航空制造知识图谱构建研究综述

目前航空装备制造企业的设计、制造相关流程中积累了大量数据,基于知识图谱技术可以对这些数据进行有效融合与管理,对不断更新的制造知识进行挖掘,将为航空制造企业智慧化升级提供有力的知识支撑。为探明知识图谱在航空制造领域的理论支撑体系与实际应用情况,通过文献调研分析航空制造知识图谱架构、定义及特点;阐明知识图谱领域构建过程中的核心技术并进行研究综述,对比航空制造知识图谱与通用知识图谱构建技术上的异同,并提出了三个切合实际的航空制造知识图谱应用方向及其解决方案;最后对未来航空制造知识图谱的挑战进行了分析及展望,为后续该领域的研究提供一些思路。     

一种增强Web Services的服务质量和性能的方法

为了更好地把握股票价格的波动，应用了在处理序列数据输入输出具有优越性的Elman 递归神经网络建立股市预测模型，并用两支股票进行了检测，检测结果说明人工神经网络应用于中国股票市场的预测是可行和有效的，有着良好的前景。     

Ontology‐based Grid resource management

Grid resources are typically diverse in nature with respect to their software and hardware configurations, resource usage policies and the kind of application they support. Aggregating and monitoring these resources, and discovering suitable resources for the applications become a challenging issue. This is partially due to the representation of Grid metadata supported by the existing Grid middleware which offers limited scope for matching the job requirements that directly affect scheduling decisions. This paper proposes a semantic component in conventional Grid architecture to support ontology‐based representation of Grid metadata and facilitate context‐based information retrieval that complements Grid schedulers for effective resource management. Web Ontology language is used for creating Grid resource ontology and Algernon inference engine has been used for resource discovery. This semantic component has been integrated with conventional Grid schedulers. Several experiments have also been carried out to investigate the performance overhead that arises while integrating this component with Grid schedulers. Copyright © 2009 John Wiley & Sons, Ltd.     

分布式GIS的多Agent系统建模与实现

将Agent技术引入到分布式GIS领域，提出了一个面向分布式GIS的多Agent系统模型，为分布式GIS的研究和开发提供了一种新的方法．首先设计了系统的体系结构，将分布式GIS系统中的Agent分成三类：Facilitator，GIS功能Agent和接口Agent，并给出了GIS Agent的结构和特征以及Agent之间的通信机制；然后采用DCOM技术和多线程技术，实现了一个空间多Agent系统的原型，并对其中的关键技术(同步技术、Agent的调度、Agent的强制终止等)进行了分析和探讨．     

Suboptimal Output Consensus for Time‐Delayed Singular Multi‐Agent Systems

The current paper investigates guaranteed‐cost output consensus analysis and design problems for high‐order linear time‐invariant singular multi‐agent systems with constant time delays, which can realize suboptimal output consensus control. Firstly, a new output consensus protocol with a suboptimal index and a single delay is proposed to realize the tradeoff design between output consensus regulation performances and control energy consumptions. Then, sufficient conditions for guaranteed‐cost output consensus and consensualization are derived in terms of linear matrix inequalities by a combined tool from the Lyapunov‐Krasovskii approach and the free‐weighting matrix technique, respectively, and the output consensus function is determined on the basis of the First Equivalent Form. Finally, a numerical example is performed to demonstrate the effectiveness and conservativeness of theoretical results.     

基于物联网的航天产品装配物流管理系统研究

针对某航天企业装配生产物料品种多、数量大和物流管理复杂等问题,将物联网技术应于装配物流管理中,构建具有感知层、网络层和应用层的装配物流管理系统架构。在感知层,综合应用条形码和RFID对装配物料进行多手段标识和多方式感知。在网络层,基于企业现有的网络资源,利用IPv6、2G/3G、Wi-Fi等现代先进通信技术搭建网络支撑体系。在应用层,给出包括物料库存管理、物料配送管理、现场物流监控管理、装配生产资源管理模块的功能模型。最后,参照Java EE技术架构,采用Java和JSP语言开发实现B/S架构的航天产品装配物流管理原型系统。     

Preliminary design and manufacturing planning integration using web-based intelligent agents

Software agents have been increasingly used in the product and process development in industry over the past years due to the rapid evolvement of the Internet technology. This paper describes agents for the integration of conceptual design and process planning. Agents provide mechanisms to interact with each other. This mechanism is important since both of those processes involve negotiations for optimization. A set of design and planning software agents has been developed. These agents are used in a computer-based collaborative environment, called a multi-agent platform. The main purpose of developing such a platform is to support product preliminary design, optimize product form and structure, and reduce the manufacturing cost in the early design stage. The agents on the platform have access to a knowledge base that contains design and planning rules. These rules are derived from an analysis of design factors that influence process and resource planning, such as product material, form, shape complexity, features, dimension, tolerance, surface condition, production volume, and production rate. These rules are used by process planning agents to provide process planners with information regarding selecting preliminary manufacturing processes, determining manufacturing resources, and constructing feedback information to product designers. Additionally, the agents communicate with WEB servers, and they are accessible by users through Internet browsers. During performing design and planning tasks, agents access the data pertinent to design and manufacturing processes by the programming interfaces of existing computer-aided design (CAD) and manufacturing system. The agents are supported by a developed prototype agent platform. The agents and the platform enable the information exchange among agents, based on a previously developed integrated design and manufacturing process object model.     

A hybrid multi-agent system architecture for enterprise integration using computer networks

The manufacturing industries are now experiencing fierce pressure of competition from every corner on this planet. In addition, the advancement in computer networks and information technologies has been gradually reshaping the manufacturing companies by shifting from the industrial age to the information era. Due to these elevated competitiveness and advanced computer technology, a number of new manufacturing and management strategies (e.g., CE or CIM) have emerged for the innovation of manufacturing enterprises. Although they have different definitions and scopes, there are several common issues: inter-enterprise functions integration; inter-enterprise resources integration; and collaboration. This paper proposes a new multi-agent system (MAS) architecture to support the inter-enterprise functions/resources integration and collaboration over the networked environment, including the hybrid agent architecture and hybrid network architecture. In contrast to the existing agent architectures, the proposed agent architecture enables agents to exhibit the hybrid (continuous and discrete) behavior and interactions. In addition, our network architecture is more suitable for building the large-scale distributed manufacturing systems that are prone to dynamic random changes of their environment. Based on the proposed MAS architecture, a collaborative product development environment is implemented as a starting point, and a multidisciplinary team-oriented design problem is illustrated to provide the vision of the proposed MAS architecture.     

Development of an agent-based Virtual CIM architecture for small to medium manufacturers

Today's global competitions are forcing enterprises to rely on integrated manufacturing systems to satisfy constantly changing market requirements. Whereas Small to Medium Enterprises (SMEs) often feel difficult to compete with large organisations due to having insufficient resources. By integrating resources of many partners, the SMEs can form global integrated manufacturing systems in the form of Virtual CIM (VCIM) and thus achieve a competitive edge. VCIM is a concept towards integrating globally distributed manufacturing resources across enterprise boundaries. In order to implement VCIM, this research project develops an agent-based architecture to support the integration and scheduling of distributed manufacturing resources. This architecture accommodates all agents for VCIM with a three-layered structure and permits new agents to be connected with the existing structure through the Internet when and where necessary. In this architecture, many Facilitator agents coordinate activities of manufacturing resources in a parallel manner. Meanwhile, the Facilitator agents achieve proposal messages through agent negotiation based on distributed resources’ real time information and use a backward network algorithm for shortest-path to perform optimisation for resource allocation. With these approaches, an optimised production schedule has the lowest cost as the primary criteria and the shortest production time as the secondary criteria while satisfying customer required due date/time and delivering destination.     

Agent计算的理论框架

如何开发复杂、庞大的Ｍｕｌｔｉ－ａｇｅｎｔ系统是目前人们关心的一个重要研究课题．文中提出了Ｍｕｌｔｉ－ａｇｅｎｔ系统中Ａｇｅｎｔ计算的理论框架,以提供方法和概念体系用于刻画和描述Ｍｕｌｔｉ－ａｇｅｎｔ系统的需求、指导系统设计．文中提出了Ａｇｅｎｔ的一种新的体系结构——ＢＩＣＣ体系结构,即Ａｇｅｎｔ是由信念（ｂｅｌｉｅｆ）、意愿（ｉｎｔｅｎｔｉｏｎ）、能力（ｃａｐａｂｉｌｉｔｙ）、承诺（ｃｏｍ ｍ ｉｔｍ ｅｎｔ）构成的意向系统．基于Ｍｕｌｔｉ－ａｇｅｎｔ系统计算的逻辑框架,文中给出了构成Ａｇｅｎｔ体系结构各个认知成份的语义定义,分析了Ａｇｅｎｔ是如何基于该体系结构来进行计算的,最后研究和验证了在动态、不确定的Ｍｕｌｔｉ－ａｇｅｎｔ系统中Ａｇｅｎｔ计算的活性和安全性问题