网络化制造系统中协同决策体系研究

网络化制造系统的协调运营是建立在各个节点企业之间高质量的信息传递与共享基础上,有效的网络化制造系统离不开信息系统提供可靠的决策支持。分析了网络化制造系统中的决策问题及其活动特点,给出了网络化制造系统中决策信息的层次概念模型。结合网络化制造系统中决策问题的特点,给出了用于网络化制造过程的决策支持系统结构模型,建立了一种基于多Agent系统(MAS)与数据仓库技术相结合的网络化制造决策支持系统(NMS-DSS)的体系框架。     

Development of a Knowledge-Based Process Planning System for an Auto Panel

Challenges and pressures from the growing globalisation of markets have made automotive enterprises shorten the product development cycle time and reduce costs through the increasing use of mathematics-based tools and processes. In order to bridge the gap between experience-based design and science-based engineering, this paper establishes a knowledge-based process planning system to fully support auto panel die development and design automation. The framework of this novel system is proposed, and key issues, such as knowledge acquisition, knowledge representation and knowledge-based design are described in detail. The function model of the system is proposed to illustrate the architecture and functionality of the system. The system provides users with just-in-time access to the appropriate knowledge and information to reduce the search burden. A practical example is used to show the great advantage of the knowledge-based process planning system.     

面向多级用户支持的决策模型层次描述框架

为支持参与决策问题求解和决策支持系统构造过程的不同层次用户,提出了一种决策模型层次描述框架.该框架由基础模型层、构件模型层和概念模型层组成.基础模型层从模型数据、方法和知识3个方面描述了基本的决策模型,用于支持模型构造者;构件模型层封装了基础模型的细节部分,通过接口向外界提供模型的基本信息,增强了模型的重用性,用于支持决策支持系统构造者;概念模型层通过给出决策问题的形式化表示,建立了决策问题与模型构件的联系,用于支持决策者或决策分析人员.通过实例,验证了本文提出的描述框架的科学性与可行性.     

Research of knowledge-based hammer forging design support system

Die design is experience-extensive in the field of plasticity engineering, in which knowledge and experience play a very important role in supporting the design process. In order to make good use of the accumulated engineering knowledge, the methodology of knowledge-based hammer forging design support is elaborated in detail, including: engineering knowledge representation, knowledge acquisition and knowledge-based design support techniques. Based on these, a knowledge-based hammer forging design support system is developed using the API of SolidWorks. This prototype system is a design guide system, which provides the right knowledge to support the designer, make decision/selection and design the die step by step. This way, the computerized public and private knowledge can be greatly shared and reused, which improves the design efficiency, and avoids previous mistakes effectively. Finally, a case study is shown to elaborate how the system is operated.     

An Intelligent Knowledge-Based System for Product Cost Modelling

An intelligent knowledge-based system for product cost modellingis presented in this paper. The developed system has the capability of selecting a material, as well as machining processes and parameters based on a set of design and production parameters; and of estimating the product cost throughout the entire product development cycle including assembly cost. The proposed system is applied without the need for detailed design information, so that it can be used at an early design stage, and, consequently, redesign cost and longer lead time can be avoided. Hybrid knowledge representation techniques, such as production rules, frame and object oriented are employed to represent manufacturing knowledge. Fuzzy logic-based knowledge representation is applied to deal with uncertainty in the knowledge of cost model to generate reliable cost estimation. This paper deals with cost modelling of both a machining component and an injection moulding component, which is a process that gives high production rates, excellent quality and accuracy of products, and low manufacturing cost. Based on the analysis of the moulded product life cycle, a computer-based cost model was developed which integrated the relationship between cost factors, product development activities, and product geometry. The estimated cost included the costs of material, mould and processing. The system has been validated through a case study.     

面向产品的CAPP方法论及其智能化概念体系

提出并论述面向产品的ＣＡＰＰ方法论,建立面向产品的ＣＡＰＰ智能化概念体系,并分析讨论面向产品的ＣＡＰＰ智能化关键技术,实践表明,以面向产品的ＣＡＰＰ方法论为指导,形成基于知识库的智能化交互式ＣＡＰＰ系统框架,才能真正理顺先进性与实用性、普及与提高等各方面的关系,满足企业对ＣＡＰ广泛应用与集成的需求。     

支持企业群体决策的一种数据仓库模型

群体决策支持系统是计算机支持的协同工作的重要组成部分,数据仓库提供了对OLAP和决策支持系统的支持.但现今的以数据仓库为基础的决策支持系统大都不能很好地支持决策者之间的协同决策.为更好地支持企业群体决策,给出了一种支持企业群体决策数据仓库的模型(SEGDDWM).该模型以分析企业的不同生产活动为目标,既可以为决策者们的协同决策提供辅助帮助,又可以为决策者们提供面向某个主题的决策服务.由于该模型引入了组合维的概念,不仅大大加快了决策信息查询的速度,而且扩展了单一数据仓库的能力,为决策者们提供统一的协同决策支持平台,也给出了一个零售企业的群组决策过程.     

面向复杂问题求解的综合集成型决策支持系统

为求解现有的常规决策方法与系统工程方法难以处理的复杂决策问题,提出了一种综合集成型决策支持系统。分析了当前各种决策支持系统的特点和存在的问题,运用并根据复杂决策问题求解的综合集成过程提出了对系统的需求,进而建立了满足需要的基于浏览器／服务器模式的系统体系结构,讨论了其组成和功能,并对系统实现的关键技术——模型、仿真、信息、意见以及知识的综合集成进行了深入研究,给出了相应的实现方法。最后,给出了一个面向武器装备论证的原型系统的实例。     

基于知识的制造业客户关系管理系统研究与实现

随着以客户为中心的竞争趋势的形成 ,客户关系管理系统的应用成为企业信息化建设的焦点。本文应用认知科学、数据仓库、智能决策分析等技术 ,并结合知识管理的先进思想 ,将知识转移和客户忠诚度智能分析等功能融入传统客户关系管理系统中 ,进而构建出适合制造业的基于知识的客户关系管理原型系统。     

Document analysis technology in information systems for supporting research and commercial activities

Ontology-based information systems for supporting research and commercial activities are considered. The tool kit required for supporting document analysis by automatic extraction of information of significance to the user from document texts is substantiated. These tools should support the various stages of text analysis and include workbenchs for designing specialized dictionaries and knowledge bases. The proposed approach allows a semantic analysis of texts based on knowledge of the subject domain, document genre, and specific terminology used by experts in the subject.     

面向敏捷企业的工作流系统建模方法

为提高企业的敏捷性，增强工作流管理系统对业务流程变化的适应性，提出了一种基于知识的工作流系统模型，并对该模型的框架构和知识表示进行了详细讨论，通过使用知识表示模式和相关谓词，建立了系统的更改传播机制，增强了系统的可靠性和柔性。最后，通过该思想在工艺设计过程管理系统开发中的实际应用表明，基于知识的工作流系统模型对于实现业务流程的自动化具有一定的应用价值。     

A process-oriented approach to modeling the conceptual design of aircraft assembly lines

The need to develop methods and software applications to support the design of assembly lines is academically and industrially acknowledged. This paper focuses on the conceptual design of aeronautical assembly lines. A model is proposed to represent the process to design an aerostructure assembly line at the conceptual design phase and the knowledge requirements to support such process. The conceptual design process is documented in an Integrated Definition for Function Modeling model and the knowledge model is documented in Unified Modeling Language. The model provides a starting point in the formalization of the assembly line conceptual design. The objective is to use such model for the development of a knowledge-based application prototype in an industrially used software system.     

Information and knowledge interrelationships within a manufacturing knowledge model

An important aspect of knowledge-based decision support systems is the logical modelling of knowledge such that knowledge can be captured and maintained. The classification of knowledge in the creation of such systems and the complex relationships within the significant volume of knowledge has received attention from a broad range of researchers. The work presented here contributes to knowledge-based decision support by exploring the interrelationships between information and knowledge within a manufacturing knowledge model and defines an approach to capture information and knowledge interactions using an object-oriented structure. It goes on to show how this approach can be applied to support process planning decisions within a manufacturing facility.     

A new process-based ontology for KBE system implementation: application to inspection process planning

This paper focuses in the definition of a new ontology (Onto-Process) and the resulting informal model. The developed ontology constitutes an improvement to other ontologies since it covers the requirements of manufacturing processes engineering and, in particular, the inspection planning process with automated machines. Inspection planning activity usually implies to make repetitive and well-known decisions. These decisions are often based on the knowledge of inspection operators; therefore, it is a good candidate for implementing a knowledge-based engineering system. The sequence of activities involved in the inspection planning has been identified using Icam definition diagrams (IDEF0) in order to express the knowledge at a high level. These diagrams constitute an important support for defining the sequence of activities and the information flow. Later on, this information has been analyzed in depth using conceptual maps and it has been classified into units of knowledge. Then, each of these units of knowledge is decomposed into elementary objects of knowledge and relationships among them are defined. In a first approach, the ontology has been tested using a very particular but essential task in inspection planning: the activity related to the definition of contact points over inspection surfaces. In this activity, decisions must be made about the number, distribution, and sequencing of points. In the methodology developed in this paper the differences between form and non-form error inspection is considered. Finally, the knowledge required to support these decisions is represented using Onto-Process.     

A STEP AP224 agent-based early manufacturability assessment environment using XML

Early design assessment activities have a significant impact on reducing the cost of manufacture. The efficient utilisation of the product development time and the level of coordination of the early design activities between the major stakeholders are becoming key factors for success in manufacturing today. The paper reports on a new distributed early design manufacturability assessment methodology using collaborative autonomous agents. A product data model compliant with STEP AP224 and corresponding process and facility data models are proposed to support the decision-making process. XML was used as a medium for exchange of requests and information between design, manufacturing, and facility planning agents. A prototype Web-enabled system for rapid product manufacturability assessment in the extended enterprise has been developed using distributed multi-agent CORBA objects. The reported research is a step towards the development of a generic prototype tool for collaborative design evaluation and rapid assessment of the manufacturing feasibility and resource availability at different stages of the product development process.     

Web-Based Fault Diagnostic and Learning System

Web-based technology holds great potential for enabling the rapid dissemination of information and facilitating distributed decision-making. This paper presents a novel knowledge-based multi-agent system for remote fault diagnosis, which is composed of diagnostic and learning agents (DLAs), machine agents (MAs) and a central management agent (CMA). Machines are remotely diagnosed by the DLAs through the communication channels between the MAs and the DLAs. In addition, the DLAs can learn new expertise from the users, and the CMA can update the central knowledge base (CKB) shared by all the DLAs with the valuable expertise. When faults that cannot be solved with the present knowledge base occur, the DLA can acquire new knowledge, translate it into rules using a rule builder, and update the rules into the CKB. The CKB will become mature through a continuous learning process. A prototype system has been developed and used for remote fault diagnostics of tool wear in computer numerically controlled (CNC) machining. This revised version with a corrected online cover date was published online in April 2004.     

Configuration-oriented product modelling and knowledge management for made-to-order manufacturing enterprises

In made-to-order (MTO) manufacturing enterprises (ME), product architectures are usually modularised and components standardised. Product configuration is a key technology for order realisation in MTO–ME and is a typical knowledge-based application. Through a configuration process, product modules or components are selected and assembled according to customer requirements. Product configuration relates to a great deal of knowledge that represents complexity relations among components or modules, such as configuration rules and assembly constraints. Traditional product modelling techniques are focused mainly on physical product modelling and geometric representation, which makes them insufficient to help in the product configuration process. This paper discusses configuration-oriented product modelling and knowledge management for MTO–ME. A general process of product configuration modelling is proposed. The configuration model represents a product family from which a specific configuration solution or product variant can be derived. Actually, configuration modelling is a process which captures and represents product knowledge. In this paper, product knowledge is organised and managed through a knowledge component (KCOM) that includes configuration rules and constraints. A KCOM-based product knowledge representation model is presented. Finally, a PDM system is extended to support product modelling and knowledge management for MTO configurable products .     

Knowledge management to support product development in cold roll-forming environment

Knowledge and information management has focused on how available knowledge is exploited to enhance organisational performance especially in marketing, costing, design, and manufacturing activities; however, there is limited information on how knowledge acquired during product development can be utilised to provide decision support throughout the product life cycle. Existing knowledge management systems do not seem to provide information on well-known manufacturing constraints and product attributes identified during product development. Secondly, such systems do not provide the means to identify, capture, formalise, present and utilise tacit knowledge which have a major impact on overall product development process. Consequently, knowledge and experiences gained from existing projects are sometimes poorly documented and therefore are not available for reuse in future projects. An organised transfer of knowledge from previous projects will no doubt enhance the quality, efficiency, cost, and time to market of new products and processes. The study carried out here has developed a knowledge management framework to support product development in a cold roll-forming manufacturing environment. Process modelling supported by Integrated Definition for Function Modeling methodology was applied to guide the identification of information and knowledge required to support product development and also for effective decision making in routine cold roll forming.     

面向退役机电产品全生命周期的知识图谱统一建模方法研究

针对退役机电产品逆向物流信息追溯过程中时空分散度高、质量不确定性强、跨组织信息关联度弱等问题,基于知识图谱技术构建了退役机电产品全生命周期统一数据模型。首先提出了从跨组织多源数据到知识图谱构建和应用的全生命周期统一数据建模方法,然后提出了知识图谱构建关键技术,针对知识图谱构建过程中的实体关系联合抽取问题,建立了基于分段注意力融合机制的实体关系联合抽取模型,解决了实体关系重叠问题,并在标准数据集和退役机电产品领域数据集上进行测试,取得了很好的效果,最后建立了退役机电产品全生命周期信息追溯系统。知识图谱的构建实现了退役机电产品生命周期中跨组织信息的统一数据结构,为退役机电产品逆向物流信息追溯提供了强有力的支撑。     

Aspects of a knowledge-based tool for manufacturing systems design

In the face of increasing worldwide competition, many manufacturing companies are reassessing their operations. Systematic design of manufacturing systems increasingly requires the adoption of a multidisciplinary approach involving all aspects of a company's activities. In carrying out this task, well structured knowledge-based systems can act as a useful tool for supporting the work of trained manufacturing systems engineers. This is due to the complex and iterative nature of the systems design process which requires the integration of knowledge from a number of application domains. User acceptance of the resulting knowledge-based system is critically dependent on the human-computer interface which, in this case, must be adaptable to the varied requirements of users with different levels of expertise and specialist skills. This paper describes the facilities provided in one such knowledge-based tool developed to help redesign existing manufacturing systems.