基于案例推理的信息系统业务流程知识重用技术研究

本文在研究信息系统业务流程设计的知识表示与重用技术的基础上,提出了一种基于案例的智能化设计知识重用方法进行信息系统业务流程设计.重用方法包含案例表示、基于相似度算法和智能聚类的案例检索、案例优化、案例库组织四个方面.综合四个方面,实现了基于案例推理的业务流程案例检索和知识重用实验系统原型,并进行了实验.实验结果表明本重用方法具有较好的可行性、有效性、效率与质量.     

基于案例推理的故障诊断算法

电力系统智能告警研究目前主要集中于规则推理领域,未能充分利用系统内历史故障的案例进行有效的分析与故障处理.本文初步研究了基于案例推理的故障诊断算法,在此基础上提出了一种基于向量计算的案例匹配算法.该算法通过对故障信息进行抽象,并与系统案例库中的案例进行相似度计算的方式,对故障信息与案例信息进行一一匹配.案例库的建立基于经过人工分析的各类历史故障信息.相似案例的故障性质、故障原因分析可对本次故障的分析、诊断和后续处理起到指导作用.     

基于案例推理的交通疏导辅助决策方法

为避免实际交通疏导问题中人为主观因素的影响,将案例推理理论应用于交通疏导决策中,提出一种基于案例推理的交通疏导决策方法,建立交通疏导案例库模型。区分属性数据类型,设计基于ID 3信息熵的案例相似度算法,案例匹配时可以兼顾特征属性与案例效果,避免传统算法中属性值缺失的问题。实例验证了该方法能够提高案例推理结果的准确度,对辅助处理交通疏导问题具有一定实际指导意义。     

面向工艺品个性化定制的图案构型提取与重用

针对工艺品个性化定制过程中知识重用性较低的问题,提出一种图案构型提取与 重用的方法,并以蜡染图案创新设计为例开展研究。首先,将蜡染知识按照工艺品个性化定制 的应用需求进行分类整理,建立蜡染知识库和案例库,并构建两者之间的语义关系,通过本体 语义检索,推荐出符合用户需求的蜡染案例。采用形状上下文法对蜡染图案的纹样进行提取, 结合拓扑学方法建立图案的构型规则。在构型重用过程中提出基于字符编码的改进形状文法, 用于表述纹样填充过程中形状的变换,从而完成了面向工艺品个性化定制的蜡染图案重用。开 发蜡染工艺品个性化定制系统,通过实例验证了该方法的可行性。     

基于案例推理的ISP知识重用方法

针对企业信息化中信息系统规划(ISP)在较大程度上依赖先前规划经验和知识的特点,为有效支持ISP知识重用和管理创新,将案例推理技术应用于ISP知识重用的全过程,提出基于案例推理的ISP知识重用方法(HRM KGANNA),研究应用框架、案例表示、案例检索算法与重用等关键技术。通过组织案例库进行ISP知识检索实验,结果表明HRM KGANNA法具有良好的准确性和较高的效率。     

基于敏感度分析的车站应急预案生成算法研究

为提高铁路车站的应急预案管理水平和应急处理能力,提出一种基于敏感度分析的案例推理方法的应急预案管理模型。运用面向对象的框架表示方法来进行案例表示和建立案例库,构建案例特征属性的层次结构。采用层次分析法确定车站紧急事件预案特征属性的权重,运用全局相似度算法对已有应急案例进行检索与匹配。实例证明该方法能有效提高车站应急决策效率,实现预案决策的信息化和智能化。     

基于投影寻踪和MapReduce的并行案例推理模型

在大规模、高维度的数据环境下,传统的案例推理具有计算复杂度高、实时性差等缺点。为在大数据环境下进行案例推理,提出了一种基于投影寻踪和MapReduce的并行推理模型dpCBR。在数据预处理阶段,计算源案例到基准向量的一维投影距离并缓存,降低计算复杂度并减少重复计算开销。在案例检索阶段,先根据投影距离裁剪案例库,再进行相似度匹配,减少不必要的案例匹配开销。应用MapReduce进行分布式并行处理,使dpCBR具备对大规模案例库的推理能力。实验结果表明,dpCBR模型可以明显提高大数据环境下案例推理的效率。     

民航突发事件应急案例语义检索方法研究

针对突发事件条件下民航应急管理与决策的特殊性,设计了一个基于领域本体的民航突发事件应急案例语义检索系统模型。通过民航突发事件领域本体与语义案例库构建方法的研究,提出了一种针对语义查询请求及其语义分析过程的语义模式表达式匹配算法,并采用基于SWRL规则的推理过程实现了民航突发事件应急案例的语义检索。给出了仿真实验与结果分析,为基于本体的民航突发事件应急管理与决策提供了理论与方法支持。     

基于案例属性特征区间相似度的改进算法研究

基于案例推理的关键是确定问题案例与案例库中的案例属性特征的相似度.针对相似度的算法问题,在分析比较多种已有算法的基础上,提出一种解决感知信息和案例库中的案例属性特征均为不确定或不完整信息的区间相似度计算模型,论证了该模型的计算结果适用于特定区间内微小区间相似的问题.结合某型艇抗沉辅助决策系统的预案推理问题,对已有的算法求解结果进行比较,证实该模型可提高案例相似度的计算结果灵敏度.     

一种基于案例属性特征的区间相似度改进算法研究

基于案例推理的关键是确定问题案例与案例库中的案例属性特征的相似度,针对相似度的算法问题,在分析比较多种已有算法的基础上,提出了一种解决感知信息和案例库中的案例属性特征均为不确定或者不完整信息的区间相似度计算模型,论证了该模型的计算结果适用于特定区间内微小区间相似的问题。结合某型艇抗沉辅助决策系统的预案推理问题,对已有的算法求解结果进行比较,证实了该模型提高了案例相似度计算结果灵敏度。     

Service customization under capacity constraints: an auction-based model

In mass customization, companies strive to enhance customer value by providing products and services that are approximate to customers’ needs. A company’s strategy of allocating its limited capacity to meeting diverse customer requirements directly impact customer perceived value in terms of available options, cost, and schedule. Proposed in this paper is an auction-based mass customization model for solving the problem of service customization under capacity constraints. The proposed model integrates customers’ customization decision making with the allocation of company’s capacity through multilateral negotiation between the company and its customers. The negotiation is conducted through a combinatorial iterative auction designed to maximize the overall customer value given limited capacity. The auction is incentive-compatible in the sense that customers will follow the prescribed myopic best-response bidding strategy. Experimental results indicate that customization solutions computed by the proposed model are very close to the optimal one. Revenue performance is also adequate when there is sufficient competition in the market.     

实现中小企业产品设计重用的若干途径

产品设计知识重用日益受到国内外企业和学术界的关注。根据我国中小企业进行产品设计知识重用需求,讨论了适宜我国中小企业进行产品设计重用的若干途径和方法,主要包括:采用大规模定制、基于PDM等商品化软件、基于Web的零件库资源共享,以及基于CAD知识和工程语义的产品知识重用方法。该方法基于CAD知识和工程语义的双重网,解决一个面向低层次的产品结构的知识表达、查询和重用问题。     

基于KBE的电梯智能设计系统

开发了一个基于知识工程(KBE)技术的面向客户定制的电梯智能设计系统，通过对电梯产品所蕴涵的知识进行归类建库，实现知识的模块化管理；并综合参数化设计、特征建模和软件集成等技术，将产品的特征和产品中凝聚的知识、经验和规则一体封装，建立内容丰富的实例库，以支持并实现智能设计．使用该系统企业可避免大部分重复开发工作，实现大量既有知识的重用，显著提高企业快速响应市场的能力和新产品开发的效率．     

Mass customization design of engineer-to-order products using Benders’ decomposition and bi-level stochastic programming

Leveraging product differentiation and mass production efficiency in mass customization basically entails a configure-to-order paradigm. In the engineer-to-order (ETO) business, however, companies build unique products in response to ‘foreseeable’ customer specifications. The key challenge of ETO mass customization lies in the complexity of accommodating future design changes when customers are involved in customizing design specifications. This paper proposes a two-stage, bi-level stochastic programming framework to tackle ETO mass customization. At the first stage, product platform configuration is integrated with production reconfiguration, which is formulated as a shortest path problem with resource constraints (SPPRC) to optimize production delays within the capabilities of the process platform. Benders’ decomposition algorithm is applied to solve this optimal configuration problem owing to its high computational efficiency. The second stage scrutinizes the optimal configuration resulting from the first stage for scaling optimization of design parameters (DPs) for each module. All DPs are differentiated by standard or customizable DPs. A bi-level stochastic program is implemented to leverage conflicting goals between the producer (leader) and consumer (follower) surpluses. As a result, ETO customization design is anchored with optimal values of standard DPs and optimal value ranges of customizable DPs. A case study of ship engine and power generator ETO design is presented, demonstrating the feasibility and potential of the ETO mass customization framework.     

Collaborative contracting for Manufacturing-as-a-Service (MaaS) by information content measurement and decision tree learning

Product realization through Manufacturing-as-a-Service (MaaS) has observed as an emerging trend towards Industry 4.0. It offers new opportunities for reaching external partner’s knowledge and resources while allowing companies to focus on their core competencies. This paper envisions the importance of collaborative contracting for MaaS fulfillments, in which tournament-based crowdsourcing entails evaluation and selection of manufacturing service providers as a best-matching problem of multi-criteria decision making. MaaS collaborative contracting involves numerous evaluation criteria related to not only technical capabilities of the fulfilling agents, but also their business performance involved with MaaS operations in the past history. This paper develops a contracting analysis and evaluation methodology for selection of appropriate MaaS agent selection. The proposed evaluation mechanism utilizes information content measure and decision tree learning for better matching of fulfilling agents to maximize customer satisfaction and effectiveness of multiple stakeholders of MaaS operations. The multi-attribute utility theory is integrated with decision tree learning within a coherent predictive analytics framework to not only synthesize pre-defined functional and cost requirements for customers, but also leverage upon historical data of business performance. A case study of orthodontic brace mass customization through MaaS is reported to illustrate the feasibility and potential of collaborative contracting in MaaS.     

A knowledge support approach for the preliminary design of platform-based products in Engineering-To-Order manufacturing

A product platform is a design approach for meeting the demand for customizable products. Traditional knowledge-based technologies or systems lack flexibility in supporting both configuration and parameter design of platform-based products. In many cases, customers’ requirements and knowledge models both contain incomplete information, and there are complex relations among various solutions, functions and solution parameters in Engineering-To-Order (ETO) products. A knowledge model for the preliminary design of ETO products is presented in this paper, and linkages are established between configuration design knowledge and parameter design procedures. The basis of the knowledge model is the Extended Function-Solutions (EFS) tree, from which design case trees, design modules, constraint checking rules, and module interface templates derive. A corresponding knowledge retrieval and reuse strategy is also presented. It uses an improved fuzzy information axiom to search for the optimal configuration with incomplete information. The parameter design process model of new products then can be generated based on the optimal configuration. The case study demonstrates the knowledge modeling, retrieval and reuse for the preliminary design of open-type crank presses. Moreover, the effectiveness of the methodology is discussed by analyzing the verification approach and the satisfaction of customers’ requirements.     

Assessment of a Product Range Model concept to support design reuse using rule based systems and case based reasoning

Knowledge reuse is recognised as a key element to support agile and effective decision-making processes during product development. The provision of information and knowledge for reuse relies on defined information structures and requires computational techniques that enable the reuse process within an integrated environment. Although, representing, saving, and sharing information is relatively well known for product modelling, it is accepted that effective and agile product development also requires knowledge sharing. For this reason, extensions of the Product Model structure are required to support specific product development process phases. This work argues that a product information model combined with extended knowledge models can provide decision support throughout the product development phases. This paper presents the results of an investigation into a specific extended knowledge model concept, named a Product Range Model (PRM), which combines both rule based systems and case based reasoning to provide product design decision support. Two product development scenarios, injection moulding and friction materials, have been selected in order to evaluate the ideas presented. For both applications the relevance of the models to support the capture and reuse of information and knowledge is stressed.     

Knowledge reuse in manufacturability analysis

This paper describes a set of modelling guidelines for the improved reuse of manufacturing knowledge in decision support systems. The work draws on research into product and manufacturing knowledge models, and uses a case study based on a simplified jet engine combustion chamber casing to illustrate the proposed guidelines. The paper describes three principles of reuse, i.e., the separation of information from knowledge, the separation of product knowledge from manufacturing process knowledge, and the correct classification of manufacturing knowledge. Whilst the first two principles were found to be well established in the research literature, guidance on how to apply classification hierarchies for optimum reuse was found to be insufficient. The guidelines presented in this paper therefore provide improved guidance on how to classify manufacturing knowledge for optimum reuse.     

Mass customization and personalization software development: a case study eco-design product service system

A large number of customers currently require manufacturers to develop more flexible products to satisfy their own personalization. Due to buyer’s market and short product lifecycles, many industries are beginning to shift from mass production to mass customization to satisfy their customer requirements. The purpose of this research is to provide a model for enhancing the software component design in order to improve quality and reusability, as well as to reduce costs based on the concept of mass customization and personalization (MC&P). First, quality function deployment (QFD) was used to find out what the customers think, and to determine the core functions and components of the software. The mass customization technology was then used to aggregate the software modules. Thirdly, the software costs for business strategies, purchasing and renting under the customization model were evaluated. Finally, a real case of Eco design software in PSS was illustrated based on the model.