基于点的鞋楦CAD/CAM技术

提出了实用的基于点的鞋楦CAD／CAM技术,给出了基于点的鞋楦几何模型定义,由经过规则化处理的鞋楦表面数据点集表示鞋楦模型;在此基础上研究了鞋楦CAD方法,通过对点集的操作完成鞋楦设计;实现了鞋楦数控编程,建立刀具模型并给出刀位点计算的详细过程．该技术已经成功地用于鞋楦CAD／CAM系统的开发,并用于实际生产,完成鞋楦的高效设计与制造。     

基于光切法的全三维量脚制鞋系统的设计和实现

介绍了基于光切法的全三维量脚制鞋系统。利用基于光切法的三维形貌扫描仪对足型进行测量,得到精度为±0.4mm的足型数据。根据足部关键参数,选择标准鞋楦。将脚型划分为多个特征段,足型数据和标准鞋楦的规则化点云拟合为NURBS曲线,各段内根据脚型的特点对标准鞋楦进行整体缩放以局部修改,利用能量优化原则同时修改控制点和权因子,对标准鞋楦进行修改,使其符合脚型的整体三维特点。定制鞋楦建模后,利用等距面法得到鞋楦的刀具加工轨迹并转化为通用格式的NC代码送入数据刻楦机进行加工,定制的鞋楦用于生产适合脚型的鞋子。该系统打破了根据有限的足部参数来选鞋的传统,真正实现了基于全三维足型数据的量脚制鞋。     

个性化鞋楦CAD系统的设计与实现

从普通三维扫描仪获得人脚的点云数据及其特征点，并通过造型软件得到人脚的三角网格模型；然后从三角网格模型中抽取出关键的脚形参数，再根据制鞋业的经验公式得到相对应的鞋楦参数；最后输出所定制的个性化鞋楦．实践证明，利用文中系统得到的结果精确可靠，可应用于各种不同需求的鞋楦定制．     

基于客户定制的产品配置

为了给客户提供一个直观和可视化的产品配置工具,研究了基于客户定制的产品配置模型,包括产品族功能模型、产品族装配模型以及产品配置知识的表达模型.利用该模型构建了一种面向客户基于Web的虚拟产品定制和展示环境,使得用户在该环境下可以提交需求目标,系统根据用户的需求进行配置,生成的产品三维实体模型可在浏览器中动态地观察和操作.     

支持大批量定制的产品配置设计系统的研究

针对大批量定制生产的特点，提出基于产品功能结构单元的产品配置模板来完成对客户配置需求的快速响应，给出了产品配置模板的信息模型和配置求解策略．由于机械产品结构的复杂性，引入配置设计知识的混合表达方法以适应不同产品设计类型的要求．最后给出基于产品配置模板信息模型的配置设计系统的实例．     

基于三维技术下健美鞋鞋楦设计

鞋楦是将实际已经完成的鞋套在上面来整理鞋帮形状的一种脚型模。一双精致的健美鞋不仅需要款式、色彩的合理搭配,而且鞋楦的式样能够充分突出鞋子的整体美感。鞋楦是制鞋行业不可或缺的一部分,是制鞋过程中鞋子款式的重要参照物。随着制鞋行业CAD/CAM技术、三维扫描技术的迅速崛起,在鞋楦设计中采用三维数字化处理技术如鞋楦CAD、鞋楦CAM等已成为必然,是国内制鞋业走向国际市场的前提保障。     

基于跖跗围参数的鞋楦曲面重构

针对面向合脚性、舒适性的鞋楦个性化设计中的曲面重构问题,提出并实 现了一种基于鞋楦跖跗围截面变换技术的鞋楦曲面参数化重构方法。通过对鞋楦跖跗截面围 长和高度的控制,将跖、跗围的截面曲线变换到个性化设计所需求效果;基于三次样条插值 函数构造局部、整体两类扩散函数,实现两种将两围截面变换效果扩散到整个鞋楦曲面的方 式。此算法不仅可以准确地满足鞋楦围长约束要求,且保持了曲面光顺性。所提出的重构过 程在Matlab 平台上可以实现可视化交互设计,界面具有操作简单方便的特点。     

基于扩展测地线的鞋楦围长测量

通过扩展测地线的定义,把鞋楦围长测量问题转化为求解鞋楦曲面上带宽度属性的测地线问题.首先以传统测地线为初始曲线在鞋楦曲面上构造具有一定宽度的子曲面,对子曲面进行离散点采样并构造弹簧质点系统;用带曲面约束的弹簧质点系统的运动能量作为子曲面的运动能量,再基于迭代优化的方法最小化子曲面能量,基于测地线思想计算出的鞋楦表面最短路径即为鞋楦围长;此外,对耗时较多的曲面约束计算采用GPU并行加速,进一步缩短了计算时间.实验结果表明,鞋楦围长测量结果达到了行业精度要求.     

红蜻蜓引入Delcam CRISPIN脚型扫描及鞋楦设计工程系统

日前,浙江红蜻蜒鞋业股份有限公司采购了Delcam Crispin脚型扫描及鞋楦设计工程系统,以进行脚型规律研究和鞋靴舒适性设计。     

基于轴变形的脚楦匹配方法*

提出并实现了通过脚楦匹配方法来仿真人脚穿上鞋子的状态,能够直观、便利地检查和分析鞋类产品的舒适度。该方法包括三个步骤：首先,保持鞋楦的位置不动,调整脚型的位置,使其与鞋楦严格对齐;其次,基于轴线变形算法,对脚型进行略微变形,使其与鞋楦姿势匹配;最后,根据匹配结果生成脚楦多个截面的分析图,指导对鞋楦舒适度的分析和楦体修改。实验结果表明,该方法能够有效地检查鞋楦的舒适度,可应用到个性化定制业务。     

Soccer shoe recommendation system based on multitechnology integration for digital transformation

Designing a soccer shoe that fits specific customer’s requirements can improve satisfaction. However, there is no sufficient information to bridge the semantic needs and design characteristics of soccer shoes. Hence, this study is aimed at integrating multiple technologies with semantic customer requirements, shoe-form categories, and appearance designs, and developing a practical Kansei soccer shoe recommendation system. The psychological responses of a customer and perceptions of soccer shoe products are evaluated using Kansei engineering method. Based on a factor analysis, customers’ requirements are classified as aesthetic, functional, and comfortable. A total of 203 soccer shoe images were used to evaluate and categorise the external shoe form into nine design elements using the Kawakida Jirou method, and the weight assigned to each shoe-form category under Kansei semantic adjectives was determined using grey system theory. The quantification theory Type 1 method was used to determine the priority of the design elements. The results indicate that 10 pairs of semantic adjectives used by customers are related to soccer shoe forms. Furthermore, the design priority of each design element of the form category under the three types is reported. A soccer shoe recommendation system that can generate suggested soccer shoe samples for customers is developed by integrating the above-mentioned technologies. A validation experiment was conducted to verify the feasibility of the proposed system. The overall satisfaction of the recommended samples generated via the system is 87.08%, as reported by 80 participants. The findings prove that a new soccer shoe business model can be launched using the proposed system, linking the semantic customer requirements to the soccer shoe-form categories.     

Shoe-last design innovation for better shoe fitting

Shoe-last, a 3D mould used for making footwear, influence the shape, size and fitting of footwear. Current shoe-last design software has focused mainly on reverse engineering of existing shoe-last and modification. Shoe-last designers have generally preferred to design the shoe-last manually due to limitations of design software. In order to solve these problems, a new software based on CATIA platform was developed. The shoe-last model is based on foot shape measurement data and foot biomechanics. Using the existing shoe-last design standards and the sections from existing shoe-lasts, design tables and relationship equations enables the design of shoe-last with different toe type, heel height and custom shoe-last. The design includes comfort and fit aspects as well as design aspect, therefore enables design of aesthetical comfortable shoes. Since the design can be modified instantaneously, the designers could visualize design changes leading to a reduction in shoe-last design cycle.     

Hybrid feature modeling for sport shoe sole design

Feature-based method has been successfully applied in several fields of manufacturing. However, most of the applications use the solid modeling method that cannot meet the requirements of a product design that needs a free-form surface or a complicated surface. A sports shoe is one of the products that need a complex surface to design its sole. In addition, sport shoes are rapidly changed with their styles based on customer and market demands. Thus, the design must be flexible enough to meet those demands particularly when a short lead time design is concerned. Previously, shoe designs have been created by using a commercial standard CAD/CAM system. Surface modeling is normally selected. However, it is time consuming and not competitive. This paper presents a new method of a sport shoe sole design using the hybrid features of surface and solid modeling. Primitive features are prepared in the library, which is written in C of Cimatron API. The user can select and modify before joining them together to create a new shoe sole model. This system has the ability to extend sizes or grading in 3D automatically. The system was tested satisfactorily. Design time is saved 35.388% by average with a single piece design, whereas 88.42% can be saved when 12 sizes grading is performed.     

基于指标结构基因模型的评价驱动型产品设计

针对产品方案设计中用户反馈信息处理、转化问题,提出了交互式产品设计方法,建立了以用户交互式评价为核心的"指标-结构-基因"产品设计模型。该模型应用模糊集与粗糙集理论处理用户评价信息;利用灰色系统理论,应用层次分析法建立评价指标体系,实现由指标体系到产品结构的转换;采用遗传算法,通过产品结构基因编码,根据用户交互式评价,获得产品进化设计方案。以某企业婴儿手推车产品方案设计为例,阐述了应用该方法进行产品方案设计的一般步骤。     

面向MC的客户群体倾向模型

面向大规模定制生产，建立了客户倾向模型，通过关联分析法量化市场调研和客户需求，采用最大树模糊聚类法进行基于属性重要度的客户群体划分和市场细分，获取客户群体消费倾向，为客户需求的工程特征转换、进行产品簇规划提供数学准备和数据支持。     

Derivation of template shoe-lasts for efficient fabrication of custom-ordered shoe-lasts

Custom-tailored products are meant by the products having various sizes and shapes to meet the customer's different tastes or needs. Thus fabrication of custom-tailored products inherently involves inefficiency. Custom-tailoring shoes are not an exception because corresponding shoe-lasts must be custom-ordered. It would be nice if many template shoe-lasts had been cast in advance, the most similar template was identified automatically from the custom-ordered shoe-last, and only the different portions in the template shoe-last could be machined. To enable this idea, the first step is to derive the geometric models of template shoe-lasts to be cast. Template shoe-lasts can be derived by grouping all the various existing shoe-lasts into manageable number of groups and by uniting all the shoe-lasts in each group such that each template shoe-last for each group barely encloses all the shoe-lasts in the group. For grouping similar shoe-lasts into respective groups, similarity between shoe-lasts should be quantized. Similarity comparison starts with the determination of the closest pose between two shapes in consideration. The closest pose is derived by comparing the ray distances while one shape is virtually rotated with respect to the other. Shape similarity value and overall similarity value calculated from ray distances are also used for grouping. A prototype system based on the proposed methodology has been implemented and applied to grouping of the shoe-lasts of various shapes and sizes and deriving template shoe-lasts.     

Mapping Product Design Specification for Mass Customization

Mass customization is an emerging field in manufacturing research community where customer satisfaction is achieved by complying with exact customer requirements at mass production efficiencies. Product varieties have mostly failed in the aspect of satisfying customer requirements, since knowing beforehand exactly what customer needs is beyond the scope of any manufacturing or marketing paradigm. So design to order and build to order is widely talked in the industry to capture heterogeneous market segments. In order to achieve the challenging task of customization at mass production efficiencies, a tight integration of the various entities involved is necessary. Gathering customer requirements, finalizing product design and eventual manufacturing need to be seamlessly integrated to achieve mass production efficiencies. Product designs are classified into customizable product platform families, and then searched based on customer requirements to identify the most conformal design family. Finally the design parameter transport is carried out from customer domain to product domain. Eventually a valid and realizable product specification is generated. The paper will address these issues of classification, selection and ultimately the mapping of parameters. A methodology to classify the product design information, which can easily accommodate design variations based on product platform architecture is proposed. Further, adaptive design customization, which relates most design parameters with the scalable platform design parameters using matrix formulation, is discussed. The proposed design parameter classification and adaptive synthesis of design parameters is applied to a spring design example.     

A Web-enabled product definition and customization system for product conceptualization

Abstract: Owing to rapidly changing customer needs and much shorter product life cycles, for developing a successful product it is imperative to employ more efficient and flexible approaches for product conceptualization. To meet this demand, a Web-enabled product definition and customization system (PDCS) is proposed, from a design-knowledge-handling viewpoint, in this paper. It comprises two phases, namely product definition based on the laddering technique and a novel design knowledge hierarchy, and product customization based on an integrated methodology of conjoint analysis and Kohonen association techniques. Basically, this system is a method of conducting design decision-making via customer involvement, i.e. a strategy for transforming customer preference into a specific product concept. A case study on wood golf club design is used to illustrate and validate the proposed Web-enabled PDCS.     

基于深度神经网络的电子商务智能客服系统设计与实现

近年来,随着自然语言处理技术的飞速发展,传统的客服越来越不能满足当前的业务需求,基于自然语言技术的智能客服系统应运而生并被广泛应用在学习、生活、工作等各个领域中。本系统使用HTML和JavaScript进行前端页面的实现,采用Django进行后端的搭建,并使用MySQL进行数据的管理;使用ESIM模型进行语义匹配,该模型综合应用了BiLSTM和注意力机制,将不同句子的各单词特征相关性进行表示,再进行差积分析,凸显了局部推理信息,最终实现了具有回答用户问题、天气查询、推荐商品等功能的智能客服系统。     

Item-level RFID for enhancement of customer shopping experience in apparel retail

In the customer-oriented apparel retail industry, providing satisfactory shopping experience for customers is a vital differentiator. However, traditional stores generally cannot fully satisfy customer needs because of difficulties in locating target products, out-of-stocks, a lack of professional assistance for product selection, and long waiting for payments. Therefore, this paper proposes an item-level RFID-enabled retail store management system for relatively high-end apparel products to provide customers with more leisure, interaction for product information, and automatic apparel collocation to promote sales during shopping. In this system, RFID hardware devices are installed to capture customer shopping behaviour and preferences, which would be especially useful for business decision-making and proactive individual marketing to enhance retail business. Intelligent fuzzy screening algorithms are then developed to promote apparel collocation based on the customer preferences, the design features of products, and the sales history accumulated in the database. It is expected that the proposed system, when fully implemented, can help promote retail business by enriching customers with intelligent and personalized services, and thus enhance the overall shopping experience.