Combining Deep Learning with Knowledge Graph for Design Knowledge Acquisition in Conceptual Product Design

The acquisition of valuable design knowledge from massive fragmentary data is challenging for designers in conceptual product design.This study proposes a novel method for acquiring design knowledge by combining deep learning with knowledge graph.Specifically,the design knowledge acquisition method utilises the knowledge extraction model to extract design-related entities and relations from fragmentary data,and further constructs the knowledge graph to support design knowledge acquisition for conceptual product design.Moreover,the knowledge extraction model introduces ALBERT to solve memory limitation and communication overhead in the entity extraction module,and uses multi-granularity information to overcome segmentation errors and polysemy ambiguity in the relation extraction module.Experimental comparison verified the effectiveness and accuracy of the proposed knowledge extraction model.The case study demonstrated the feasibility of the knowledge graph construction with real fragmentary porcelain data and showed the capability to provide designers with interconnected and visualised design knowledge.

A Design Method with Knowledge Modeling for Complex Product Based on Ontology

Innovation design for complex products is a difficult issue in the military manufacturing industry. Ontology may provide a feasible way to rebuild the design process for complex products via sharing and reusing of design knowledge. In this paper, a design method used in the innovation design process of the complex products with knowledge modeling is proposed. Knowledge modeling is realized through ontology construction by combining the cycling evolutional theory of constructing ontology and OWL (Ontology Web Language)-based knowledge representation. As a case study, the satellite is selected as one of the complex products. The application domain of the satellite ontology is analyzed. According to the analysis result, the knowledge structure of satellite ontology is put forward based on OWL. The application of satellite product design shows that the method can effectively organize and reuse the knowledge resources in the innovation design of complex product and help companies to create more competitive products based on the existing knowledge and experience.

Knowledge-reuse-oriented Product Modeling and Knowledge Management in Digital Design

Mostly product design knowledge and experience exists in design handbook or expert’s brain. During design process,designer has to refer to many handbooks and design materials,and design solution is hard to be reused. In order to deal with these deficiencies in digital design,this paper focuses on knowledge-reuse-oriented product modeling and knowledge management. Design knowledge is used to guide design process,and it is embedded into product model along with design process. Through analyzing design process,mechanical product knowledge is classified into four basic types that include calculation formula,design rule,engineering check and parameter spectrum etc. In order to manage and encapsulate design knowledge the concept of knowledge component(KCOM) is proposed. Design knowledge base can be organized as a hierarchy tree of KCOM. Knowledge reuse in KCOM level is the reuse of whole object in knowledge base,and knowledge reuse in item level is the reuse of basic knowledge type. Finally knowledge reuse approaches between knowledge base and CAD system is presented.

Constructing the Ontology for Modeling the Fish Production in Pearl River Basin

This paper puts forward a construction method based on ontology for the Pearl River Basin fish production, to facilitate the domain knowledge analysis and information retrieval. By converting the concepts and terms in domain ordinally, the fish production ontology was constructed with the definition of classes, properties, instances, and relationships. The developed ontology model of the fish production knowledge is proposed and applied in the system of fish diseases diagnosis primarily. The research lays the semantic foundation for the further efficient knowledge management and practical application.

Uncertain Multidisciplinary Design Optimization on Next Generation Subsea Production System by Using Surrogate Model and Interval Method

The innovative Next Generation Subsea Production System(NextGen SPS)concept is a newly proposed petroleum development solution in ultra-deep water areas.The definition of NextGen SPS involves several disciplines,which makes the design process difficult.In this paper,the definition of NextGen SPS is modeled as an uncertain multidisciplinary design optimization(MDO)problem.The deterministic optimization model is formulated,and three concerning disciplines—cost calculation,hydrodynamic analysis and global performance analysis are presented.Surrogate model technique is applied in the latter two disciplines.Collaborative optimization(CO)architecture is utilized to organize the concerning disciplines.A deterministic CO framework with two disciplinelevel optimizations is proposed firstly.Then the uncertainties of design parameters and surrogate models are incorporated by using interval method,and uncertain CO frameworks with triple loop and double loop optimization structure are established respectively.The optimization results illustrate that,although the deterministic MDO result achieves higher reduction in objective function than the uncertain MDO result,the latter is more reliable than the former.

Intelligent Multilevel Knowledge Acquisition System for Product Design and Its Implementation

The characteristics of design process, design object and domain knowledge of complex product are analyzed. A kind of knowledge representation schema based on integrated generalized rule is stated. An AND-OR tree based model of concept for domain knowledge is set up. The strategy of multilevel domain knowledge acquisition based on the model is presented. The intelligent multilevel knowledge acquisition system (IMKAS) for product design is developed, and it is applied in the intelligent decision support system of concept design of complex product.

Product-design knowledge retrieval based on ontology

In order to improve the utilization ratio of knowledge retrieval, a product-design knowledge retrieval approach based on ontology is proposed. A representation model of product-design knowledge is proposed according to its characteristics. Domain ontology of product-design is estab- lished and the semantic annotation technology is used to connect the design knowledge and ontolo- gy. A new semantic annotation format is developed and semantic information of the design knowl- edge is enriched by making use of ontology. On that basis a retrieval algorithm is designed for semantic retrieval. Finally, this approach is used in a knowledge management system for military-vehi- cle design and its effectiveness and feasibility are validated. Results show that the recall ratio and the precision ratio of knowledge retrieval are improved greatly and users＇ requirements in semantic retrieval are satisfied.

Research and Design of Parallel Knowledge Base Machine- PKBM95

ＲｅｓｅａｒｃｈａｎｄＤｅｓｉｇｎｏｆＰａｒａｌｌｅｌＫｎｏｗｌｅｄｇｅＢａｓｅＭａｃｈｉｎｅ－ＰＫＢＭ９５￥ＧＵＯＦｕｓｈｕｎ；ＬＩＡＯＭｉｎｇｈｏｎｇ；ＳＯＮＧＺｈｅｎ；ＷＵＺｈｉｇａｎｇ（郭福顺，廖明宏，宋震，吴志刚）（Ｄｅｐｔ．ｏｆＣｏｍｐｕ...

Application of Solid Thinking Evolve in Product Modeling Design

In view of application characteristics of Solid Thinking Evolve in product modeling design, and the practical design of cosmetics packaging, this paper introduced the unique Construction TreeTM, fast, convenient and easy features of Solid Thinking Evolve, and its application prospects in product development.

A Solution to Knowledge Management in Networked Collaborative Design

Concerning the demands in networked collaborative innovative design, a knowledge-based collaborative design model is introduced the model of knowledge integration along with its relevant supporting techniques are presented. After illustrating the general knowledge search paradigm, a kind of dynamic user model is proposed to improve knowledge search efficiency. At last a short introduction of the system’s implementation is described.

Knowledge acquisition method for case-knowledge-based product family design

Knowledge acquisition has always been the bottleneck of artificial intelligence. It is the critical point in product family design. Here a knowledge acquisition method was introduced based on scenario model and repository grid and attribute ordering table technology. This method acquired knowledge through providing product design cases to expert, and recording the means and knowledge used by the expert to describe and resolve problems. It used object to express design entity, used scenario to describe the design process, used Event-Condition-Action(ECA) rule to drive design process, and with the help of repository grid and attribute ordering table technology to acquire design knowledge. It’s a good way to capture explicit and implicit knowledge. And its validity is proved with respective examples.

Optimization of integrated geological-engineering design of volume fracturing with fan-shaped well pattern

According to the variable toe-to-heel well spacing, combined with the dislocation theory, discrete lattice method, and finite-element-method(FEM) based fluid-solid coupling, an integrated geological-engineering method of volume fracturing for fan-shaped well pattern is proposed considering the geomechanical modeling, induced stress calculation, hydraulic fracturing simulation, and post-frac productivity evaluation. Besides, we propose the differential fracturing design for the conventional productivity-area and the potential production area for fan-shaped horizontal wells. After the fracturing of the conventional production area for H1 fan-shaped well platform, the research shows that the maximum reduction of the horizontal principal stress difference in the potential productivity-area is 0.2 MPa, which cannot cause the stress reversal, but this reduction is still conducive to the lateral propagation of hydraulic fractures. According to the optimized fracturing design, in zone-Ⅰ of the potential production area, only Well 2 is fractured, with a cluster spacing of 30 m and an injection rate of 12 m^(3)/min per stage;in zone-Ⅱ, Well 2 is fractured before Well 3, with a cluster spacing of 30 m and an injection rate of 12 m^(3)/min per stage. The swept area of the pore pressure drop in the potential production area is small, showing that the reservoir is not well developed. The hydraulic fracturing in the toe area can be improved by, for example, properly densifying the fractures and adjusting the fracture distribution, in order to enhance the swept volume and increase the reservoir utilization.

大数据牵引背景下的服装设计开发模式

在大数据牵引背景下,随着数据量呈爆炸式增长和大数据应用的不断深化,大数据资源以数据要素的形式牵引着传统服装设计模式的改变。通过对服装设计相关的大数据进行分类甄别,探讨大数据在多方面赋能服装设计协同价值创造,多维度比较传统服装设计开发与以大数据牵引的服装设计开发模式,以大数据赋能服装精准设计,构建基于大数据引导下的服装设计框架;将该框架应用于MZ品牌的开发案例中,从商品企划、设计开发和预售下单3个方面论述大数据在服装设计开发中的实践应用。大数据时代设计模式的演变将更加聚焦于设计师与海量数据之间的相互作用,应用大数据牵引服装设计开发模式的迭代,可实现更高精准度和更快反应能力的服装设计开发。

参与式设计影响要素探析

针对参与式设计概念模糊以及用户参与性较弱现状,明确参与式设计要素,梳理用户参与目的、参与方法和工具。围绕参与式设计协作要素:参与者知识和参与工具,具体阐述参与对象和参与模式。并将参与式设计中的工具、技术和方法从参与形式角度分成制作、讲述和表演3类,探讨具体应用时目的与方式。参与式设计是一种设计理念,在设计过程中应用各种工具和方法获取用户的需求以及创新想法。通过分析参与要素与方法特点,设计实现非专家用户参与设计过程的工具,将对参与式设计在用户研究领域的应用具有重要意义。

感性工学视域下外卖配送电动车造型设计

目的提出符合用户感性需求特征的外卖配送电动车造型设计方案。方法基于感性工学理论,将感性需求转化成定性分析与定量分析,采用SDM(语意差异法)方法制作调查问卷,收集并筛选描述外卖配送电动车造型的感性意象词汇与样本图片,并结合主成分分析法,提取影响造型设计的主要因子和外卖电动车造型元素,构建感性意象数学模型;通过多元线性回归法,借助SPSS统计软件对四个主要造型构成要素与感性意象进行量化处理。结果对外卖配送电动车的前面板、前大灯、车身架和座垫的造型元素展开分析,设计出与用户“时尚”和“速度”情感需求最匹配的梯形前面板、变异多边形前大灯、多边形车身架和细长型座垫造型元素。结论感性工学不仅能有效挖掘用户需求,而且还能直观表达出感性感受与数值的对应关系,对外卖配送电动车造型要素进行有目的的设计和调整。

浅谈数字化设计对产品包装的影响——以三维可视化立体模型为例

随着科技的不断发展,三维可视化技术已被应用于多个领域。三维可视化技术是一种将三维模型转化为二维图像的技术,可以将复杂的产品结构、工艺流程、装配方式等信息以三维的形式呈现出来,让人们更加直观地了解产品。对产品包装设计的数码设计来说,三维可视化技术已经逐渐成为产品包装设计和营销中不可或缺的一部分。利用三维可视化技术,可以更直观地展现产品的外包装、功能、性能等信息,从而吸引更多的消费者,提高产品销量。本文以三维可视化的立体模型为例,主要阐述了产品包装设计的数码设计效果。

基于Kano模型的中国非遗文创设计需求研究

目的 近年来,我国非物质文化遗产日益受到重视,探索中国非物质文化遗产的活态遗产传承路径和方法成为重要的研究领域。然而,目前设计师用于需求研究的工具和方法受到主观性的显著影响,因此使用定量方法来探索用户需求。方法 通过KJ法对初步访谈要素数据进行定性分析,并确定最终的一级和二级需求,使用Kano模型对分散的用户需求进行需求类型的运算和归纳。结论 形成非遗当代化的用户需求模型,并对其中各项进行了解释说明,通过需求模型的构建揭示了当代非遗文创的用户需求项和关系脉络,为非遗文创转化的设计实践过程提供一定的指导作用和借鉴价值。

基于图文多模态融合推理的产品创新方案设计方法研究

目的针对当前产品创新设计领域中对基于图像-文本多模态知识支撑创新设计方法研究不足的问题,提出了一套基于图文多模态的产品创新方案设计方法。方法首先,对设计师的设计草图与文本要求进行预处理,然后引入产品设计知识图谱来促进设计思维的发散和创新;其次,通过微调的生成式预训练变换器模型和扩散模型生成产品方案及其概念图;最后,利用深度多模态设计评估模型对产品设计方案的可行性和市场潜力进行评估。结果通过产品设计知识图谱,及深度多模态设计评估模型的引入,该设计流程可以生成富有创新性且具备可行性的产品方案。结论基于图文多模态的产品创新方案设计流程结合了最新的深度学习技术,不仅提高了设计的效率,还为设计师提供了更广阔的创新视角和灵感来源。

光热驱动的膜分离生物甲烷制氢过程建模与仿真分析

光热驱动的甲烷重整制氢技术,是将太阳能转化为燃料的主要技术路径之一。引入聚光集热技术,可实现太阳能的全光谱利用,有效提高太阳能到燃料化学能的转化效率,同时显著降低系统能耗及碳排放。将多孔碳化硅吸热体和La_(1-x)Sr_(x)Co_(1-y)Fe_(y)O_(3-δ)钙钛矿透氧膜结合,提出一种光热驱动的膜反应制氢的设计思路,实现了连续、高效的制氢过程。完成了该反应过程的概念设计,建立考虑辐射-传热-膜分离-反应的数值模型并进行仿真模拟;重点评估了膜表面的温度均匀性,并分析温度对膜内反应及出口产物的影响规律。结果表明,该模型可以有效精准描述概念设计过程。研究成果可为光热驱动的高温膜反应器设计和放大提供理论依据以及初步设计方法。

不同人格特质消费者的产品造型意象认知差异研究

获取不同人格特质消费者产品造型意象感性认知与差异。以人格特质中的“大五”人格理论为基础,以家用小型宠物喂食器为例,采用语义差异法与问卷法获取消费者的造型意象认知信息,分析各群体的认知差异。研究发现在“普通与新颖”“实用与花哨”“简约与复杂”“协调与奇异”4个造型意象维度上,外倾性、神经质、开放性消费者群体的认知与其他群体的认知表现出了不同的差异性,这种差异与消费者认知经验、造型意象内涵相关。该分析结果为产品造型意象构建与设计创新提供了支撑。