Full-Text Search:
Home|About CNKI|User Service|中文
Add to Favorite Get Latest Update

Application of K-means Clustering Algorithm to Divide Surface and Experimental Verification

WU Ming-yang;ZHANG Rui;YUE Cai-xu;LIU Xian-li;DING Yun-peng;ZHU Lei;School of Mechanical and Power Engineering,Harbin University of Science and Technology;  
In view of the quality problems of large panel die during integrative processing,the method of slice surface partition is used with the goal of dispersing the surface in accordance with certain accuracy.The geometric parameters and processing parameters of the discrete points are obtained,and then the surface is roughly divided.K-means clustering algorithm is adopted to further determine the amount of surface area and number of clustering center.And Voronoi diagram algorithm is used to extract the boundary of the surface.Different areas are processed using different processing method for the dividing surface of aluminum alloy material.Through the contrastive processing experiments between traditional method and the method of slice surface partition,the correctness and feasibility of proposed method are verified.
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©CNKI All Rights Reserved