Comparison of Clustering Techniques for Feature-Based Toolpath Generation in Dieless Manufacturing

Abstract

Abstract The aim of the current research is to compare the data clustering techniques for the geometrical feature extraction. The CAD models of the geometries are sliced to generate the data sets for clustering. This paper presents the comparison of K-means, Spectral, Density-based spatial clustering of applications with noise (DBSCAN) and Single Linkage Hierarchical (SLH) clustering techniques for arbitrary shaped contour clustering and formation of the groups based on the means of the contours. The factors considered for the comparison include, the inputs desired by the clustering techniques; time taken for contour clustering; ability to identify the arbitrary shaped contours; and the ability to form the features in feature-based toolpath generation in dieless manufacturing. The paper discusses three different approaches designed to accomplish the task. From the comparative analysis, it is found that the Spectral, DBSCAN and SLH can identify the arbitrary shaped contours. Further, DBSCAN and SLH clustering techniques can form the groups that can be used for feature-based toolpath generation in dieless manufacturing, whereas the other two fails to perform the same. The DBSCAN performs the contour clustering faster than the Spectral and SLH clustering.