高级检索

基于BP二分类网络的复杂加工特征的识别算法

Recognition Algorithm of Complex Machining Features Based on BP Binary Classification Network

  • 摘要: 加工特征识别是实现从设计到数字化加工无缝连接的重要方法, 是智能制造的重要保障之一, 能够从实体模型的几何拓扑关系中提取出有价值的制造语义信息, 减少设计向加工转变中的信息丢失. 然而现有的加工特征识别方法对复杂特征的处理还不能满足工程需要. 为了提高对复杂制造特征的识别性能, 提出一种基于BP二分类网络的复杂加工特征识别算法. 首先, 设计了在B-Rep模型中识别加工特征组成面的方法, 并基于工程实践, 对相关的特征面进行合并处理. 其次, 根据构成特征的特征面的边的属性, 自定义特征编码规则, 并将特征表示为12维特征向量. 然后, 针对铣削零件中常见的6种加工特征设计了6种多重BP二分类网络, 并运用自主设计的特征数据集对网络进行训练, 获得了良好的特征识别效果. 为了构建较大规模的训练用的加工特征数据集, 设计了特征数据集自动生成方法, 运用广义几何欧拉公式对自动生成特征数据集的模型进行了有效性验证. 最后, 针对神经网络识别失效的相交加工特征, 运用基面的概念将相交特征分解为多个孤立特征, 再用网络进行特征识别. 通过实例验证了该方法的可行性与有效性.

     

    Abstract: Identification of machining features is an important method to realize seamless connection from design to digital processing, and is one of the important guarantees of intelligent manufacturing. It can extract valuable manufacturing semantic information from the geometric topological relationship of solid model and reduce the information loss in the transition from design to processing. However, the existing machining feature recognition methods can not meet the needs of engineering. In order to improve the recognition performance of complex manufacturing features, a novel feature recognition algorithm based on BP binary classification network was proposed. Firstly, a method to identify the component surfaces of machining features in B-Rep model is designed, and the related feature surfaces are combined based on engineering practice. Secondly, the feature coding rules are customized according to the properties of edges from the feature surfaces, and the features are represented as 12-dimensional feature vectors. Then, 6 kinds of multi-BP binary classification networks are designed for 6 kinds of common machining features in milling parts, are trained by self-designed feature data set and obtain the good feature recognition effect. In order to construct a large scale machining feature data set for training, an automatic generation method of feature data set is designed, and the generalized geometric Euler formula is used to verify the validity of the model that automatically generates the feature data set. Finally, based on the concept of ground surface, the intersection features are decomposed into multiple isolated features, and then the network is used to identify the features. The feasibility and effectiveness of this method are verified by an example.

     

/

返回文章
返回