高级检索
苗洁, 曹伟娟, 潘万彬, 王毅刚. 双层次装配语义智能识别与设置方法[J]. 计算机辅助设计与图形学学报, 2024, 36(3): 423-434. DOI: 10.3724/SP.J.1089.2024.19766
引用本文: 苗洁, 曹伟娟, 潘万彬, 王毅刚. 双层次装配语义智能识别与设置方法[J]. 计算机辅助设计与图形学学报, 2024, 36(3): 423-434. DOI: 10.3724/SP.J.1089.2024.19766
Miao Jie, Cao Weijuan, Pan Wanbin, Wang Yigang. An Intelligent Approach to Identifying and Setting Dual-Level Assembly Semantics[J]. Journal of Computer-Aided Design & Computer Graphics, 2024, 36(3): 423-434. DOI: 10.3724/SP.J.1089.2024.19766
Citation: Miao Jie, Cao Weijuan, Pan Wanbin, Wang Yigang. An Intelligent Approach to Identifying and Setting Dual-Level Assembly Semantics[J]. Journal of Computer-Aided Design & Computer Graphics, 2024, 36(3): 423-434. DOI: 10.3724/SP.J.1089.2024.19766

双层次装配语义智能识别与设置方法

An Intelligent Approach to Identifying and Setting Dual-Level Assembly Semantics

  • 摘要: 作为装配体模型中的重要内容,即装配语义,目前大多采用人工交互的方式进行设置,过程往往费时低效.为解决此问题,提出一种双层次装配语义智能识别与设置方法.首先,改进现有的图注意力网络,将其拓展为双层次识别网络,实现透过各种几何形状,智能识别每个零件模型表面的典型运动副接口;其次,改进现有反向传播人工神经网络的网络结构以提高网络性能,智能识别每个零件模型所有运动副接口上蕴含的装配约束类型及关联的几何实体;最后,基于上述识别的信息,任意2个零件模型之间自动搜索配对的运动副接口和装配约束几何实体,并快速且半自动地设置它们之间完整的装配语义.为有效地支持上述网络模型训练,构建了一个包含2 787个CAD零件模型的数据集.实验表明,该方法对运动副接口和装配约束的类型及关联几何实体识别的准确率均超过93.0%.同时,与现有的相关工作相比,所提方法具有有效地适用于快速设置各种装配体模型其装配语义的优势和潜力.

     

    Abstract: Assembly semantics, as a vital content of an assembly model, is mainly set interactively by designers, which is usually time-consuming and inefficient. To account for this, an intelligent approach to identifying and setting dual-level assembly semantics is proposed. First, the existing graph attention network is improved where it is extended to a dual-level identification network, identifying all typical kinematic pair interfaces on each part model that have various geometric shapes but consistent kinematic semantics. After that, the existing back-propagation artificial neural network structure is modified for improving performance, recognizing all assembly constraint types (as well as their associated geometric entities) that are embodied in each kinematic pair interface. Based on the above-identified information, the mating kinematic pair interfaces and mating assembly-constraint geometric entities between arbitrary two-part models can be searched automatically, and the full assembly semantics between them can be rapidly and semi-automatically set. To train the aforementioned network, a dataset containing 2787 CAD models is generated. Experiments show that the accuracy of identification on the kinematic pair interface or on the assembly constraint type (as well as its associated geometric entity) is more than 93.0%. Besides, compared to recent related works, the proposed approach also has some advantages and potentials to set the assembly semantics for various assembly models rapidly.

     

/

返回文章
返回