Pose-free assembly retrieval based on spatial-contact skeleton

In complicated product industry such as aircraft manufacturing, an assembly model contains abundant engineering information for use in design, manufacture, and maintenance. Assembly retrieval can be used to find relevant models for knowledge reuse. However, an assembly with rotatable joints may have many poses, which brings difficulty to assembly retrieval, since there is no pose principle for assembly design. Therefore, focused on rotatable joints in assembly, a skeleton-based descriptor for pose-free assembly retrieval is proposed. The centroid points of part surfaces and contact faces in an assembly are extracted to construct a spatial-contact skeleton. The skeletonbased distance is proposed to measure the distance between two surface points, which is invariant to the rotatable joints. The distribution of skeleton distances between two parts is used to describe the pair. Considering a part paired with all other parts in the assembly, the set of part pairs is used to represent a part, and the modified Hausdorff distance is used to measure the dissimilarity between parts for assembly retrieval. Experiments are conducted to compare the accuracy of the proposed descriptor to holistic and structureless descriptors. The proposed method is shown to retrieve assemblies with similar parts and structures regardless of their rotatable joints.

DESIGN REUSE METHOD FOR ASSEMBLIES IN CONCEPT DESIGN

Aiming at difficult sorting and retrieving complicated structure assembliesin assembly lib, a method for compartmentalizing assembly design resource by conceptual productstructure model is presented. The similar assembly retrieval mechanisms of symbol assembly relationgraph matching and symbol assembly relation graph similarity are discussed. The method is validatedby taking valve rod assemblies as example.