一个基于多重推理的遥感图片解译专家系统

本文研究了在图象模式识别过程中引入人工智能的知识学习、知识表达和知识推理的理论和技术,设计并实现了一个应用于遥感图片解译的计算机视觉专家系统。 为使系统具有较高的智能化程度,本文提出了一种新的推理方法——多重推理法,它具有处理某些不完全知识和错误知识的能力,并且推理过程所运用的部分知识(规则)是从已知样本中自动归纳学习生成的。     

支持索引词汇动态扩充的实例检索算法

实例检索是基于实例产品设计的关键。文中介绍了一种实例检索策略，支持实例索引词汇的动态扩充，并综合考虑“当前问题”、“用户选择实例”和“实例集中相似度更高的实例”的比较，提出了6条法则动态调整特征权重和特征属性相似度。所开发的“基于知识的机床夹具CAD系统”已在某大型航空企业应用于国家重点型号工程的研制，取得了满意的效果。     

空间飞行器推进系统的故障检测

文中采用基于人工智能条件下的专家系统知识，应用门限算法进行故障特性提取和相应的故障推理机制研究，在由大量小发动机组成的空间飞行器推进系统实验中进行应用，通过已有的实验数据，离线回放表明此方法具有实时检测功能，可以解决工程实际问题。     

飞机发动机燃料计量系统故障分析的一种方法

随着产品成本和复杂性的提高，故障模式影响分析已成为复杂系统设计过程中不可或缺的部分。但其有效性多年来一直存在争议，其主要原因在于采用以经验为主的定性推理法，分析繁琐，工作量大，导致很难确定每种故障模式的故障影响。本文从BIT设计的角度，以功能角色模型理论为基础，导出在反馈系统中的推理规则和故障模式影响分析方法。最后以喷气式发动机燃料计量系统为例，阐述对该系统进行故障分析的一般步骤。研究表明，本文提出的功能角色模型理论可有效提高故障模式影响分析效率。     

基于一种隶属函数的夹具相似度计算模型

针对夹具概念设计过程的复杂性和设计结果的不确定性等缺点,将基于实例推理技术应用于夹具概念设计过程当中。并根据夹具特征和概念设计中的模糊需求,选取三角函数作为隶属函数进行相似度计算,构建相似度计算模型,并将其应用于夹具实例推理过程中,最终实现简化夹具设计过程和提高设计效率的目的。     

Space,Language and Ontology: A Response to Davis

Abstract

Ernest Davis' article “Qualititative Spatial Reasoning in Interpreting Text and Narrative” discusses challenges that the interpretation of natural language appears to raise for the formalization of commonsense spatial reasoning. Davis finds these to be of “surprising logical complexity,” but also “erratic” in that they do not show a logical structuring of the problem space that could guide productive research. In this response I argue that much of the apparent lack of structure Davis laments is due to the very style of formal modeling he pursues. By augmenting logical considerations with substantial input from other disciplines and by adopting a heterogeneous and modular approach to formalization, I suggest that the problem space is by no means as ill-structured as Davis presents it.     

Qualitative Spatial Reasoning for Topological Map Learning

Abstract

In this paper we investigate the application of qualitative spatial reasoning methods for learning the topological map of an unknown environment. We develop a topological mapping framework that achieves robustness against ambiguity in the available information by tracking all possible graph hypotheses simultaneously. We then exploit spatial reasoning to reduce the space of possible hypotheses. The considered constraints are qualitative direction information and the assumption that the map is planar. We investigate the effects of absolute and relative direction information using two different spatial calculi and combine the approach with a real mapping system based on Voronoi graphs.     

On Embedding a Qualitative Representation in a Two-Dimensional Plane

Abstract

This paper discusses embedding in a two-dimensional plane a symbolic representation for spatial data using the simple objects, points (P), lines (L), circuits (C), and areas (A). We have proposed PLCA as a new framework for a qualitative spatial reasoning. In a PLCA expression, the entire figure is represented in a form in which all the objects are related. We investigate the conditions for two-dimensional realizability of a PLCA expression, and derive the relation that the numbers of objects in a PLCA expression should have. In this process, we use the well-known Euler's formula. We also give an algorithm for drawing the figure of the PLCA expression that satisfies this condition in a two-dimensional plane and prove its correctness. The algorithm generates a quantitative expression from qualitative expression.     

空间目标态势行为与事件本体设计与构建

针对空间目标态势威胁响应和预警研究不完善的问题，为实现空间目标行为和事件的智能推理、实时响应和主动预警，保障航天活动和空间利益，提出面向行为与事件的空间目标态势本体模型(BEO-SO2)。基于基本形式本体(BFO)，构建空间目标态势行为与事件本体模型。在统一时空框架下建立空间目标关系模型，实现空间目标行为执行和事件发生过程的动态推演。以空间目标碰撞威胁为背景，设计对象实体等级体系和碰撞威胁行为与事件要素，建立碰撞威胁推理规则，基于空间目标态势行为与事件本体进行实现、验证与展示。结果表明,空间目标态势行为与事件本体能够实现空间目标碰撞威胁的等级推理与预警，并指导进一步的空间活动，为航天任务与空间活动提供有效保障。     

Study on UAV Path Planning Approach Based on Fuzzy Virtual Force

This article proposes a novel fuzzy virtual force (FVF) method for unmanned aerial vehicle (UAV) path planning in complicated environment. An integrated mathematical model of UAV path planning based on virtual force (VF) is constructed and the corresponding optimal solving method under the given indicators is presented. Specifically, a fixed step method is developed to reduce computational cost and the reachable condition of path planning is proved. The Bayesian belief network and fuzzy logic reasoning theories are applied to setting the path planning parameters adaptively, which can reflect the battlefield situation dynamically and precisely. A new way of combining threats is proposed to solve the local minima problem completely. Simulation results prove the feasibility and usefulness of using FVF for UAV path planning. Performance comparisons between the FVF method and the A* search algorithm demonstrate that the proposed approach is fast enough to meet the real-time requirements of the online path planning problems.