Automatic assembly modeling predicts and matches assembly features accurately
Automatic assembly modeling through attention-based assembly feature mate prediction and assembly feature pattern recognition
Computer Vision and Pattern RecognitionComputational Engineering, Finance, and ScienceGraphics
Summary
Building complex 3D models of assembled products usually requires lots of manual work and experience. The authors created a new computer method that can automatically match parts together by learning how their connecting surfaces fit. They made a big dataset to train their system and used a special attention-based network to guess how parts connect. Their method achieved about 75% accuracy in predicting correct assembly constraints without needing extra hints, and even higher accuracy when given some guidance.
What this means in practice
- •For cad software developers: Integrate automated assembly feature mate prediction to reduce manual input and speed up 3D CAD assembly modeling processes.$Commercial implications: Allows CAD software vendors to offer smarter assembly modeling features that automatically generate editable constraints, enhancing user productivity.
- •For manufacturing designers: Use data-driven assembly feature matching to quickly validate and generate product assembly configurations from unassembled parts.
Authors
Ziheng Dai, Wanbin Pan, Zhihong Tang, Shuming Gao
Abstract
Assembly modeling plays an important role in constructing product models, yet it is still mainly performed via interactive operations that are experience-dependent and labor-intensive. Data-driven strategies hold promise for automating this process; however, existing approaches either predict poses that cannot directly generate editable B-Rep assembly constraints or require prescribed part pairs or predefined assembly faces. To reduce the large candidate space of constraint prediction without predefined assembly faces, we propose a data-driven framework based on assembly feature mate prediction. The framework performs automatic assembly modeling from unassembled B-Rep parts, using assembly features to group the geometric entities of local mating interfaces and restrict candidate formation. Given the lack of suitable assembly feature annotations in existing datasets, we construct a large-scale dataset through an automatic annotation pipeline. Using the annotated dataset, we train an attention-based network to predict assembly feature mates, with Engineering Compatibility Fusion (ECF) incorporating explicit engineering compatibility into learned matching scores. To improve the accuracy of automatic assembly modeling, we use assembly feature patterns (AFPs) to guide the matching process. Finally, a post-processing search selects assembly feature mate and AFP mate candidates, whose associated constraints are generated and solved to complete assembly modeling. Experimental results show that the framework achieves assembly constraint accuracies of 74.79% on the six-assembly comparison set and 64.09% on the extended test set of 16 assemblies, which includes the comparison set. With ground-truth face labels supplied as additional input, the corresponding accuracies increase to 81.78% and 80.93%, respectively.