在特征造型中扑元素命名机制的研究

特征造型中最根本问题之一是模型的拓扑元素,经特征编辑重构模后的识别。为此本文提出了基于ＧＳＧ村的拓扑标识号命名机制和虚拓扑标识号命名机制,并运用拓扑元素的继承性、割裂关系表的约束准则和相似性匹配技术实现其只号在新旧模型中正确传递,大大提高特征编辑的可靠性。     

基于特征的参数化设计和实体模型编辑的研究

本文概述和研究了基于特征的模型表示、特征的生成方法与手段、特征参数和约束尺寸的变量命名机制、约束关系的求解方法后,提出基于面向装配设计的抽取零件模型策略和重用ＣＳＧ树技术,实现实体模型编辑与其历程树无关和加速实体模型生成,大大提高后期设计修改的灵活性,满足交互式设计需要。     

特征造型中拓扑元素和约束关系管理体系

在特征造型过程中，随着造型体数目的增加，设计模型将变得越来越复杂。为了能够正确地维护设计者的设计意图，提出了一种新的拓扑元素与约束关系管理体系。并给出了在此种管理体系下，特征拓扑元素编码和约束关系维护方法。将这种方法应用于造型过程中，必将使系统的设计效率有大幅度的提高。     

特征造型系统中草图元素编码方法研究

拓扑实体编码是特征造型系统重要的使能技术,而草图元素的编码是拓扑实体编码的基础.该文提出了草图元素编码的唯一性、恒定性和紧凑性原则,根据这些原则,给出了通过增加索引和标志位解决编码过程中共享草图点问题和编码重生成问题的方法.该草图元素编码方法已在特征造型系统InteSolid 2.0中采用.     

基于注意力机制的包装命名实体识别

目的 为了解决包装行业相关文本命名实体识别困难问题,提出在BiLSTM（Bidirectional Long Short-Term Memory）神经网络中加入注意力机制（Attention）和字词联合特征,构建一种基于注意力机制的BiLSTM深度学习模型（简称Attention-BiLSTM）,以识别包装命名实体。方法 首先构建包装领域词典匹配包装语料中词语的类别特征,同时将包装语料转换为字特征和词特征联合的向量特征,并且在过程中加入POS（词性）信息。然后将以上特征联合馈送到BiLSTM网络,以获取文本的全局特征,并利用注意力机制获取局部特征。最后根据文本的全局特征和局部特征使用CRF（Conditional Random Field）解码整个句子的最优标注序列。结果 通过对《中国包装网》新闻数据集的实验,获得了85.6%的F值。结论 所提方法在包装命名实体识别中优于传统方法。     

模块化夹具设计的研究和应用

利用夹具设计中常用到的典型夹具结构、拓扑结构和通用元件,应用UG软件三维参数化建立主模型,利用IMAN的PORTAL导入到工装资源库,在资源库中建立典型夹具结构、拓扑结构和通用元件模型分类结构,并加已命名、标注属性、分类、两维、三维预览图,然后将实例保存,供以后类似结构设计用或选择通用单元,提高设计速度和准确性。     

基于文化原型的创意设计应用机制模型构建

目的研究文化元素在文化创意设计中的应用机制。方法以文化的三因子论为理论指导,对文化元素进行整体结构的认知解析,然后从3个层次提炼关键性特征以及它们之间的内在联系和逻辑关系,组成特定文化元素的文化原型,构建基于文化原型的创意设计应用机制模型,最后以基于客家围楼文化元素的创意产品设计为例,对模型的可行性进行验证。结论获得了基于文化原型的创意设计应用机制模型,在设计实践中验证了其可操作性和有效性。     

从计算机辅助设计(CAD)到人辅助设计(HAD)——一种等几何拓扑优化方法（英文）OA

本文提出了一种新的设计模式——人辅助设计,以取代传统的计算机辅助设计。在人辅助设计中,计算机可以通过一种新的等几何拓扑优化自动完成整个产品设计,而人类仅需协助轻微修改设计以满足要求。文中提出了一种嵌入域等几何拓扑优化用于设计具有不规则设计域的复杂模型,并且可以基于分层等几何拓扑优化结果自动生成优化结果的可编辑几何模型。测试了三个算例以验证所提出的等几何拓扑优化模式,包括一个具有规则设计域的3D悬臂梁,一个具有不规则设计域的汽车零件和一个具有多尺度结构的MBB梁。结果表明,所提出的等几何拓扑优化模式可以自动生成高质量的优化模型。因此,该技术具有成为革命性技术的巨大潜力,将当前设计模式由计算机辅助设计转变为人辅助设计。     

产品质量安全风险监控拓扑模型研究

本文基于整体性治理的思想,分析产品质量安全风险监控系统复杂性,明晰风险监控系统的要素,提出了产品质量安全风险监控系统拓扑模型.认为产品质量安全风险监控系统是由宏观层面的树形拓扑结构,中观层面的网状拓扑结构和微观层面的环形拓扑结构构成.各主体间通过业务协调、责权利、激励评价等机制的构建,形成持续的横向、纵向和斜向互动,使得监控过程更加有序高效.     

一种支持纸的折叠、剪切与展开的计算模型

为了满足儿童剪纸方案的交互设计以及向儿童展示典型的儿童剪纸过程的需要,设计了一个支持纸的折叠、剪切与展开的计算模型,它包括当前纸态的几何与拓扑数据结构、操作过程的记录方法以及各相关功能的实现算法。以此计算模型为核心所开发的原型软件（命名为Virtual Paper）验证了该模型的可行性。     

Generation of optimal parting direction based on undercut features in injection molded parts

An algorithm has been developed for the automated recognition of undercut features for determining the optimal parting direction of injection molded parts. On the basis of the 3-D solid model of a molded part described in Boundary Representation (B-Rep), the geometrical entities and the information of a solid model and their topological relationships are extracted. According to these information, the criteria under which the undercut feature is formed are set up and the undercut feature directions (the withdrawal directions of side-cores or side-cavities) are identified. The optimal parting direction is chosen based on the criterion of maximizing undercut feature volumes in each undercut feature group. Through the case studies on industrial parts, the methodology developed is found to be efficient and effective in determining the undercut features and the optimal parting direction automatically.mining the optimal parting direction of injection molded parts. On the basis of the 3-D solid model of a molded part described in Boundary Representation (B-Rep), the geometrical entities and the information of a solid model and their topological relationships are extracted. According to these information, the criteria under which the undercut feature is formed are set up and the undercut feature directions (the withdrawal directions of side-cores or side-cavities) are identified. The optimal parting direction is chosen based on the criterion of maximizing undercut feature volumes in each undercut feature group. Through the case studies on industrial parts, the methodology developed is found to be efficient and effective in determining the undercut features and the optimal parting direction automatically.     

A compact adjacency‐based topological data structure for finite element mesh representation

This paper presents a novel compact adjacency‐based topological data structure for finite element mesh representation. The proposed data structure is designed to support, under the same framework, both two‐ and three‐dimensional meshes, with any type of elements defined by templates of ordered nodes. When compared to other proposals, our data structure reduces the required storage space while being ‘complete’, in the sense that it preserves the ability to retrieve all topological adjacency relationships in constant time or in time proportional to the number of retrieved entities. Element and node are the only entities explicitly represented. Other topological entities, which include facet, edge, and vertex, are implicitly represented. In order to simplify accessing topological adjacency relationships, we also define and implicitly represent oriented entities, associated to the use of facets, edges, and vertices by an element. All implicit entities are represented by concrete types, being handled as values, which avoid usual problems encountered in other reduced data structures when performing operations such as entity enumeration and attribute attachment. We also extend the data structure with the use of ‘reverse indices’, which improves performance for extracting adjacency relationships while maintaining storage space within reasonable limits. The data structure effectiveness is demonstrated by two different applications: for supporting fragmentation simulation and for supporting volume rendering algorithms. Copyright © 2005 John Wiley & Sons, Ltd.     

Applying the topological relationships of form features to retrieve part files from a CAD system

The efficient retrieval of stored CAD files is an area that has received significant attention in recent years. Several Product Data Management products have been developed, most of which are based on the use of coding concepts to retrieve designs. However, the limited number of codes that can be used limits the flexibility of part shape representation and also versatility in retrieving existing drawings. In this paper, an integrated approach using topological relationships among form features as the search indices is proposed. The use of a feature adjacency graph and also a feature topological relation graph that acts as the interface enables this approach to translate the feature-based B-Rep model of a part that is stored in the CAD system into topological relationships that are stored in a relational database. In addition, five types of queries based on topological relationships an; used to aid the retrieval of designs. The proposed technique for design retrieval is more convenient than traditional coding based methods:     

基于可拓符号学和眼动实验的黄梅挑花再设计研究

目的 针对传统文化符号再设计过程中,显隐性因子提取与表征存在模糊主观问题,提出一种基于可拓符号学和眼动实验的显隐性文化特征提取与应用的研究方法。方法 以黄梅挑花为例,在可拓符号学的基础上融入眼动实验,首先,利用爬虫技术提取黄梅挑花文化特征词(隐性因子),并进行可拓语义评估得到其可拓区间值;其次,运用眼动实验提取挑花纹样特征(显性因子),结合隐性因子可拓区间值进行综合图解语义评估;最后,将图案元素进行可拓变换设计。结果 变换结果在服饰纹样图案设计中得到合理应用。结论 研究表明:运用该方法可修正传统的依据从业经验及主观思维表征文化特征存在的偏差,能客观、科学地提取显隐性因子并作为设计因素,有助于更好地表达文创产品的文化内涵。     

Automated Autism Spectral Disorder Classification Using Optimal Machine Learning Model

Autism Spectrum Disorder (ASD) refers to a neuro-disorder where an individual has long-lasting effects on communication and interaction with others. Advanced information technology which employs artificial intelligence (AI) model has assisted in early identify ASD by using pattern detection. Recent advances of AI models assist in the automated identification and classification of ASD, which helps to reduce the severity of the disease. This study introduces an automated ASD classification using owl search algorithm with machine learning (ASDC-OSAML) model. The proposed ASDC-OSAML model majorly focuses on the identification and classification of ASD. To attain this, the presented ASDC-OSAML model follows min-max normalization approach as a pre-processing stage. Next, the owl search algorithm (OSA)-based feature selection (OSA-FS) model is used to derive feature subsets. Then, beetle swarm antenna search (BSAS) algorithm with Iterative Dichotomiser 3 (ID3) classification method was implied for ASD detection and classification. The design of BSAS algorithm helps to determine the parameter values of the ID3 classifier. The performance analysis of the ASDC-OSAML model is performed using benchmark dataset. An extensive comparison study highlighted the supremacy of the ASDC-OSAML model over recent state of art approaches.     

A referential scheme for modeling and identifying spatial attributes of entities in constructed facilities

This paper presents a referential scheme for representing and identifying the spatial extent of physical entities of constructed facilities, such as buildings and offshore structures. Using the basic operations of a non-manifold geometric modeler, a set of high-level algebraic operations is defined. The scheme and its algebra are used for modeling the spatial attributes of a facility entity at two levels: primary and secondary. The primary representation uniquely captures an entity's spatial attributes at the skeletal level and is used mainly for identifying discipline-independent topological relationships of that entity with others. Secondary representations, on the other hand, are used to provide an entity's discipline-specific geometric attributes. The topological relationships and geometric attributes of facility entities thus need not be explicitly stored, but can be computed on demand by the underlying non-manifold modeler.     

Deep Learning-Based Hybrid Intelligent Intrusion Detection System

Machine learning (ML) algorithms are often used to design effective intrusion detection (ID) systems for appropriate mitigation and effective detection of malicious cyber threats at the host and network levels. However, cybersecurity attacks are still increasing. An ID system can play a vital role in detecting such threats. Existing ID systems are unable to detect malicious threats, primarily because they adopt approaches that are based on traditional ML techniques, which are less concerned with the accurate classification and feature selection. Thus, developing an accurate and intelligent ID system is a priority. The main objective of this study was to develop a hybrid intelligent intrusion detection system (HIIDS) to learn crucial features representation efficiently and automatically from massive unlabeled raw network traffic data. Many ID datasets are publicly available to the cybersecurity research community. As such, we used a spark MLlib (machine learning library)-based robust classifier, such as logistic regression (LR), extreme gradient boosting (XGB) was used for anomaly detection, and a state-of-the-art DL, such as a long short-term memory autoencoder (LSTMAE) for misuse attack was used to develop an efficient and HIIDS to detect and classify unpredictable attacks. Our approach utilized LSTM to detect temporal features and an AE to more efficiently detect global features. Therefore, to evaluate the efficacy of our proposed approach, experiments were conducted on a publicly existing dataset, the contemporary real-life ISCX-UNB dataset. The simulation results demonstrate that our proposed spark MLlib and LSTMAE-based HIIDS significantly outperformed existing ID approaches, achieving a high accuracy rate of up to 97.52% for the ISCX-UNB dataset respectively 10-fold cross-validation test. It is quite promising to use our proposed HIIDS in real-world circumstances on a large-scale.