A micro complex part modeling method based on feature recognition

Abstract

The invention discloses a miniature complex part modeling method based on feature recognition, namely a method for reconstructing a CAD (Computer Aided Design) model by using a physical sample piece,which comprises the following steps of: establishing a point cloud topological relation, extracting feature points, partitioning point cloud data, reconstructing a model and the like. Wherein the stepof establishing the point cloud topological relation is responsible for finding k nearest neighbor points of each sampling point; the feature point extraction step is responsible for extracting feature points of the point cloud model; the point cloud data partitioning step is responsible for constructing feature lines and segmenting point clouds belonging to the same curved surface; and the modelreconstruction step is responsible for generating a curved surface by using the point cloud and the feature line, and obtaining an entity through curved surface projection. According to the modelingmethod, reconstruction of the complex curved surface part model can be completed with less manual participation. The modeling method provided by the invention has simple steps and higher efficiency, and can be suitable for reverse modeling of parts with similar geometrical characteristics.

Description

technical field [0001] The invention relates to a modeling method of miniature complex parts based on feature recognition, and belongs to the technical field of reverse engineering. Background technique [0002] Miniature complex curved surfaces are widely found in handicrafts such as jade carvings, earphones and hearing aids, and medical products. Forward modeling of such small-sized, complex-featured models is usually impossible. It is necessary to scan the entity into point cloud data and complete the reconstruction of the model through reverse engineering technology. [0003] At present, the methods of reconstructing CAD models by reverse modeling technology are mainly divided into two categories: reverse modeling methods based on surface reconstruction, and reverse modeling methods based on entity reconstruction. The reverse modeling method based on solid feature reconstruction is suitable for parts composed of basic features, and the reverse modeling method based on s...

AI Technical Summary

Problems solved by technology

In 2012, Angelina et al. improved the region growing method with region merging and genetic algorithm. The segmentation efficiency is high, but the boundary preservation is poor.

[0010] The above method of extracting feature points based on normal vector, curvature, extreme value of curvature, field force, and reflective point is better for sharp feature point extraction, but there are many surfaces with extremely small curvature in micro-complex surface parts, and the fillet angle between intersecting surfaces different

If the threshold is too small, it is easy to miss the feature points in the smoother place. If the threshold is too large, the feature points extracted in the sharp place will have a larger bandwidth, which will affect the accuracy of feature line reconstruction.

Images