on wavelet clustering[J] Nanotechnology and Precision Engineering, 2012,10（6）:531-536.
[9]Anggraini E L，Suciati N，Suadi W. Parallel computing of WaveCluster algorithm for face recognition application [C]// Proceedings of the 2013 IEEE International Conference on Quality in Research. Yogyakarta: IEEE，2013:56-59
[10] Urso P D， Maharaj E A.．Wavelets-based clustering of multivariate time series[J].Fuzzy Sets and Systems ,2012，193:33–61
[11] Sheikholeslami G，Chatterjee S，Zhang A．WaveCluster: a wavelet-based clustering approach for spatial datain very large databases [J].The VLDB Journal 2000(8)：289-304
[12] 钱江波，董逸生.一种基于广度优先搜索邻居的聚类算法[J].东南大学学报，2004,34（1）：109-112
Qian Jiang-bo, Dong Yi-sheng . A clustering algorithm based on broad first searching neighbors[J] Journal of southeast university,2004,34（1）：109-112.
[13].陈 昊，侯慧群，杨承志，等. SA-BFSN ：一种自适应基于密度聚类的算法[J]计算机工程与应用，2012, 48（36）：186-189
CHEN Hao, HOU Hui-qun, YANG Cheng-zhi, et al. SA-BFSN：adaptive algorithm based on density clustering.[J]Computer Engineering and Applications, 2012, 48（36）：186-189
[14] 刘福荣,王宏伟,高晓智.基于粒子群优化聚类的汽轮机组振动故障诊断[J]振动与冲击，2010,29(8):9-12
LIU Fu-rong, WANG Hong-wei, GAO Xiao-zhi. Steam turbine vibration fault diagnosis based on particle swarm optimization clustering[J]Journal of Vibration and Shock，2010,29(8):9-12
[15] 陈安华，周 博，张会福，等基于改进人工鱼群算法的机械故障聚类诊断方法[J]振动与冲击，2012,31（17）:145-148
CHEN An-hua，ZHOU Bo，ZHANG Hui-fu，et al.A clustering method for mechanical fault diagnosis based on improved fish-swarm algorithm[J]Journal of Vibration and Shock，2012,31（17）:145-148
[16]涂俊超. 基于振幅熵和功率谱重心的聚类分析在旋转机械故障诊断中的运用[D]南昌：南昌航空大学，2014
TU Jun-chao. The application of clustering analysis based on amplitude entropy and power Spectral Centroid to the fault diagnosis of rotating machinery[D]Nanchang: Nanchang Hangkong University,2014
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(1871 KB)
