面向军事群体的聚合及解聚可视化控制模型

作战编队是军事领域特有的军事群体组织方式,具有广泛的军事应用,针对战场态势中作战编队的聚合/解聚可视化问题,基于知识图谱及模型-视图-控制器(MVC)设计模式,提出了面向作战编队的聚合/解聚可视化控制模型,主要研究作战编队基于MVC的架构设计、作战编队基于知识图谱语义建模、基于主成分分析（PCA）的作战编队区域几何辅助对象构建、作战编队解聚/聚合ADLOD显示及地图比例尺控制以及作战编队聚合/解聚可视化模型的向量形式表征,该模型既弥补了军事标绘相关标准中作战群体方面研究的空白,也为联合作战态势多分辨率显示优化提供了基于作战编队聚合简化的新技术途径,同时,提供的可视化手段可加深对战场综合态势的认知,提升作战指挥决策水平,军事应用前景良好。     

一个基于知识的电网调度操作票自动规划系统

本文介绍电网调度操作票专家系统ＥＳＤＰＯＮ。电网调度操作票的制定可看作一个规划问题。由于电网拓扑结构特别是电网操作本身呈现层次性,故推理机采用分层规划控制策略。相应地,知识库也分层次组织,具有三类规则。     

面向目标的博弈搜索策略及其应用

博弈是人工智能研究的重要分支,它涉及人工智能中的推理技术、搜索方法和决策规划。而搜索策略是博弈问题的关键。针对搜索技术中存在的由于搜索空间巨大而引起的搜索效率下降的缺点,结合五子棋的特点,探讨了相应博弈问题的求解策略,提出一种结合PVS算法、静态着法启发、历史启发算法的搜索策略。实验结果证明,该算法不但能保证博弈水平,还能得到较好的搜索效率。     

Building a Tool for Battle Planning: Challenges,Tradeoffs, and Experimental Findings

Use of knowledge-based decision aids can help alleviate the challenges of planning complex operations. We describe a knowledge-based tool capable of translating a high-level concept for a tactical military operation into a fully detailed, actionable plan, producing automatically (or with human guidance) plans with realistic degree of detail and complexity. Tight interleaving of planning, adversary estimates, scheduling, routing, attrition and consumption processes comprise the computational approach of this tool. Although originally developed for Army large-unit operations, the technology is generic and also applies to a number of other domains, particularly in critical situations requiring detailed planning within a constrained period of time. In this paper, we focus particularly on the engineering tradeoffs in the design of the tool. An experimental comparative evaluation indicated that the tool's performance compared favorably with human planners. Alexander Kott is a Program Manager at Defense Advanced Research Projects Agency (DARPA). While performing the research described in this paper, he was the Director of R&D at Carnegie Group, Inc., and a Technical Director at BBN Technologies in Pittsburgh, PA. His work included development of algorithms and decision aids for dealing with dynamic planning and scheduling in constrained, uncertain and adversarial environments, and research in dynamic distributed decision-making systems, such as in military command and control. He earned his PhD from the University of Pittsburgh where he explored the use AI techniques for innovative design of systems. He can be reached at DARPA, 3701 N Fairfax Drive, Arlington, VA, 22203. Raymond Budd is a member of the technical staff at BBN Technologies. His areas of interest include knowledge representations, knowledge engineering, and planning and scheduling. He received a BS in computer science from the University of Pittsburgh. Contact him at BBN Technologies 1300 N. 17th Street, Suite 400, Arlington, VA 22209. Larry Ground is a senior analyst with Green River Associates, Inc. His research interests include development of tools for analysis and decision support of Army maneuver and logistics planning. Retired from the US Army as a Lieutenant Colonel, he served in a variety of command and staff positions and taught at the US Army Command and General Staff College. He is a Certified Professional Logistician by the International Society of Logistics. Contact him at Green River Associates, Inc., Fredericksburg, VA. Lakshmi Rebbapragada is a senior computer engineer at US Army CECOM Research, Development and Engineering Center (RDEC). Her research interests include application of advanced technologies to tactical planning, execution-based replanning, VA Standards for Ontology based Knowledge sharing re-use, and Network Centric Infrastructure for Command and Control. She is a member of the IEEE Standard Upper Ontology (SUO) Working Group. She has a Ph.D in High Energy Physics from Bristol University U.K. She can be contacted at PM UA NSI Battle Command, Bldg. 2405, Ft. Monmouth, NJ 07703. John Langston is a senior analyst with Austin Information Systems. He served in a variety of command and staff positions in the US Army, including extensive combat experience in the Republic of Vietnam. Retired as a Lieutenant Colonel, he is widely recognized for his extensive research and knowledge in the areas of military leadership and decision making and has contributed significantly to the development of automated battle planning tools. Contact him at Austin Information Systems, Whispering Woods Cove, Parkville, MO 64152.     

A knowledge-based architecture for implementing military geographical intelligence system on Intranet

Military geographical intelligence analysis in support of both tactical and strategic operation is a process that is associated with data gathering, processing, analyzing, and distribution. It is an important activity, carried out before the preparation of a military operation. A system that can assist in arranging support, exercise analysis training, and manage knowledge on military geographical intelligence have always been ultimate goals for both military intelligence units and intelligence officers alike. Therefore, it can be seen that research into the military geographical intelligence system is a critical and important research subject. This research investigates military geographical intelligence systems as a problem-solving procedure in terms of observing the military geographical intelligence operational procedure, generating situation analysis, and generating planning process. This paper intends to present a knowledge-based architecture that incorporates the function of case base, heuristic base, and rule base for implementing the military geographical intelligence system on Intranet.     

A knowledge-based architecture for implementing collaborative problem-solving methods in military e-training

E-learning systems provide a variety of instructional aids and communication methods, and offer learners great flexibility as to the time and place of instruction. Given these advantages, it is not surprising that business and educational institutions are making substantial investments in e-learning systems. In military, the military scenario is a tool or environment that supports the classroom training in collaborative decision-making and problem solving. It offers a method to train officers by simulating battlefield situations to analyze situations, generate plans, make decision, and acquire knowledge and experience from the scenario training procedure. This article is an example on implementing a military e-training system on military training institute in the Taiwanese Military. For this, this paper proposes a knowledge-based system architecture that incorporates the functions of military training materials, scenario case base, database, and geographical information systems (GIS) in terms of integrating web-based and collaborative problem solving methods in military collaborative scenario training. A scenario case is presented as an example of system implementation and some issue discussion are also described.     

Case-based heuristic selection for timetabling problems

This paper presents a case-based heuristic selection approach for automated university course and exam timetabling. The method described in this paper is motivated by the goal of developing timetabling systems that are fundamentally more general than the current state of the art. Heuristics that worked well in previous similar situations are memorized in a case base and are retrieved for solving the problem in hand. Knowledge discovery techniques are employed in two distinct scenarios. Firstly, we model the problem and the problem solving situations along with specific heuristics for those problems. Secondly, we refine the case base and discard cases which prove to be non-useful in solving new problems. Experimental results are presented and analyzed. It is shown that case based reasoning can act effectively as an intelligent approach to learn which heuristics work well for particular timetabling situations. We conclude by outlining and discussing potential research issues in this critical area of knowledge discovery for different difficult timetabling problems.     

一种基于MAS/CDMA的军事指挥通信系统

设计了一个基于MAS/CDMA的导弹部队作战指挥通信系统,该系统具有安全性好、使用方便,节约成本等优点,为我军军事指挥系统的智能化、信息化发展提供一个新的途径,亦可以此为蓝本用于别的战术作战部队或者车辆等的管理。     

SVNTS算法的动态武器目标分配问题研究

动态武器目标分配(Weapon Target Assignment,WTA)问题是军事运筹学研究的重要理论问题,也是作战指挥决策中迫切需要解决的现实问题。运用约束规划方法建立了动态WTA问题的约束满足问题(ConstraintSatisfactionProb-lem,CSP)模型。提出了随机变邻域禁忌搜索(StochasticVariableNeighborhoodTabuSearch,SVNTS)算法对模型进行求解。与静态WTA模型相比,动态WTA模型通过时间优化以及匹配优化解决了武器射击时机问题,提高了武器利用效率。SVNTS算法运算速度快,解的质量基本令人满意,可用于解决较大规模的动态WTA问题。最后通过仿真实验,验证了模型和算法的有效性。     

数据挖掘技术在我军C4ISR指挥控制系统中的应用

随着军事高科技的发展,信息战成为现代战争的一种主要作战形态。作为军事信息化建设的重要组成部分,C4ISR（指挥、控制、通信、计算机、情报、监视与侦察）系统是实现军事指挥自动化的主要内容。对数据挖掘技术在我军C4ISR指挥控制系统的应用进行了探讨,为部队作战、训练和管理提供智能化的数据分析方法和决策依据。     

问题求解建模：开发对问题求解任务的深入理解

问题求解建模旨在基于ＰＳ的结构化组织去构造ＰＳ过程模型和ＰＳ参考的世界模型。引入知识级分析并使用基于问题归约的分析方法，促进了对ＰＳ组织的开发，尤其是ＰＳ概念模型和深，浅层推理的综合。对于ＰＳ组织的深入理解不仅提高了ＰＳ性能，对启发式联和领域基本知识的获取也具有指导作用。     

Dispatching rule selection using artificial neural networks for dynamic planning and scheduling

To schedule a job shop, the first task is to select an appropriate scheduling algorithm or rule. Because of the complexity of scheduling problems, no general algorithm sufficient for solving all scheduling problems has yet been developed. Most job-shop scheduling systems offer alternative algorithms for different situations, and experienced human schedulers are needed to select the best dispatching rule in these systems. This paper proposes a new algorithm for job-shop scheduling problems. This algorithm consists of three stages. First, computer simulation techniques are used to evaluate the efficiency of heuristic rules in different scheduling situations. Second, the simulation results are used to train a neural network in order to capture the knowledge which can be used to select the most efficient heuristic rule for each scheduling situation. Finally, the trained neural network is used as a dispatching rule selector in the real-time scheduling process. Research results have shown great potential in using a neural network to replace human schedulers in selecting an appropriate approach for real-time scheduling. This research is part of an ongoing project of developing a real-time planning and scheduling system.     

基于GA和机器学习的启发式规则调度方法

采用基于遗传算法的启发式规则的新型调度方法来处理可变工艺路径的调度问题,同时建立起启发式调度规则库和用于选择规则的知识库,并利用机器学习和模糊推理机制进行样本与知识库的匹配,实现高效实用的调度。计算实例表明了该算法的优越性能     

Trends in cooperative distributed problem solving

The authors present an overview of cooperative distributed problem solving (CDPS), an emerging research area that combines aspects of AI (artificial intelligence) and distributed processing. CDPS can be used to study how a loosely coupled network of sophisticated problem-solving nodes can solve a complex problem which consists of a set of interdependent subproblems. Subproblems arise because of spatial, temporal, and functional distribution of data, knowledge, and processing capabilities. Application areas include distributed interpretation, distributed planning and control, cooperating expert systems, and computer-supported human cooperation. The authors survey the important approaches and empirical investigations that have been developed. The approaches covered include negotiation, functionally accurate cooperation, organizational structuring, multiagent planning, sophisticated local control, and theoretical frameworks     

物联网关键技术及典型军事应用

物联网技术能够实现物与物之间的互联和监控,因而必将引起军事领域的巨大变革,成为加速军队战斗力生成模式转变、推进军事变革的有力推手。文中描述了物联网的发展历程,介绍了物联网的技术框架和标准化进程以及物联网在军事上的典型应用,包括战场兵力呈现系统、战场物资保障综合系统和战术战法仿真验证系统。利用这些系统,可使指挥员实时感知战场的兵力分布和物资保障情况,并能通过获得的敌方兵力分布,来对不同的战术战法进行仿真,以验证其可行性和有效性。     

军事组织本体分析

军事组织是作战的重要要素之一,军事组织关系,特别是指挥控制关系、通信关系和联合作战关系,是现代作战结构的核心,其描述对于军事建模仿真、军事训练系统和指挥自动化系统开发具有重要的意义。本文试图建立军事组织的本体框架,以便于组织知识的重用、互操作和知识验证。     

A knowledge-based inspection process planning system for coordinate measuring machines

The coordinate measuring machine (CMM) is one of the most effective geometry inspection facilities used in manufacturing industry. To fully utilize its capabilities in a computer-integrated manufacturing (CIM) environment, we should integrate CMM with other systems and facilities. This paper presents the development of a knowledge-based inspection planner based on the fundamental principles of AI planning to integrate computer-aided design systems and CMMs. The issues involved in CAD-directed inspection process planning are examined; the task of inspection process planning is decomposed into a number of sub-tasks. According to the task decomposition, a knowledge-based planning system was designed with several modules. Each of these modules consists of a knowledge base, a control operator, a context and a communication interface. The knowledge base is the local knowledge source for problem solving; the control operator determines when and where the knowledge is applied; the context contains the initial planning state which is essential input part information, the intermediate planning states which result from the tentative decision made by the modules, and the goal state. The module interfacing was realized by directly calling procedures defined in other modules to pass the planning tasks and decisions. Examples are included to explain the planning knowledge and strategy.     

Representing inference control by hypothesis-based association

An approach for representing inference control is presented. It is proposed that the representation of inference control should consist of two levels: planning level which realizes problem solving strategies, and a performing level, which represents inference tactics. Based on this approach, the representation system hypothesis-based associative representation (HAR) has been developed to realize the functional architecture for knowledge-based systems. Because users are allowed to organize hypothesis-based associative networks that perform the problem solving strategies with different features, HAR becomes not only a tool for building knowledge-based systems, but also an environment for exploring AI techniques. For example, by comparing three strategies of block-world action planning, it is found that the least commitment strategy is the most efficient     

Planning and meta-planning (MOLGEN: Part 2)

The selection of what to do next is often the hardest part of resource-limited problem solving. In planning problems, there are typically many goals to be achieved in some order. The goals interact with each other in ways which depend both on the order in which they are achieved and on the particular operators which are used to achieve them. A planning program needs to keep its options open because decisions about one part of a plan are likely to have consequences for another part.This paper describes an approach to planning which integrates and extends two strategies termed the least-commitment and the heuristic strategies. By integrating these, the approach makes sense of the need for guessing; it resorts to plausible reasoning to compensate for the limitations of its knowledge base. The decision-making knowledge is organized in a layered control structure which separates decisions about the planning problem from decisions about the planning process. The approach, termed meta-planning, exposes and organizes a variety of decisions, which are usually made implicitly and sub-optimally in planning programs with rigid control structures. This is part of a course of research which seeks to enhance the power of a problem solvers by enabling them to reason about their own reasoning processes.Meta-planning has been implemented and exercised in a knowledge-based program (named MOLGEN) that plans gene cloning experiments in molecular genetics.     

数控自动编程专家系统

本文简要地介绍了数控自动编程专家系统.其中包括:专家系统知识表示的形式;分层次的黑板结构;前向推理求解策略和相应的解释功能;系统针对不同类型的曲线组合,采用不同的独立的知识源(KS)进行处理.由于在知识的处理上采用编码技术,在前向推理求解策略中使用启发信息和“剪技”技术,提高了系统的时空效率.系统中的规划程序能自动规划切削路径.输出供数控车床使用的 NC 代码,并可在显示屏上进行图形显示和切削仿真.目前原型系统已经在 IBM-PC 和 Sun3/60计算机上利用FORTRAN 语言实现.