QSCC: A Quaternion Semantic Cell Convolution Graph Neural Network for MBD Product Model Classification
Chengfeng Jian, Zewen Sheng, Yiqiang Lu, Mingliang Lin, Meiyu Zhang, Xianghui Hou
Abstract
Model-based definition (MBD) 3-D engineering has gained wide popularity that enables smart manufacturing. Its tip orientation to the effective reuse of MBD-based product models for creating efficient digital twins. The deep-learning-based 3-D model classification is an important way in the most recent years, but the existing methods only concern geometric information with very little or no manufacturing information. In this article, we proposed quaternion semantic cell convolution (QSCC), the quaternion semantic cell convolution graph neural network for MBD product model classification. It is mainly composed of the quaternion product semantic cell (QPSC) and the quaternion simple graph convolution (QSGC). The QPSC is established to fully express the digital twins' semantic information, which includes the multidimensional product manufacturing information of the MBD model. The QSGC is established by embedding QPSC into the quaternion vector space, which serializes the multigranularity semantic features to learn the context semantics through the gated recurrent unit. Compared with existing methods, our approach can solve the problem of model classification with similar geometry but different functions. Specifically, our approach can solve the ambiguity problem caused by blend features such as chamfer. We give quantitative and qualitative evaluations to demonstrate the accuracy and efficiency.