Extraction Profile Feature Points of Complex Parts Based on Genetic Algorithms

Abstract

The structures of mechanical parts are becoming more and more complex with the continuous expansion of the design industry. In this article, the profile points are reduced first according to the angle and distance threshold. Based on the minimal integral square error (ISE), Genetic algorithms (GAs) are then used with line segments and circular segments as the primitive form cell so that the profile feature points can be identified and extracted for the complex parts. It is shown that the genetic algorithms are successful for complex parts, although for a large amount of points, computation time is longer, and this will be considered in our further work.