一个基于C语言建造的专家系统

本文介绍一个基于C语言建造的诊断型专家系统以及系统的功能结构和设计方法。对C语言建造专家系统的应用理论、实用技术和优越性进行了探讨和研究。在实现策略、知识采集、知识描述、知识运行、模拟人类专家思维的推理技术等诸方面采用C语言进行程序设计,做了新的尝试,并取得了令人满意的结果。     

设计型专家系统在机械工程中的应用研究

专家系统是人工智能技术的一个重要分支,它是特定领域的一套计算机程序,具有类似专家工作时利用知识进行推理来解决问题的能力.它一般用以求解那些需要人类专家才能求解的高难度问题或不良结构的问题,为人类保存、使用、传播和评价知识提供了一条有效的捷径.文中主要介绍设计型专家系统在机械工程中的应用以及其基本结构、知识表示方法、推理方式及构建策略,然后介绍了它在齿轮传动设计中的应用.设计型专家系统的产生和发展必然会促进设计自动化技术在机械工程中的应用.     

设计型专家系统在机械工程中的应用研究

专家系统是人工智能技术的一个重要分支，它是特定领域的一套计算机程序，具有类似专家工作时利用知识进行推理来解决问题的能力。它一般用以求解那些需要人类专家才能求解的高难度问题或不良结构的问题，为人类保存、使用、传播和评价知识提供了一条有效的捷径。文中主要介绍设计型专家系统在机械工程中的应用以及其基本结构、知识表示方法、推理方式及构建策略，然后介绍了它在齿轮传动设计中的应用。设计型专家系统的产生和发展必然会促进设计自动化技术在机械工程中的应用。     

一个基于神经网络的专家系统

医疗专家系统主要使用基于知识的技术，其中的决策规则和策略来自于人类的专家。把这些知识和各种推理方法结合，可以建立一个模拟专家决策过程的系统。建立这样一个系统，需要经常与专家磋商，以获取专家的知识，因而需要大量的时间和精力。为此，本文提出直接从数据中提取有效的信息，即用神经网络提取隐含在大量数据中对医疗诊断有效的信息，继之与基于规则的知识，各种推理方法相结合，建立一个神经网络专家系统。     

纺织专家系统中知识与知识库的应用

专家系统是人工智能的一个分支，是一种模拟专家决策能力的计算机系统，知识库是系统的重要组成部分，是系统的核心。本文结合纺织工艺设计及管理专家系统介绍了基于知识的专家系统的概念和结构，对系统中知识的获取、存储方式予以说明．并对其知识的表示方法加以阐述。     

基于MVC模式的桥梁处治专家系统研究

专家系统(Expert system简称ES)是模拟人类专家解决问题的智能程序系统。专家系统的主要特征是有一个巨大的知识库,存储着某个专门领域的知识。在解决问题时,用户为系统提供一些已知数据,然后从系统中获得专家水平的结论[1-2]。目前专家系统已经应用到生活中的各个方面,本文着重研究了专家系统在在役桥梁中的应用,并且给出了模型建立方法、系统设计以及专家系统软件的设计流程[3]。最后将该系统应用到具体的实例中,实验证明在役桥梁专家决策系统具有良好的效果[4]。     

地质分析专家系统GAES的设计

地质分析是一项复杂的人类劳动,采用人工智能技术模拟人类专家活动,可以大大减轻人类的负担.因此,开发了一个地质分析专家系统GAES.该系统以黑板模型为基础,采用分布式系统结构,在中心节点的协调控制下,各普通节点相互合作,共同进行问题求解.在系统技术特点方面,解决了知识源分配、冲突消解和知识源筛选等问题,该系统具有求解效率高、可靠性强、通讯机制好等特点.     

提高基于规则专家系统效率的技术和方法

针对目前基于规则的专家系统效率不高的现状,从推理机设计、知识库设计、与其他先进技术结合等三个方面详细论述了提高这类专家系统效率的技术和方法,从而构建一个能真正反映人类专家水平的高效的专家系统。     

催化知识智能处理的初步研究

应用专家系统技术处理催化剂设计中大量非数值信息具有重要的实用价值。本文采用专家系统工具M.1,通过一个“离子浸渍吸附”子系统的原型构造实例,讨论催化知识构成和相应的处理方法。在此基础上,提出了结合传统的数值模拟技术构造催化专家系统的设想。     

知识--智能的源泉

“智能”就是系统在不确定环境下,为了恰当的行动,针对特定的目标而有效的地获取信息（知识）、处理信息（知识）和利用信息（知识）,从而成功的达到目标的能力。机器要想“智能”绝对离不开“知识”。
　　知识工程的概念是1977年美国斯坦福大学计算机科学家费根鲍姆教授(B．A．Feigenbaum)在第五届国际人工智能会议上提出的。他认为,知识工程是用人工智能的原理和方法为那些需要专家知识才能解决的应用难题提供求解的手段。因此,恰当运用知识的获取、表达和推理技术构成与解释知识系统,是设计知识系统的重要技术问题。费根鲍姆构建的“专家系统”,就是期待要在机器智能与人类智慧（专家的知识经验）之间构建桥梁。他期望中的专家系统是人类专家可以信赖的高水平智力助手：“是一个已被赋予知识和才能的计算机程序,从而使这种程序所起到的作用达到专家的水平。”     

A knowledge-based system for assessment of human physiological abilities in manual lifting tasks

The purpose of this paper is to develop and test an expert system for assessment of human physiological abilities in manual lifting tasks. The expert system was implemented on an IBM PC-XT personal computer. An example on how to utilize the expert system in designing manual lifting tasks from a physiological standpoint is given.     

一种基于系统相似性的智能设计的新方法

针对智能设计的复杂性 ,该文提出了一种以专家系统为设计平台 ,通过与典型实例进行相似比较、排队、映射建立设计原始模型 ,然后再进行二次设计的新方法 ,给出了该方法的数学描述和具体实现途径。对水电站装机方案设计的实践表明该方法切实可行 ,有着广泛的应用前景     

基于Agent的专家系统推理模型

针对传统专家系统推理模型结构在知识获取方面适应性差的现状,从系统科学的视角,运用复杂适应系统理论,对传统专家系统的结构及运行机制进行了改进.引入Agent来模拟人脑中的神经元,用来承载专家系统中相互作用的知识,然后,基于Multi-Agent之间的相互作用来构建复杂适应的专家系统推理模型.从而,将专家系统中的知识获取机制、知识库、推理机三者统一于由Multi-Agent进行相互作用的复杂适应系统之中.通过设计体育赛事申办决策专家系统的原型,进行了专家系统推理模型的验证.原型运行结果表明:基于Multi-Agent的专家系统推理模型结构能够有效地提高专家系统知识获取的适应性.这为研究更加接近人脑智能的专家系统提供了崭新的研究思路.     

面向问题分析与决策的专家系统

专家系统的根本目标在于为实际应用问题提供强有力的分析与决策能力。以人类通过长期实践活动总结的复杂问题分析与决策方法为指导思想,建立了以问题对象为核心、相关对象为问题主体、问题现象为表现形式、因果关系为问题变化驱动力、过程知识和原理知识为参考对象的面向问题分析与决策的专家系统。这种专家系统围绕应用领域中的问题构建知识库,而不是使用规则,所以得到的知识系统比较合理、清晰,不容易产生知识矛盾与冲突,有利于大型知识库的构建;同时,采用基于问题的推理,与人类的思维习惯相符合,可以大大提高推理效率;此外,开发这种专家     

How a real-life system stands up to the commandments

Many expert academics and practitioners have recommended some basic principles of good system design in organizational settings. This paper presents a case-study whose findings relate to many such principles. It is written with no other purpose than to serve as a reminder of these principles to those involved in the business of designing successful systems for human use.     

AN INTELLIGENT TUNING CONTROL TECHNIQUE

This paper argues that existing adaptive control algorithms are limited in many practical applications because they lack the inclusion of human intelligence, knowledge, reasoning skills, and human-machine interaction. To solve these problems, an Intelligent Tuning Control (ITC) technique is presented. The TTC technique combines expert system technology and adaptive control techniques and integrates numeric computation with symbolic reasoning. Since most physical systems have uncertainties to some extent, an inexact reasoning method is proposed in the knowledge-based component. The TTC system is implemented using a Lisp-based expert system shell on an IBM PC. The utility of the TTC technique has been positively confirmed by simulation results.     

A financial expert system demonstration for business students

Expert systems is a rapidly developing application of artificial intelligence technology for the capture and dissemination of human knowledge. A number of very practical implementations of knowledge bases have been achieved, using program shells which are quite accessible by people other than programmers. Since college business students have a high probability of encountering expert systems in the workplace, it is appropriate that their curriculum expose them to this expanding arena. This paper presents an expert system demonstration designed to provide a hands-on educational environment for allowing students to explore the capabilities of artificial intelligence in business organizations.     

Robot selection expert ‘Rose’

One of the major problems facing the robot user in the future will be his choice of the optimum robot for a particular task. What is needed is a highly automated robot selection system which will eliminate the human decision-making process. The system presented will be used when a robot is being considered to replace a human at a particular task, while the rest of the workplace remains fixed. The purpose of this paper is twofold; firstly, to demonstrate the knowledge required in making an optimum robot selection, and secondly, to provide a tutoral in designing an expert system using EXPERT. The paper will provide (1) the data base, (2) rules for transforming that data base, and (3) the control strategy that is necessary in implementing an expert system to perform the aforementioned task. The system will query the user as to the characteristics of the desired robot and the expert system will choose an optimum robot from the choices in the data base. The user will construct the environment in which the robot will be working by using 3-D modeling techniques. The user will choose from a menu and place the various objects which the robot will have to conform to. Thus, constraints such as maximum space available, can be stripped out of the 3-D drawing rather than having the expert system query the user for dimensions. One very good feature of such a system is that as new robots are developed their specifications can be added to the data base very easily.     

The role of expertise research and human factors in capturing, explaining, and producing superior performance

OBJECTIVES: The goal of this article is to identify some of the major trends and findings in expertise research and their connections to human factors. BACKGROUND: Progress in the study of superior human performance has come from improved methods of measuring expertise and the development of better tools for revealing the mechanisms that support expert performance, such as protocol analysis and eye tracking. METHODS: We review some of the challenges of capturing superior human performance in the laboratory and the means by which the expert performance approach may overcome such challenges. We then discuss applications of the expert performance approach to a handful of domains that have long been of interest to human factors researchers. RESULTS: Experts depend heavily on domain-specific knowledge for superior performance, and such knowledge enables the expert to anticipate and prepare for future actions more efficiently. Training programs designed to focus learners' attention on task-related knowledge and skills critical to expert performance have shown promise in facilitating skill acquisition among nonexperts and in reducing errors by experts on representative tasks. CONCLUSIONS: Although significant challenges remain, there is encouraging progress in domains such as sports, aviation, and medicine in understanding some of the mechanisms underlying human expertise and in structuring training and tools to improve skilled performance. APPLICATIONS: Knowledge engineering techniques can capture expert knowledge and preserve it for organizations and for the development of expert systems. Understanding the mechanisms that underlie expert performance may provide insights into the structuring of better training programs for improvingskill and in designing systems to support professional expertise.     

基于混合型专家系统的资信评估系统模型设计与实现

文章探讨将人工神经网络与专家系统结合应用于商业银行企业信用评估，并以一个混合型专家系统ECAMES（Enterprise Credit Assessment Mixed Expert System)为例，阐述了混合型专家系统模型的设计与实现。