冲压件的特征识别技术研究

特征识别是指从产品中识别出具有一定工程意义的几何形状,即特征信息的过程.作为CAD与CAPP间的智能接口,特征识别技术对实现CAD/CAPP/CAM的集成具有重要意义.针对冲压零件,尤其是带体积成形的冲压件的特点,提出了一种新型的冲压特征识别算法,并对特征识别中的难点-特征相交问题提出基于痕迹的冲压件相交特征识别方法.     

基于图和体分解的异型零件加工特征识别方法

针对异型零件具有众多复杂的相交特征，加工特征难以自动识别，进而影响其高效、高质量自动编程设计的问题，提出了一种基于图和体分解的加工特征识别方法。首先，以STEP中性文件作为输入，获取异型零件的几何、拓扑信息，以构造其毛坯特征和体积特征；同时，采用布尔减运算得到异型零件的加工体积特征，并将其分解为只含凸边关系的单一特征。然后，设计了一种基于特征面关系的几何特征矩阵（geometric feature matrix, GFM）和拓扑特征矩阵（topological feature matrix, TFM）构建方法，其中GFM侧重描述零件模型中面与面之间的位置关系，TFM侧重描述零件模型中面与面之间相邻的凹凸性，该方法较好地解决了传统属性邻接矩阵（attribute adjacency matrix, AAM）易出现无法准确表达零件加工特征的问题。最后，将异型零件的GFM和TFM与加工特征库进行匹配，以实现其加工特征的识别。在Visual Studio 2019平台中开发基于图和体分解的异型零件加工特征识别系统并开展验证实验。结果表明，所提出的方法能准确识别异型零件的所有加工特征，这可为异型...     

零件族描述和识别的语义技术

本文论述了零件族形成的自动的特征识别。为了形成零件族,应用了基于数据和特征两方面的框架描述系统,在应用分析聚类法时,考虑了零件的几何形态、尺寸以及加工顺序。系统还具有自学功能,因此,要把新零件分进零件族是比较方便的。     

集成环境下的成组夹具CAD

文中介绍了一种CAD/CAM集成环境下基于产品零件特征的三维成组夹具CAD系统,其关键技术是成组夹具CAD与工件CAD、CAPP的接口,基于产品零件CAD及CAPP的信息,零件按加工方位在成组夹具CAD系统中再现,及智能化的夹具方案设计。     

轴类零件二维工程图的特征识别方法

提出了轴类零件特征识别的方法.首先对特征进行了分类,接着建立了轴类零件的特征树模型,并且给出了实现该特征树模型的类结构;然后确定了主特征、辅助特征的识别原则和特征识别过程中的图形调整方法;最后描述了建立特征树的算法.在AutoCAD 2006环境下,以ObjectARX为开发工具,开发出了特征浏览器,实现了文中提出的原理和方法,以某典型轴类零件图为例进行了特征识别,识别效果良好.     

基于成组技术的夹具快速配置研究

提出了基于成组技术的夹具快速配置系统体系结构,研究贯穿了零件分类编码、夹具设计需求和夹具元件库的建立等方面.采用基于成组技术的方法开发了夹具快速配置系统,支持企业对夹具快速设计.     

基于自组织特征映射神经网络的零件加工尺寸类型识别

 提出一种基于自组织特征映射神经网络（SOFM）的零件加工尺寸类型识别方法.首先从三维CAD软件中获取包含零件特征数据的XML文件,并从文件中提取相应的加工特征及尺寸.然后以零件加工特征作为SOFM的输入层的神经元,经处理后作为SOFM的输入向量,利用SOFM自学习和自组织能力对输入向量进行训练.训练好的网络可以实现对零件加工尺寸类型进行较好的识别.最后通过对某零件的尺寸类型识别,验证了所提方法对平面、内孔、外圆和定位四类典型加工尺寸类型识别的有效性.     

基于三维钣金模型的加工特征识别

研究了钣金数控折弯加工特征信息的识别方法.可将三维CAD模型映射表示为由特征节点构成的网络图,这一方法可以对钣金零件的折弯加工工序模拟、折弯模具以及折弯夹具进行有效分析.     

冲裁件几何形状特征识别

在冲裁件的几何形状识别中,基于二维几何图形特点提出了外轮廓特征、内部图形布置特征、外轮廓特征矢量和内部图形距离。通过几何外部相似性与内部相似性,给出了外轮廓相似度计算与内部图形布置相似度计算方法。并根据外轮廓特征矢量的匹配,设计了二维图形的几何形状识别算法,利用实例验证了几何形状识别算法的可行性和有效性。     

融合几何特征的ICP改进算法在数字化测量评价中的应用

针对ICP算法对初值依赖程度高、在配准过程中可能陷入局部最优解的问题,提出了一种融合几何特征的ICP改进算法。利用零件具有丰富几何参数的特点,首先对实测点云进行基于曲率的体素采样,尽可能保留几何特征,再将点云的曲率差值和法向量夹角差值引入算法的目标误差函数中进行迭代计算,当目标误差函数达到设定阈值时迭代结束,得到最终配准结果。利用复杂曲面标准件进行了点云配准实验验证,结果表明：相较ICP算法,融合几何特征的ICP改进算法的收敛速度更快、误差更低;相较快速全局配准加ICP配准算法,融合几何特征的ICP改进算法在保证配准准确性的同时,减弱了对初值的需求,简化了点云配准过程。融合几何特征的ICP改进算法为促进零件的准确数字化测量评价提供了有力支撑,具有技术借鉴价值。     

A hint-based machining feature recognition system for 2.5D parts

The recognition of machining features in a part with arbitrary feature interactions is a difficult task. In this paper a hint-based machining feature recognition system for 2.5D parts with arbitrary feature interactions is presented. A pre-processor is used to screen out invalid 2.5D parts automatically and calculate the possible machining directions. The feature recognition starts with identifying the traces of features present in the part. Once a hint is found, geometrical reasoning is then used to compute other parameters to complete a maximally extended feature instance. The system handles hole, linear slot and circular slot features in the first pass. Various possibilities, like through or blind hole, through or blind slot, floorless or multi-floor slots are instantiated after their testing and repairing. The system then, likewise, handles floor-based and floorless pockets, in the second pass. The recognition process is tightly coupled with the machining environment to ensure machinability of the recognized features. A prototype of the system is implemented in visual C++ and ACIS® 3D modelling toolkit.     

采用图分解的特征识别算法研究

CAD/CAE模型转换,其关键在于如何将模型分解为最简单元,这些单元往往具有相近的网格划分属性,可以方便估计计算误差和计算时间。基于此提出了基于图分解的特征识别算法,对属性邻接图进行分解,根据分解后的属性邻接图中的连通分量生成体特征。该算法不再局限于特征类型,只要合理控制顶点的可分解性判断就可以得到期望的模型分解结果;同时该算法可以获得体特征,使得可以在特征这一粒度上进行特征删除和替换,以方便地完成模型的简化。     

Centre-based restricted nearest feature plane with angle classifier for face recognition

An improved classifier based on the nearest feature plane (NFP), called the centre-based restricted nearest feature plane with the angle (RNFPA) classifier, is proposed for the face recognition problems here. The famous NFP uses the geometrical information of samples to increase the number of training samples, but it increases the computation complexity and it also has an inaccuracy problem coursed by the extended feature plane. To solve the above problems, RNFPA exploits a centre-based feature plane and utilizes a threshold of angle to restrict extended feature space. By choosing the appropriate angle threshold, RNFPA can improve the performance and decrease computation complexity. Experiments in the AT&T face database, AR face database and FERET face database are used to evaluate the proposed classifier. Compared with the original NFP classifier, the nearest feature line (NFL) classifier, the nearest neighbour (NN) classifier and some other improved NFP classifiers, the proposed one achieves competitive performance.     

Computer-aided fixture design system for comprehensive modular fixtures

Fixture design plays an important role at the planning stage before shop-floor production. A desired fixture design can be employed to hold the workpart securely so that slippage and excessive deformation can be prevented during machining. Therefore, appropriate fixturing contributes highly to machining quality. To reduce lead time and the human effort devoted to fixture planning, computer-aided fixture design (CAFD) is required. In this paper, a CAFD system consisting of three modules, i.e. Fixture Data Management, Fixture Element Selection and Fixture Layout Design, is developed. According to fixture feature recognition and classification, a comprehensive fixture database in the Fixture Data Management module is constructed to maintain efficiently the fixture-related data. The domain of the fixture database consists of modular mechanical fixtures, modular hydraulic fixtures and modular V-blocks. After expertise extraction, suitable fixture elements can be automatically selected according to the machining conditions in the Fixture Element Selection module. Finally, by integrating previous reasoning algorithms, fixturing locations and orientations are determined. Feasible fixture layouts that meet manufacturing and inspection specifications can be generated in the Fixture Layout Design module. The prototype system is implemented under commercial CAD and database management system (DBMS) software. Comprehensive fixture databases and a rule-based knowledge base are built to provide effective data management. The paper aims to propose a systematic CAFD framework and application system to provide efficient decision support for different types of fixture planning.     

夹具CAD的相似性分析

依据夹具自身特征信息,以相似性理论为为基础,构造了夹具的相似信息模型．该信息模型提供了夹具概要设计和详细设计所需求的信息,并为夹具定量分析提供了相似分析算法,在该信息模型的基础上,建立了相似夹具零部件数据库,并设计了该数据库的管理程序．     

基于加权硬度特征的仪表数字识别

仪表数字识别是智能仪表应用的关键,针对现有方法对角度倾斜、半字识别效率低的问题,引入硬度特征参数来衡量数字图像目标区域在某方向上的抵抗变形的能力,提出了一种结合数字结构特征和统计特征的识别方法。通过对仪表盘上采集的数字进行分析,建立数字自上而下及自下而上的硬度特征库。并依据每个特征重要程度的不同,引入权重,采用加权特征匹配的方法进行数字识别。实验表明,算法不仅简单高效,对于整字和半字都能够取得很好的分割和识别效果,而且对旋转和畸变有较强的容错。     

一种有效降维的特征选择方法及其在水声目标识别中的应用

为在保证目标识别准确率基础上进行有效特征降维,文章以目标识别准确率为特征选择准则,提出一种支持向量机递归特征消除（Support Vector Machine Recursive Feature Elimination,SVM-RFE）快速筛选出部分优质特征子集与猫群算法（Cat Swarm Algorithm,CSO）迭代寻优结合的特征选择方法,并将该方法应用于水声目标识别的特征选择。实验数据处理结果表明：相比SVM-RFE和CSO特征选择算法,文中提出的方法在平均特征维数降低8%的基础上,平均目标识别率提高了1.88%,能够实现有效降维的目的。该方法对判断特征是否适合用于特定的目标识别也有一定应用价值。     

分布式光纤入侵信号检测与识别

分布式光纤声波传感(DAS)技术通过接收相干瑞利散射光的相位信息来探测声波或振动信号,具有灵敏度高、动态范围广等特性,可利用线性定量测量实现对信号的高保真还原。随着实际应用的需求不断提高,光纤入侵检测领域对事件的定位和识别提出了更高的要求,表现为对入侵事件的准确分类,因此将分布式光纤声波传感技术与模式识别(PR)技术相结合是目前研究的热门,有利于推动分布式光纤传感技术的应用发展。本文总结了近年来在分布式光纤入侵检测的模式识别技术中所应用的特征提取和分类算法的研究进展,回顾了几种实现入侵事件信号识别的特征提取方法及其在不同应用场合面临的特征选择难点,同时对特定事件识别算法的优劣进行分析归纳。     

一种视听融合的水下目标识别方法研究

特征提取是水下目标识别研究中最为关键的技术之一,特征参数的优劣将直接决定分类识别系统的性能。将声信号的听觉与视觉感知特征结合,应用于水下目标识别,通过实验得出如下结论,相比于单独应用听觉特征,融合特征的平均识别率能提高4%~6%以上,特别是将听觉特征与声谱图的Gabor小波变换特征、灰度-梯度共生特征进行融合后,分类性能较好,平均达到87%以上。     

A pilot framework developed as a common platform integrating diverse elements of computer aided fixture design

In the present study, an integrated computer-aided engineering platform has been developed for fixture design. Different computer aids needed for an automated fixture design system include geometrical modelling, finite element analysis, specialised mathematical tools, such as screw theory, and also artificial intelligence routines. It has been illustrated through several examples that the Python environment is a capable candidate to be employed for developing an integrated platform capable of providing these computer-aided tools. For this purpose, different specialised modules were developed, including a CAD system for geometrical modelling of workpiece, a mathematical analysis module for designing the locating system by using the screw theory, a FEM module being employed for support system design and an expert fixture planning module. The developed platform has also been examined for its capability to be interfaced with existing commercial CAD, FEM and expert system programmes.