基于实例的钣金零件检测信息三维表示技术

针对应用组件构架(CAA)钣金零件检测系统存在的缺陷,以VS2005为工具,调用API函数对CATIA进行二次开发,对钣金零件检测规划系统的功能进行完善.通过CATIA二次开发技术,将钣金零件检测信息加入零件特征树.设计数模在增加检测信息后形成了新的数模,为检验员工提供了3D视图的检测信息,实现了对整个检测系统的闭环设计.检测规划过程与三维数字化模型有效衔接,提高了生产效率和检验质量.     

飞机钣金特征的智能三维标注技术

采用CAA对CATIA进行二次开发,建立了钣金零件的检验规划系统.通过钣金零件的检验规划系统得到特征的检验方法,并将所有特征对应的检验方法通过智能三维标注技术,标注到三维模型上.智能三维标注,即通过人机智能交互的方式,将所有的检验信息全部表示在三维图上,简单,直观,明了.     

基于STL数据处理的钣金检验特征识别

针对CATIA对航空钣金零件的设计数模,应用CATIA二次开发工具,直接提取钣金零件的STL点云数据.基于CATIA平台,采用VC++6.0工具和CATIA的API函数,对提取的STL点云建立拓扑关系.基于高斯曲率进行曲面特征识别,提取钣金件的特征,并对检验方法进行规划,在实际的运用中提高了钣金零件的加工设计效率,使得产品开发周期缩短近30%,降低了加工成本,节约了能源和人力,实现了加工的高效性和精确性.     

基于三维模型的飞机钣金零件数字化检测技术

针对飞机钣金零件传统检验方法的缺点和局限性,提出一种利用光电设备对飞机钣金零件检验的方法.利用扫描仪对成形钣金零件进行扫描,得到钣金件点云模型,再利用模型对比软件,与钣金零件设计的三维模型进行对比,同时根据飞机钣金零件的检测规则库,判断钣金零件产品是否合格.     

Drools规则引擎在钣金检验特征识别中的应用

针对钣金零件的CATIA设计数模,利用其二次开发软件CAA,提取了CATIA特征树中的钣金零件综合信息．重点采用Drools规则引擎从复杂的特征树中提取待检测钣金零件的特征,并将特征信息存储到数据库中．     

基于实例推理的飞机钣金零件智能三维检验规划技术

研究了一种基于实例推理的飞机钣金零件的检验规划的专家系统,主要针对典型的飞机钣金零件进行检验规划.将飞机钣金零件检验涉及的知识主要划分为板材类钣金零件知识、型材类钣金零件知识、蒙皮类钣金零件知识、壁板类钣金零件知识,以及各自对应的实例库,将实例的特征属性用一组产生式规则描述,然后用基于规则的匹配方法加以推理识别,并进行修改,得到所需钣金零件的检验卡片.     

飞机钣金零件的数字化建模及逆向验证

数字化建模为某型号飞机钣金零件制造方式由模拟量向数字量传递转变的基础,该文以CATIA作为正向建模与逆向验证的集成三维设计软件,分析了模拟量信息提取与三维数字模型构造实施过程中流程管控和建模要素对于精确建模的动态关系,提出了激光扫描仪捕捉工装曲面特征与三维柔性测量臂获取零件外轮廓特征得到实际零件外形数字量的方法,通过逆向验证检验了正向建模的可行性。     

基于CATIA的橡皮囊工艺审查系统的二次开发

为实现橡皮囊成形工艺审查系统,采用CAA对CATIA进行二次开发,对橡皮囊成形零件进行工艺审查.分析了钣金零件的工艺特征,建立了CATIA与知识数据库的连接.通过对钣金零件特征信息的提取,对零件的各个成形特征分别进行审查,完成了橡皮囊钣金成形零件的审查.通过实例验证,高压橡皮囊成形工艺在3组不同压力下,6个凸弯边零件的凸缘部分都出现起皱现象,与系统审查结果一致,说明该工艺审查系统是可靠的.     

基于特征的飞机钣金零件检验过程规划

针对目前飞机钣金零件检验没有统一合理的标准检验过程,以VC++6.0与Oracle 10g数据库及CAA为平台,从三维数模中提取零件检验信息,采用专家系统或人工交互式的形式,设计规划基于特征的飞机钣金零件检验路线,以合理检验路线实现检验过程与数字化设计、加工过程的有效衔接,确保检验的合理、准确和高效.     

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.     

A staged approach for feature extraction from sheet metal part models

This paper proposes a staged approach of feature identification and extraction for sheet metal parts from a solid model. The identification and extraction process is divided into several stages. Each stage is automatically processed and the results after each stage can be interactively corrected and modified for the next stage. With this approach, the features of sheet metal parts can be automatically extracted from their well-defined solid models. At the same time, for ill-defined or inaccurate solid models of sheet metal parts, their features can be extracted through certain user interaction at a suitable stage. An attribute is also introduced in the paper to measure the relationship between sheet surfaces and other surfaces, and simplify the identification process. The approach has been implemented in the AutoCAD® environment and used by an industrial collaborator for the design of progressive dies.     

Processing of 3D sheet metal components in STEP AP-203 format. Part I: feature recognition system

To automate planning activities in a computer integrated manufacturing environment, an integrated system of feature recognition and reasoning is essential. An attempt is made in the present work to develop such a system for 3D sheet metal components. Though certain part-modellers use feature-based methodology, they lack the information required for manufacturing and entire feature information is lost when converted to a neutral format such as STEP AP-203. The proposed feature recognition identifies manufacturing features in a generic manner, while feature reasoning gives the information required for manufacturing. Taking 3D model data in STEP AP-203 format as input to the feature recognition system, the central plane of the component is first generated. Further processing of faces is carried out and various features with similar manufacturing attributes are identified using a set of rules based on the topology, geometry and Boolean logic. Different types of manufacturing features such as cut, stretched, drawn and bent features as well as composite features are effectively identified irrespective of their shape. The system proposed here was tested with components taken from industry and examples available in the published literature. The proposed feature recognition system serves as input to the feature reasoning system dealt with in Part II of this work (Kannan, T.R. and Shunmugam, M.S., Processing of 3D Sheet metal components in STEP AP-203 format. Part II: feature reasoning system. Int. J. Prod. Res., 2009 (in press)).     

高速冲击式粉体改性主机的三维建模与运动仿真

解剖一台实验室用HYB-0高速冲击式粉体表面改性机,利用CATIA软件的建模技术和运动仿真功能,实现高速冲击式粉体改性主机的三维建模、虚拟装配和运动仿真,着重讨论HYB主机主要部件的建模方法和虚拟装配方法。结果表明:虚拟装配的顺利完成验证了高速冲击式粉体改性主机所采用三维建模方法的正确性和所建模型尺寸的精确性,仿真结果能直观、准确地表达出该高速冲击式粉体改性主机的机械结构和运转情况。     

Processing of 3D sheet metal components in STEP AP-203 format. Part II: feature reasoning system

Both feature recognition and reasoning are needed for automating manufacturing planning activities for 3D sheet metal components. The feature reasoning system proposed here generates manufacturing information (e.g. flat pattern, locations of various features, internal cuts and blank profiles, type of tools required, operation sequence, bending sequence, etc.) for the features recognized in Part I of this paper. The issues related to flat pattern developments as experienced while using commercial software have been addressed in this work. A tool selection approach that uses standard tools for single and multiple blow features in punch presses is suggested. A zigzag method for operation sequencing and a virtual bend sequencing system are included. The system has been tested with various components and the results are compatible with industrial practices.     

基于多分辨率时频特征融合的声学场景分类

声学场景分类是计算机听觉中最难的任务之一,在单一特征条件下采用基本的卷积神经网络相对于传统的分类方法精度已经有所提升,但是效果依然不够理想。针对这一问题,在卷积神经网络框架下,提出了一种基于时频特征融合的声学场景分类方案。在分类模型构建方面,提出一种多分辨率卷积池化方案,构造多分辨率卷积神经网络,以更好地适应提取特征的时频结构;在特征选取方面,融合低层次包络特征对数——Mel子带能量和高层次结构特征——非负矩阵分解系数矩阵,把两种二维特征堆叠为三维特征送入分类模型。在2017年和2018年声学场景分类和事件检测挑战赛的开发数据集上进行了训练和测试。实验结果表明,文中提出方案比基线系统的分类精度分别提高7.5%和10.3%,可有效改善分类效果。     

An intelligent process planning system for micro turn-mill parts

An attempt has been made to develop a generalised system for the generation of process plan for the manufacture of micro parts in this work. It has two components; first one deals with automatic part feature extraction from feature-based model and second one performs the execution of process planning activities in accordance with feature using knowledge-based system approach. The proposed system maps extensible markup language (XML) data for the feature based-model and produces the corresponding manufacturing activities needed for the manufacture of micro parts. The process plan modules considered in this work includes process sequence, tools and fixtures, process parameters selection and set-up plan generation. An attempt has been made to develop process parameters selection module based on experimental investigation and optimisation apart from manufacturing catalogues and user manuals. Feature extraction through XML files avoids complex feature extraction process. The application of the developed system has been verified with a case study. The present system is limited to micro turn-mill features. Incorporation of more micro features and consideration of other activities of process plan ensures a complete process planning system for micro-machining processes.     

Additive Manufacturing of 3D‐Architected Multifunctional Metal Oxides

Additive manufacturing (AM) of complex three‐dimensional (3D) metal oxides at the micro‐ and nanoscales has attracted considerable attention in recent years. State‐of‐the‐art techniques that use slurry‐based or organic–inorganic photoresins are often hampered by challenges in resin preparation and synthesis, and/or by the limited resolution of patterned features. A facile process for fabricating 3D‐architected metal oxides via the use of an aqueous metal‐ion‐containing photoresin is presented. The efficacy of this process, which is termed photopolymer complex synthesis, is demonstrated by creating nanoarchitected zinc oxide (ZnO) architectures with feature sizes of 250 nm, by first patterning a zinc‐ion‐containing aqueous photoresin using two‐photon lithography and subsequently calcining them at 500 ºC. Transmission electron microscopy (TEM) analysis reveals their microstructure to be nanocrystalline ZnO with grain sizes of 5.1 ± 1.6 nm. In situ compression experiments conducted in a scanning electron microscope show an emergent electromechanical response: a 200 nm mechanical compression of an architected ZnO structure results in a voltage drop of 0.52 mV. This photopolymer complex synthesis provides a pathway to easily create arbitrarily shaped 3D metal oxides that could enable previously impossible devices and smart materials.     

Random forest and rotation forest ensemble methods for classification of epileptic EEG signals based on improved 1D‐LBP feature extraction

In this study, an efficient method for extracting and selecting features of unrefined Electroencephalogram (EEG) signals according to the one‐dimensional local binary pattern (1D‐LBP) is presented. Considering that taking a correct decision on various issues particularly in the field of diagnosing diseases, such as epilepsy, is of paramount importance, a functional approach is designed to extract the optimal features of EEG signals. The proposed method is comprised of two main steps: First, extraction and selection of features is performed based on a novel improved 1D‐LBP model followed by data normalization through principal component analysis (PCA); as combining 1D‐LBP neighboring models and PCA (1D‐LBP^c2p) method. The second step includes classification using two of the best ensemble classification algorithms, that is, random forest and rotation forest. A comparative evaluation is performed between the proposed methods and 13 distinct reported approaches including uniform and non‐uniform 1D‐LBP. The results are demonstrating that the combining method presented in our approaches has superiority along with efficiency by providing higher accuracy compared to the other models and classifiers. The proposed method in this paper can be considered as a new method for feature extraction and selection of other kinds of EEG signals and data sets.