An approach to capturing and reusing tacit design knowledge using relational learning for knowledge graphs

Tacit design knowledge plays an important role in the process of product design and is a valuable knowledge asset for enterprises. In terms of the characteristics of tacit rational design knowledge, this paper puts forward a scientific hypothesis and approach on capturing and reusing tacit rational design knowledge. The presented approach represents the observable design result facts of products using design knowledge graphs. A design issue-solving oriented knowledge graph model is presented, where directed relation edges represent design issues, and nodes stand for design solutions. When a new design solutions requirement needs to be searched, tacit design knowledge can be reused by relational learning for the constructed design knowledge graphs. In relational learning, the design knowledge graph is converted into a three-order tensor, where two modes are solution nodes, and the third mode holds the issue relations. Then, a tensor factorization approach is employed to calculate the latent features between design solutions for an issue relation. As a result, a score vector to represent the existence of issue-solution relations can be obtained. By sorting the scores in descending order, we may select the solution node with the highest score as the design solution to be searched. Finally, a stamping die design case study is provided. The case study shows that the proposed approach is feasible, and effective, and has better flexibility, scalability and efficiency than CBR methods.     

Fostering continuous innovation in design with an integrated knowledge management approach

In the global competition, companies are propelled by an immense pressure to innovate. The trend to produce more new knowledge-intensive products or services and the rapid progress of information technologies arouse huge interest on knowledge management for innovation. However the strategy of knowledge management is not widely adopted for innovation in industries due to a lack of an effective approach of their integration. This study aims to help the designers to innovate more efficiently based on an integrated approach of knowledge management. Based on this integrated approach, a prototype of distributed knowledge management system for innovation is developed. An industrial application is presented and its initial results indicate the applicability of the approach and the prototype in practice.     

Semantic Web based innovative design knowledge modeling for collaborative design

This paper describes a study about how to use the Semantic Web technologies for innovative design knowledge modeling in a multi-agent distributed design environment. Semantic Web based knowledge modeling for innovative design is proposed as prelude to the meaningful agent communication and knowledge reuse for collaborative work among multidisciplinary organizations. A model for innovative design is proposed at first, based on which a knowledge schema is brought forward. For sharing the design knowledge among an internet-based or distributed work team, even globally, A RDF-based knowledge model is presented to realize its representation on Semantic Web. A Semantic Web based repository for innovative design and its API for topper Semantic Web applications have been also constructed. The proposed knowledge modeling extends traditional product modeling with capabilities of innovative design, knowledge sharing and distributed problem solving, and is employed as a content language within the messages in the proposed multi-agent system architecture. The proposed approach is viewed as a promising knowledge management method that facilitates the implementation of computer supported cooperative work in innovative design of Semantic Web applications.     

Utilizing knowledge context in virtual collaborative work

The understanding of knowledge can be impaired if it is isolated from the proper context. Despite the importance of contextual information, there has been limited support for utilizing context in current knowledge management and collaborative systems. This paper presents a knowledge context model, called KC-V, which facilitates the use of contextual information in virtual collaborative work. Four benefits of using KC-V are suggested: evolutionary accumulation of knowledge aligned with collaborative activities, supporting the virtual team lifecycle, improved understanding by rich navigation paths, and searching for knowledge with similar context. A web-based collaboration system called VWSS is developed using KC-V.     

A design methodology for form-based knowledge reuse and representation

Paper forms are regularly used for collecting and disseminating knowledge in offices; they are a natural way of eliciting requirements of knowledge workers. Many organizations have implemented a groupware system to integrate the organizational knowledge and support knowledge creation. However, design methods for flexible form-based knowledge reuse and representation are limited. We developed a methodology based on the enhanced cognitive fit theory; it utilizes factoring and synthesis principles to manipulate form-based knowledge. The methodology was articulated using the design science research methodology. A prototype embedded methodology was built to support a knowledge worker in knowledge creation and reuse in a high tech firm. The resulting system allowed flexible form-based knowledge creation that was useful for problem solving and exploiting opportunities. Implications and conclusions are discussed.     

A part affordance-based approach for capturing detailed design knowledge

Design knowledge reuse is widely accepted as an effective strategy for designers to develop robust artifacts with less time and lower cost. However, there has been very little research on how to help designers capture detailed design knowledge for reuse. As a result, most detailed design knowledge still has to remain in designers’ memories as tacit knowledge, which can easily get lost due to oblivion or the mobility of designers. Therefore, this paper attempts to develop a part affordance-based approach for externalizing and capturing detailed design knowledge for effective reuse. It first introduces a part model for representing the detailed design-related information. Based on the relational theory for design, the concept, part affordance, is then employed to help designers externalize and capture various lifecycle factors that are implicit in a detailed design. Based on the affordance constraint axiom, a systematic approach is then proposed for deriving tacit design knowledge from captured part affordances through the analysis of extreme working situations. The proposed approach has been implemented as the Design Knowledge-Capturing System (DKCS). A fixture design case has been employed to illustrate the proposed approach.     

Research on an active knowledge push service based on collaborative intent capture

The quality of a knowledge service influences the quality, efficiency and innovation of product conceptual design. Existing approaches lack intelligence and individuation when providing a knowledge retrieval service via rules and cases. In this paper, we propose a framework of an active knowledge service based on collaborative intent capture to assist product conceptual design. First, a collaborative intent capture model is constructed through the study of the expression and capture of collaborative intent; second, a framework and a process of active knowledge push based on collaborative intent capture are designed after analyzing the method of knowledge resources acquisition based on the constraint satisfaction theory. Finally, match algorithms for text content are studied. Based on the above research achievements, a prototype system of a collaborative design and active knowledge service platform (C-AKSP) has been developed for providing a knowledge service and assisting product conceptual design. An example, the conceptual design of a machine tool spindle system, is used to validate the proposed theories for the model, the framework and the algorithm. As a result, C-AKSP can provide a superior knowledge service that meets the designer's knowledge needs.     

A hypernetwork-based approach to collaborative retrieval and reasoning of engineering design knowledge

Complex product development increasingly entails creation and sharing of design knowledge in a collaborative and integrated working environment. In this context, it has become a central issue to address the multifaceted feature of design knowledge for such a collaborative knowledge sharing scheme. This paper proposes a hypernetwork-based approach to explicitly capturing the relationships between various elements in a multifaceted knowledge representation. Specifically, a knowledge hypernetwork model is constructed, which is composed of a designer network, a product network, an issue network and a knowledge unit network. The relationships between various nodes from different networks are identified and defined according to specific node properties. In addition, topological characteristics of the hypernetwork structure are analyzed together with the statistical indicators. Based on this model, the Bayesian approach is adopted to conduct the collaborative reasoning process whereby knowledge elements relevant to the current design task are recommended according to the issues to be resolved and the current design context. A case study conducted in this work shows that the proposed approach is effective in capturing the complex relationships between multi-faceted knowledge elements and enables collaborative retrieval and reasoning of knowledge records.     

Causal design knowledge: Alternative representation method for product development knowledge management

This paper presents a mathematical comparison of procedural knowledge and causal knowledge, and discusses the potential roles and feasibility of causal knowledge across product development knowledge management. Since reuse of knowledge is so important in product development, various knowledge management approaches have been introduced. Most of the product design knowledge is represented by procedural knowledge, which unfortunately requires cumbersome processes to define, and is typically inadequate for representing the kind of knowledge generated during the product development process. A causal knowledge representation, however, can help us to overcome this limitation and is an alternative formalism for representing product design knowledge. In this paper we compare the procedural and causal knowledge representations. We present the mathematical definitions of two knowledge paradigms, then mathematically describe the relationship between the two. Both knowledge paradigms are then compared based on the perspective of knowledge expression, decision alternative representation, reasoning capability, and knowledge cultivation. This paper concludes that causal knowledge representation is superior to procedural knowledge representation based on the four perspectives. Finally, the knowledge systems are modeled using Systems Modeling Language (SysML), and we present a case study that demonstrates the causal knowledge features using a realistic example from industry.     

A user requirement driven framework for collaborative design knowledge management

In today’s competitive global marketplace and knowledge-based economy, user requirement becomes an important input information for enterprises to develop new product and a critical factor to drive product collaborative design evolution. Meanwhile, there remains no consensus on how best to support knowledge activities and significant challenges to establishing design information management facing to rapid collaborative product development with dynamic user requirement. This paper introduces solutions for designer to deal with dynamic user requirement information through requirement evaluation and prediction method. In this study, we propose a user requirements-oriented knowledge management concept that is based on a four level hierarchy map model with special regard to knowledge collaboration and information communication. Furthermore, a novel distributed concurrent and interactive user requirement database was constructed, and the framework driven by user requirement was put forward to support collaborative design knowledge management. Finally, the service robot design project of a start-up company is used as a case study to explain the implementation of proposed framework.     

A model for capturing and representing the engineering design process

This paper presents a Collaborative Model for capturing and representing the engineering Design process (CoMoDe). CoMoDe is a deductive object-oriented model that, in relation to an engineering design process, is able to capture the different elements that participate in a design process in an integrated fashion. In particular, it is able to represent (i) the activities, operations, and actors that have generated each design product, (ii) the imposed requirements, and (iii) the rationale behind each decision. Furthermore, it also offers an explicit mechanism to represent and trace the different model versions that have participated in the design process. On such a basis, this proposal introduces specific procedures to handle various situations appearing in cooperative environments. They are: (i) different design teams perform independent concurrent activities on “a priori” independent parts of the artefact being designed and afterwards their results need to be made consistent; (ii) distinct teams concurrently work on slightly coupled parts of the artefact being designed and conflict handling must be addressed along their “parallel” course of actions.     

The push strategy of product design knowledge in cloud environment with the multidimensional hierarchical context and SSA-BPNN model

To assist designers in completing design tasks and improve the efficiency of product design, more and more design knowledge push approaches are coming about. With developments of information technology and cloud computing, knowledge service goes with the whole design process and it is represented by the knowledge push forming. The knowledge push is complex engineering, however, existing knowledge push approaches in traditional design patterns cannot exactly meet the personalized knowledge requirements of designers in cloud environment. To address this issue, we attempt to explore the push strategy of product design knowledge in cloud environment. Firstly, knowledge demands are analyzed with the multidimensional hierarchical context model and the design knowledge modeling is represented following characteristics of the cloud-based design pattern. Then, the knowledge push architecture contains the matching of knowledge to obtain alternative knowledge and the knowledge importance degree prediction with SSA-BPNN model to overcome the inaccuracy of judgments, which is put forward. Moreover, the push coefficient is calculated as the knowledge push reference. Eventually, an illustrative case of intelligent air conditioner product design in the cloud platform is taken to verify the application and performance of the proposed approach. We expect that this work could provide useful insights into the product design knowledge push in cloud environment.     

Design gene based secure mechanism for collaborative product development

In collaborative product development, a CAD model needs to be effectively shared among partners to facilitate co-design. In the meantime, it is essential to preserve the intellectual property information (design knowledge) of the shared CAD. To resolve the above dilemma, this paper presents a novel approach to share CAD models to support collaboration, as well as conserving confidential design knowledge in the models. The motivation of the approach is to develop collaborative mechanisms pertaining to an innovative concept of design genes, which imitate biological genes that are responsible for the heritable characteristics of an organism during evolving. The approach consists of the following steps. Firstly, design genes are defined to represent the design knowledge in CAD models. Secondly, a filter is introduced to retrieve design genes from the CAD model flexibly. An encryption algorithm is then designed to encrypt the design genes, and ensure the geometrical validity of the model to support effective collaboration. Finally, case studies are used to validate the developed approach. The complexity of the case studies can demonstrate that the approach is applicable to real-world application scenarios.     

A knowledge system for integrated product design

This paper discusses the architecture and implementation issues for a knowledge system to assist in product design. The goals of the concurrent Design Advisor (CODA) are to enhance the quality of designs by 25 percent and the efficiency by a factor of 10. The improvement springs from the integration of diverse knowledge bases, ranging from customer needs to product evaluation, and from process configuration to production control. One source of efficiency is the automation of many routine tasks, thereby increasing user productivity. Another source is the increase in the quality of initial designs, which obviates the need for numerous iterations in the design process due to poor manufacturability. CODA is based on the general architecture of the Creativity Support System, an expert system for assisting users in specific domains requiring creative solutions. The bilevel structure of the system consists of a domain-independent module containing general tools and techniques for creative problem-solving, and a domain-dependent module incorporating knowledge specific to particular fields of application. The utility of this approach is illustrated in the realm of concurrent product design by demonstrating a CODA within the general architecture of the system.     

Multi-agent collaborative 3D design with geometric model at different levels of detail

This paper presents a scheme for collaborative 3D design using product model at various levels of detail (LODs). Design features are selectively hidden at each level from certain participants, depending on their actual needs and individual accessibility in the collaboration. A tree data structure represents the feature hierarchy of CAD construction, the link between feature and LOD, and 2D mesh data for display control of each feature. An XML/XSLT-based approach is proposed to enable real-time visualization of different LOD models in distributed environment. A collaborative design system is implemented using multi-agent technologies, which focuses on function design of each agent, interactions among agents, the client–server structure, and generation of the LOD data using the XML/XSLT approach. A scenario of synchronous 3D mold assembly demonstrates that geometric categorization of product model provides an operational mechanism for assuring security of information sharing in engineering collaborations over the Internet. It also validates the effectiveness of the agent technologies for automating complex engineering activities.     

Developing a distributed knowledge model for knowledge management in collaborative development and implementation of an enterprise system

Recently, enterprise systems have been extensively adopted to boost enterprise competitiveness. The development and implementation of enterprise systems is a knowledge intensive procedure, being related to enterprise processes and involving information, system and software engineering technologies. Consequently, knowledge management is required to enhance the effectiveness of enterprise system development and implementation, thus helping to increase industrial competitiveness.This study aims to develop a distributed knowledge model for knowledge management, capable of supporting the collaborative development and implementation of enterprise systems. This objective can be obtained by performing the following tasks: (1) modeling and characterization of the collaborative development and implementation process, (2) identification, analysis and modeling of involved knowledge, and (3) development of a distributed knowledge model for knowledge management related to the collaborative development and implementation of enterprise systems.     

A distributed and interactive system to integrated design and simulation for collaborative product development

The goal of applying collaborative product development in industry has raised the need to develop software tools supporting system integration and group collaboration. Current methods and tools mainly focus on the collaborative creation of design components and assemblies. However, few of them support the collaborative work in developing simulation models so that proposed design concepts and solutions can be evaluated by integrating expertise from several disciplines. The purpose of this research is to develop a distributed and interactive system on which designers and experts can work together to create, integrate and run simulations for engineering design. To develop such a system, a number of issues, e.g. effectiveness and efficiency of modeling work, the re-use of models, interaction and cooperation, accuracy of simulation, collaborative operation on models, etc., need to be addressed. This paper describes an open architecture to developing simulations for engineering design in a distributed and collaborative environment, identifies a set of key issues raised in this architecture, and presents the techniques employed in our solution.     

A concurrent engineering-oriented design database representation model

A concurrent engineering-oriented design database representation model (CE-DDRM) is introduced in this research for supporting various life-cycle aspects in concurrent design. In this model, concepts and behaviors of different design database modeling components, including entities, properties, relationships, tasks, and specifications, are defined at meta-class level. Design database is modeled at two different levels, class level and instance level, representing generic design libraries and special design cases, respectively. A Web-based system architecture is proposed to model distributed design database and allow team-members for different product development life-cycle aspects at different locations to access the design database. This newly introduced approach provides the foundation for developing the next generation CAD systems with concurrent engineering functions.     

面向对象的专家知识模型

文中用面向对象方法来分析、设计基于规则的专家系统,提出一种新的采用分层递阶结构的专家知识模型,并从结构和功能角度进行详细阐述。