A method for recognising feature interactions and feature components within the interactions

Handling feature interaction is an outstanding issue in the feature recognition approach. This paper presents a method for recognising the presence of feature interactions and for determining the feature components within the interactions. First, two general feature types, namely depression and protrusion features, are identified from B-rep models based on a modified convex hull concept. Secondly, the identified features are represented by a modified AAG (Attributes Adjacency Graph) for facilitating their classification into low-level feature components, such as slots, pockets and bosses. Any unrecognisable features that remain after this second step are regarded as interacting features and they are finally recognised as low-level features via a process of virtual face building and volume adding.     

基于属性邻接图的加工特征识别研究

从零件的CAD模型中获取工艺设计所需的加工特征信息是CAPP的基础,也是实现CAPP与CAD集成的关键。研究旨在探讨中等复杂程度机械零件的加工特征识别方法。采取方法是从三维设计软件中得到CAD模型,对该模型输出的STEP AP203文件进行处理,获得面特征及其连接边的凹凸性,得到属性邻接图,将其进行处理得到全凹(或全凸)连接的子图,然后将子图中所有代表毛坯面的节点去掉,剩下的就是各特征对应的特征子图。再按照特征子图匹配法,将每个子图与预先定义的特征图进行匹配,就得到了所需要识别的特征。实例结果显示该方法是简便有效的,大大减少了图匹配的计算量。     

基于再扩展属性面边图的复杂结构件特征识别技术

针对飞机结构件的特点,提出了基于再扩展属性面边图的特征识别算法,该算法以再扩展属性面边图为基础,用种子面表示特征痕迹,基于种子面进行痕迹的检索和扩展,能够有效处理飞机结构件中的曲面特征和相交特征.基于以上研究开发的原型系统已在某大型航空制造企业框类零件数控加工中应用验证,提高了飞机结构件数控编程的效率和质量.     

Automatic recognition of machining features from a solid model using the 2D feature pattern

Feature recognition systems are now widely identified as a cornerstone for conceiving an automated process planning system. Various techniques have been reported in the literature, but a few of them acquired a status of generic methodology. A flexible and robust approach is demanded for recognising a wide variety of features, e.g., non-interacting, interacting circular and slanting features. This research aims to exploit the concept of the ray - firing technique, in which a 2D surface pattern for each feature is generated and information is extracted from these patterns to correlate it with the corresponding machining features. The system first defines a virtual surface and then probing rays are dropped from each point of this surface to the 2.5D features of the B-rep solid model. According to the length of rays between the bottom face of the 2.5D machining features and the virtual surface, 2D feature patterns are formed for each machining feature. Finally, features are recognised using an algorithm described in this article. Different types of examples have been considered to demonstrate the effectiveness of the proposed approach.     

Automatic recognition of design and machining features from prismatic parts

Prismatic parts usually comprise basic features, such as slots, steps, holes, bosses, which may intersect with one another. In general, automatic recognition of intersecting features is difficult and may present bottlenecks when automating the design procedures which make use of features for downstream operations.This paper presents a novel approach to recognising intersecting features and auxiliary features due to tool movements and cutter radii. Since no cutting edges can be perfectly sharp, corner fillets on machined features are invariably created by end mills and other cutters. Fillets, on the other hand, could very well be features which have been designed to increase strength and reduce stress concentration of certain features. A feature recognition system is proposed to recognise features having fillets which may be either design or manufacturing features. This information will be useful to the product designer as it would be possible to distinguish between the intended and unintended features of a part. The developed system has been implemented on an HP-ME30 Solid Modeler.     

基于特征面分割的自动特征识别

相交特征的识别是自动特征识别的难点,提出一种新的基于图的特征识别算法,首先构造加工面邻接图(MFAG),然后通过特征匹配快速识别出孤立特征,通过特征面的延拓、求交与分割,主动找出特征痕迹,分解出基本特征子图,从而识别出相交特征.该算法使孤立特征和相交特征的识别模式统一,同时有利于与交互特征定义集成.     

Extraction of machining features for CAD/CAM integration

Feature-based CAD/CAM integration is a technology used to realise automatic transmission and conversion of component information among CAD, CAPP and CAM applications. A feature is the medium of information transmission in the integration. Since a process planning downstream application has a different viewpoint from the component designer, feature conversion or feature extraction methodology is used to create a machining feature model based on the design feature model. One of the major difficulties in generating machining features is the preservation of feature integrity because of feature interactivity. The most current research, therefore, focuses on the planar-type form feature conversion. This paper discusses the problem of feature interactivity and proposes a feature-based approach to generating hole-series machining features from a design feature model. Hole-series features are important machining features for gearbox components used in machine tools. These kinds of features cannot be obtained directly from a design feature database. A constraint-based method is developed in this paper to define a hole-series feature model based on the geometric and topological information extracted from the design database. In addition, a STEP file is generated to interface the converted machining feature model with the downstream CAPP application. The implemented feature conversion system is verified by considering its application to some component examples and the developed prototype CAPP system. This revised version was published online in October 2004 with a correction to the issue number.     

基于改进图匹配的角盒类零件型腔加工特征自动识别

为满足角盒类零件型腔特征识别需求,提出了一种基于改进图匹配的型腔特征自动识别方法.分析了角盒类零件型腔特征,提取了特征简化模型的共性模板属性.获取了模型栅格高度点云数据,以高度中值作为阈值并将其转换为0-1特征值矩阵,提取了型腔面投影特征值以分离识别型腔壁边面.采用共性模板面邻接属性判定搜索型腔侧壁面,最终识别出了包含...     

A shape feature recognition framework and its application to holes in prismatic parts

A feature recognition framework is proposed, consisting of a feature definition part and a feature matching part and operating on a B-rep model. Feature definition consists of a unique name, of a feature template yielding feature geometry, and of a set of parameter-extracting procedures yielding shape parameters. A feature template is defined in terms of building blocks and their relationships and properties. Building blocks are defined mainly in terms of profiles, their outward indexes, the types of their edges (solid/void) and their orientation. Features are classified as main and auxiliary, the former being further classified as unique and non-unique. Feature uniqueness is ensured by using key blocks that do not share elements with other feature blocks. Patterns of identical features are also identifiable. These concepts were implemented in Prolog for hole features and tested for real engineering components.     

面向STEP文件基于属性邻接图的加工特征识别研究

研究了从中性文件STEPAP203文件中得到加工几何特征的方法。首先分析了STEPAP203文件的组织结构,然后从中提取有关面和面之间的连接信息,用属性邻接图表示出来。讨论了基于特征子图匹配的特征识别方法以及属性邻接图的分解。用此特征识别方法实现了中等复杂程度机械零件的特征识别。     

模具中的规则窄深特征自动识别

模具中通常含有一些细长窄深区域需要进行特种加工。为自动确定这些区域,提出了一种将基于痕迹和体分解特征识别方法相结合的规则窄深特征自动识别方法。首先定义了规则窄深特征,利用规则窄深特征的特性,提取特征痕迹;再从痕迹出发生成特征的初步扩展体,通过几何推理,逐步切割特征扩展体,得到对应痕迹的特征,并通过启发式方法进行特征组合;最后,通过实例验证了规则窄深特征自动识别方法。将自动特征识别技术应用于模具非机加工领域,可为窄深特征特种加工提供一个计算机辅助设计与计算机辅助工艺规划连接的智能接口。     

基于波形特征和小波的脉搏波特征点识别研究*

脉搏波是人体心脏有节律的收缩射血,血液流经弹性血管所产生的波动。不同的人在不同的生理状态下的脉搏波波形是不同的,因此脉搏波的特征点识别对于分析人体的生理病理状况、预防诊断心血管疾病是非常有帮助的。本文结合小波分析和脉搏波时域特征,提出了一种从脉搏波预处理到特征点准确识别的综合算法,实验表明该算法能够有效识别处于不同运动状态的脉搏波特征点,为后续相关人体生理病理信息的有效提取创造了条件。     

Retrieval of machining information from feature patterns using artificial neural networks

The integration of design and manufacturing has been the subject of much debate and discussion over a long period of time. Recognition of feature patterns and the retrieval of necessary machining information from those patterns play vital roles in this process of integration, as they facilitate the selection of the necessary manufacturing parameters required to transform the designed product into a final physical entity. Although the problem of recognising features from a solid model has been exclusively studied, most existing product models are expressed as engineering drawings. Moreover, the solid model can only provide complete 3D topological and geometrical data and some of the essential machining information cannot be retrieved. In this paper, an approach for defining engineering features, like slots, steps and circular pockets is proposed using binary strings. Two artificial neural networks, one for slots and steps and the other for circular pockets, are designed and developed. These neural networks take the binary strings as inputs and give the relevant machining information as outputs. The networks are trained with non-interacting features and after training, those will become capable of providing the necessary machining information for both non-interacting and interacting features in the domains of slots, steps and circular pockets. This novel approach can further be extended to other features for retrieving relevant machining information and thus facilitating the effective integration of design and manufacturing.     

基于Pro/E平台的零件可制造特征分析

从DFM系统总体要求及各功能模块的结构关系出发,研究以VC.NET为统一开发平台,在统一数据库下构建Pro/E平台上基于特征的产品可制造性设计与分析框架体系。运用MFC动态链接库(DLL),通过Pro/E提供的Pro/TOOLKIT接口,实现产品零件制造特征的提取、重构和交互操作,通过对制造信息的进一步封装,建立制造特征类库,较好地解决了通过零件三维设计模型获取零件的制造信息的方法。     

Influence of time and length size feature selections for human activity sequences recognition

In this paper, Viterbi algorithm based on a hidden Markov model is applied to recognize activity sequences from observed sensors events. Alternative features selections of time feature values of sensors events and activity length size feature values are tested, respectively, and then the results of activity sequences recognition performances of Viterbi algorithm are evaluated. The results show that the selection of larger time feature values of sensor events and/or smaller activity length size feature values will generate relatively better results on the activity sequences recognition performances.     

基于序列图像提取稳定特征点的虹膜识别算法

为了尽可能降低不稳定特征点对识别率的影响,研究提出了基于序列图像提取稳定特征点的虹膜识别算法.该算法首先用二维Gabor滤波器对序列虹膜图像提取特征编码,然后对该序列特征编码求交集以提取稳定特征点,并利用这些稳定特征点建立虹膜的特征模板库,最后通过计算相似度,获得识别结果.在实验室采集的序列虹膜图库上,当等错率为0.3017%,分类阈值为0.6402时,正确识别率可以达到99.73%.实验证明该算法是有效、可行的,并更好地提高了虹膜的分类精度和改善了虹膜的识别性能.     

基于STEP文件的图匹配方法研究

从零件的CAD模型中获取工艺设计所需的加工特征信息是CAPP的基础,也是实现CAPP与CAD集成的关键。研究旨在探讨中等复杂程度的机械零件加工特征识别方法,采取其方法从三维设计软件中得到CAD模型。对该模型输出的STEPAP203文件进行处理,获得面特征及其连接边的凹凸性,得到属性邻接图,将其进行处理得到全凹（或全凸）连接的子图,然后将子图中所有代表毛坯面的节点去掉,剩下的就是各特征对应的特征子图。再按照特征子图匹配法,将每个子图与预先定义的特征图进行匹配,就得到了所需要识别的特征。实例结果显示,该方法简便有效,大大减少了图匹配的计算量。     

A system for recognition and modification of machining features on prismatic components

A recognition process of the features in a part model resorts to the knowledge of an application engineer. The knowledge is encoded as rules of the recognition procedure at the beginning that are applied to the part model during the recognition process. Such a human interaction is difficult to control in extracting the intended features because the intended features by the application engineer may change from one engineer to the other and the external situations. Instead, we treat the result of the recognition process as a rough extraction and allow the user interactively modify the result. In this paper, we present a feature recognition system where the user can inspect the result of the recognition and delete recognized features interactively.     

Extraction/conversion of geometric dimensions and tolerances for machining features

It is important for a feature-based system to preserve feature integrity during feature operation, especially when feature interaction occurs. The paper presents a feature conversion approach to convert design features used in a design model into machining features for the downstream applications. This process includes both form features (geometric information) and non-geometric features conversion. Most researchers have concentrated on geometric information extraction and conversion without tackling the important problem of non-geometric feature information. This paper focuses on the extraction and conversion of feature geometric dimensions and tolerances (GD&T) for downstream machining application.The main barrier to the integration of a feature-based CAD/CAPP/CAM system – feature interaction – is discussed in this paper, which alters design features in their geometries and non-geometric information. How to identify and validate these feature dimensions and tolerances is one of the key issues in feature interaction conversion. The development of robust methodologies for preserving feature integrity for use in process planning application is the main thrust of the work reported in this paper.     

基于全视域特征表征与ELM-Adaboost方法的情绪辨识研究

情绪在人类的行为和认知中具有不可或缺的地位,开展情绪辨识研究具有非常重要的实际意义。为提高四类情绪多被试交叉辨识的准确性,提出了基于全视域特征表征与ELM-Adaboost的情绪辨识方法。首先,提出了基于融合信息的数据处理策略,交叉融合的多类生理信号构成的样本数据,有助于从全视域角度提取样本特征。其次,采用最大相关性最小冗余度的特征选择方法对融合后的特征进行选择,进而实现有效的情绪状态表征。最后,通过ELM-Adaboost方法构建的强分类器实现情绪状态辨识。多角度的实验分析研究充分证明了所提方法的有效性,四类情绪多被试交叉辨识准确率达到了83.06%。