基于特征矩阵的大型舱体类构件毛坯模型复杂特征分层识别方法

Feature Matrix Based Complex Feature Hierarchical Recognition for Blank Model of Large Cabin Component

大型舱体类构件是大飞机、火箭等航空航天飞行器型号的重要部件,具有众多复杂内部相交特征,给其内部特征的准确识别带来极大挑战,毛坯模型内部特征的有效识别是实现加工余量确定、切削参数优化及刀具路径规划的重要基础。提出了一种基于特征矩阵的大型复杂构件毛坯模型相交特征分层识别算法,实现基于毛坯模型几何拓扑信息的多层次复杂相交特征识别。首先使用阈值分割法识别和剔除大型复杂构件毛坯模型伪特征及其数据,进行毛坯模型优化。然后构建该优化毛坯模型的属性邻接图,采用分层识别方法对构件的优化毛坯模型相交特征进行分层处理,得到单一特征并计算其特征矩阵。将多类型单一特征均转换为特征矩阵,建立特征匹配库。最后将特征矩阵与特征库进行匹配,以进行模型相交特征准确识别。对具有多种特征的舱体零件毛坯模型进行实例验证,通过准确识别多类型特征分别验证了该算法的可行性和有效性。

Large cabin components are important parts of aerospace vehicles such as large aircrafts and rockets.They have many complex intersection features,which brings great challenges to the accurate identification of their internal features.The effective recognition of the internal characteristics of the blank model is foundation of the determination of machining allowance,optimization of cutting parameters and tool path planning.A hierarchical recognition algorithm for the intersection features of large and complex component blank models based on feature matrices is proposed,which realizes the multi-level complex intersection feature recognition based on the geometric topology information of the blank model.First,the threshold segmentation method is used to identify and eliminate the pseudo-features and data of the large and complex component blank model and optimize the blank model.Then,the attribute adjacency graph of the optimized blank model is constructed,and the intersection features of the optimized blank model are processed in layers by using the hierarchical recognition method to obtain a single feature and calculate its feature matrix.Multi-type single features are converted into feature matrices,and feature matching libraries are established.Finally,the feature matrix is matched with the feature library to accurately identify the intersection features.The blank model of cabin parts with multiple features is verified by cases,and the feasibility and effectiveness of the algorithm are verified by accurately identifying multiple types of features.