关于实时专家系统及其实现方法的探讨

实时专家系统是为了解决具有实时性的问题而构造的专家系统，它除了具有一般专家系统的结构和特点外，还包含了相应的实时控制机制。本文提出了三种实现方法，并讨论了一个具体的ＲＥＳＣ转炉吹炼控制实时专家系统。     

转炉吹炼实时控制专家系统RESC的设计与实现

本文分析了一个转炉吹炼实时控制专家系统ＲＥＳＣ的设计与实现，在开发中系统采用了专家系统技术，实时控制技术和吹炼控制模型相结合的方法，这里着重讨论了ＲＥＳＣ的系统结构，知识表示与推理机制，吹炼控制机制，网络通信以及主析实现技术。     

非线性欠驱动系统的实时控制

提出了一种基于专家系统及变步长预测控制的实时非线性系统控制方法.变步长一步 预测的使用不但打破了原有采样时间对预测控制最小步长的限制,而且有效地避开了复杂的非 线性推导.结合系统控制目标,设计了一类新的系统优化性能指标函数.利用专家系统实时地对 系统优化性能指标当中的控制参数进行修正,有效地提高了滚动优化的效率,从而实现对复杂 非线性系统的实时控制.利用这种方法,有效地实现了对三级倒立摆的稳定实时控制.     

基于神经网络的实时专家控制系统及其PTA工业应用

以精对苯二甲酸结晶过程为研究对象。提出一种基于神经网络模型的实时专家控制系统．该方法利用神经网络建模技术获取对象的机理知识,通过对影响模型特性的多个变量进行分析,自动得到常规专家控制系统难于获取的定性、定量知识,并按分级递阶的启发式搜索机制,实现了对工业过程对象的实时控制．实际应用表明：该方法不但克服了以往专家系统知识获取的瓶颈,而且有效实现了人机对话的功能,便于现场操作和更改专家知识库,为化工过程的多变量控制提供了新的思路．     

实时控制专家系统推理机的设计

本文以炼钢吹炼控制专家系统为背景，提出了一种实时控制专家系统推理机的设计方法，着重介绍了模糊推理的主要策略，以及实时推理的设计思想。     

基于神经网络的控制专家系统开发环境的实现

为了充分发挥专家系统与人工神经网络技术两者的优势，支持高效实用的结合型控制专家系统的开发，本文首次提出并在微机上实现了一个以神经网络为核心的控制专家系统开发环境（ＮＥＳＤＥＶ）。可辅助控制领域的工程技术人员，方便、快速、高效地开发基于神经网络的实时控制专家系统。本文将叙述该开发环境的系统结构，规则库－神经网络翻译算法，人机接口技术等内容。     

基于虚拟仪器技术的故障诊断专家系统的实现

随着计算机技术的发展,智能技术在测试领域显得越来越重要,在传统的测试系统中使用专家系统技术成为测试系统的发展趋势;文章通过对专家系统原理的介绍,提出了将专家系统技术引入测试领域的可行性,并分别介绍了基于虚拟仪器的测试系统软件设计方法和基于规则的专家系统软件设计方法,并给出了故障诊断专家系统的实现方法和实时故障专家系统的设计方案;经使用后,认为专家系统技术将有助于智能化故障诊断的实现,并且可提高测试技术的智能化程度。     

工业生产系统的故障监控和诊断实时专家系统开发工具的研究

本文从工业生产系统的现场需要出发，将故障监控技术，诊断技术和维修技术融为一体，提出了采用主从式实时专家系统技术来实现故障监控和诊断的新方案，并相应研制了工业生产系统故障监控和诊断实时专家系统的开发工具，利用该开发工具，开发了直流提升机故障监控和诊断的实时专家系统，实验表明，该开发工具支撑环境良好，知识获取功能较强，开发应用方便，开发后的故障监控和诊断实时专家系统，不仅满足故障监控和诊断的实时性要求     

仿生机器鱼动力电源管理专家系统设计

提出一种基于专家系统控制策略,能监控电池充电、放电并实现电池单元自动切换控制的直流动力电源管理专家系统。该动力电源管理专家系统软件采用模块化设计,硬件采用光电隔离手段。将动力电源管理专家系统应用在SPC3-UUV仿生机器鱼平台上,试验结果表明该系统在机器鱼长航程巡游过程中运行良好,实现了电源的科学管理和实时控制,有效提高了可靠性。     

VC++6.0下用中断实现转速实时测量

本文介绍了在Windows98下利用VxD技术编写中断处理程序．并且利用VC 6．0的多线程技术实现转速的实时测量，并实现了数据存储、再现功能，可用于数据采集，实时控制等领域。     

基于G2的实时生产调度系统研究

该文以实时专家系统工具G2作为生产调度的平台 ,通过对G2中的知识表达、知识库管理以及实时推理等关键问题的探讨 ,以某钢厂炼钢车间调度为例 ,建立调度的复合知识模型 ,最终开发一个调度的原型系统 ,并给出仿真结果     

一种图象理解的专家系统工具语言

为了在实时图象处理系统中,实现并行环境下基于黑板模型的多知识源协同求解,从知识表示、推理方式、控制机制等方面介绍了智能所自行研制的一种图象理解专家系统工具语言--V语言（V.3版本）。该语言具有多种知识表示,采用数据驱动与模型驱动相结合的推理方式,由黑板对推理进行控制,知识库由多个知识源（分别存在有关模型的静态知识和各种图象处理算法）组成等特点。最后给出了针对水上桥梁一类的图象进行理解的具体实例。     

The use of knowledge acquisition in instructional design

Expert systems and knowledge based systems have emerged from “esoteric” laboratory research in Artificial Intelligence (AI) to become an important tool for approaching real world problems. Expert systems are distinctive in that they are designed to address problems in a similar manner and with similar results as a human expert. The basic structure of an expert system is comprised of three functionally separate components: (a) knowledge base, which contains a representation of domain related facts; (b) means of knowledge base use to solve a problem, inference mechanism; and (c) working memory, which records the input data and progress for each problem. Given the complexity and cost of expert system construction, it is imperative that system developers and researchers attend to research issues which are critical to knowledge engineering. These questions can be categorized according to the parts of an expert system: (a) knowledge representation; (b) knowledge utilization; and (c) knowledge acquisition. A knowledge acquisition procedure is presented which displays the relationship between subject matter expert expertise consisting of declarative knowledge, procedural knowledge, heuristics, formal rules, and meta-rules. The knowledge engineer uses one or a combination of elicitation methods to gather relevant data to eventually build the components of an expert system. Further explained are the acquisition methods: (a) structured interview; (b) verbal reports; (c) teaching the subject matter; (d) observation; and (e) automated knowledge acquisition tools. The paper concludes with a discussion of the future research issues concerned with using knowledge mapping and task analysis vs. knowledge acquisition techniques.     

Experimental results from parallel backward-chained expert systems

There are many applications which may be done by an expert system in real time, if the system is capable of real time response. the first Lisp- and Prolog-based expert systems have typically been too slow for real time response. This has lead to an effort to use other languages, the development of fast pattern matching techniques, and other methods of improving the speed of expert systems. Another approach to developing faster expert systems is to make use of the emerging parallel processing computer technology. A further use for parallelism is to allow reasonable response time for large knowledge bases. the size of knowledge bases may become as large as 20,000 chunks of knowledge (and more) in the near future in medical and space applications. This article describes the use of parallel processing in the EMYCIN backward chained rule-based model. Performance on two examples of shared memory multiprocessors is presented and contrasted with earlier simulations.     

A Software Tool for Constructing Traditional Chinese Medical Expert Systems

It is an urgent task to hnplemeut a lot of expert systems to capture the valuable expertise ofexperienced doctors of traditional Chinese medicine.In order to meet the needs,a software tool isdeveloped.It features a unified diagnosis model,a specially designed knowledge representationlanguage and an efficient but effective inference engine.To implement an expert system,it isonly necessary to input the expert's knowledge expressed in knowledge representation languagewithout the design of any additional software.The time and effort required for implementing anexpert system are thus greatly saved.The software is very compact and can run onmicrocomputers e.g.IBM-PC/XT.Two traditional Chinese medical expert systems have beensuccessfully implemented with the tool.     

Prolog versus Kee — A case study

The selection of the software development tool for the development of an expert system is a difficult and often disputed decision. This paper describes a comparison of a knowledge engineering tool, Kee, and a general purpose language, Prolog, on concrete and real life example from AGATHA, an electronic circuit board diagnosis expert system.Prolog is a high-level programming language with flexible and powerful inference mechanisms. Kee is a big tool that supports a frame-based knowledge representation, an object-oriented programming style and a built-in rule system. It also offers a window environment suitable for rapid development of user-interface prototypes.Prolog's representation is more succinct, implicit and uses problem specific predicates and therefore leaves more room for personal programming styles. Kee is more verbose, explicit and uses standard templates. The maintainability of a Prolog implementation relies heavily on good documentation. In Kee, the unavoidable ‘escapes to Lisp’ require a maintainer to be fluent in Kee and Lisp.Both Prolog and Kee require a considerable investment in learning time.     

基于专家系统的CODOG动力系统实时诊断的研究

讨论了运用专家系统ＣＬＩＰＳ结合高级编程语言Ｖｉｓｕａｌ Ｂａｓｉｃ实现实时故障诊断的一种方法。利用高级语言开发应用程序及专家知识库,并通过调用ＣＬＩＰＳ动态链接库,实现ＣＯＤＯＧ动力系统的状态监测、故障诊断。     

KNOWLEDGE TRANSFORMATION

The transformation of knowledge bases from one expert system tool to another raises several issues: transformation of the syntax, adaptation to a different inferencing procedure, conservation of the knowledge, testing and evaluation of the transformed knowledge base, and its comparison to the original. The solutions for these issues were developed during the transformation of six expert systems originally developed with PC+, a parameter-driven expert system tool and one expert system developed with KES-HT, a hypothesis and lest expert system tool, into a forward-chaining pattern-matching tool: CLIPS.     

Expert systems designed for maintenance

Constraints for knowledge are proposed as a tool for constructing maintainable expert systems. A simple taxonomy of knowledge constraints is given. It is shown that a special class of knowledge constraints, coupled with the referential integrity constraint, together provide the necessary foundation for a mechanism to substantially automate the expert systems maintenance process provided that the knowledge has been normalised. The normalisation of knowledge is described and its inherent value to the maintenance process is illustrated. An experimental expert systems design and maintenance tool based on this approach has been built.