OPTIMUM-AIV: A planning and scheduling system for spacecraft AIV

This paper presents a project undertaken for the European Space Agency (ESA). The project is developing a knowledge based system for planning and scheduling of activities for spacecraft assembly, integration and verification (AIV). The system extends to the monitoring of plan execution and the plan repair phases.

The objectives of the contract are to develop an operational kernel of a planning, scheduling and plan repair tool, called OPTIMUM-AIV, and to provide facilities which will allow individual projects to customize the kernel to suit its specific needs. The kernel shall consist of a set of software functionalities for assistance in the initial specification of the AIV plan, in the verification and generation of valid plans and schedules for the AIV activities, and in interactive monitoring and execution problem recovery for the detailed AIV plans. Embedded in OPTIMUM-AIV are external interfaces which allow integration with alternative scheduling systems and project databases.

The current status of the OPTIMUM-AIV project, as of May 1991, is that the architectural design of the system has been agreed on by ESTEC/ESA and detailed design and implementation is now underway, expecting a final delivery in October of 1991.     

基于案例与规则推理的故障诊断专家系统

设计并实现基于案例的推理(CBR)与基于规则的推理(RBR)的故障旋转机械诊断专家系统。采用CBR与RBR串行方式进行推理,优先通过案例匹配方式寻求诊断结果,在不适用情况下转入通用性规则推理,并将诊断结果反馈给知识库进行优化。应用结果表明,该系统诊断结果与实际相符合,且诊断速度快、针对性强。     

PREVISE: A knowledge-based system to support the preparation and verification of space operations procedures

This paper presents the Previse system for preparing and verifying operations procedures, developed in the frame of a project conducted by Matra Marconi Space for the European Space Agency ESA/ESTEC. This knowledge-based system supports an evolutive procedures language (syntax and vocabulary). It improves the efficiency of procedures preparation by providing powerful editing facilities, by checking the validity of the syntax used by procedures writers, and by automating the formatting task. It also provides a set of verification mechanisms allowing to detect different types of semantic errors in procedures.     

一种基于本体和CBR的电子政务项目审批决策支持系统

分析了将本体与CBR方法结合开发电子政务项目审批决策支持系统的优点,给出了该系统的总体框架和决策支持流程,着重介绍了基于本体的电子政务项目案例的组织和表示方法以及引入本体后案例检索过程中的相似度计算方法。实验结果表明,利用本体对项目案例包含的知识进行提取和表示,再利用这些知识对案例进行组织和检索,有效地提高了案例检索的查准率和查全率。     

基于范例推理的交通事故智能处理系统

介绍了一个基于范例推理的交通事故智能处理系统。首先给出了基于CBR的交通事故智能处理系统的总体框架。之后,对该系统中的核心部分：范例搜索、基于范例推理的综合推理模型、人机智能系统分别进行了讨论。     

基于案例推理系统中案例检索算法的探索

案例检索是基于案例推理系统的中心环节,目前应用最多的欧氏距离检索算法在实际应用中经常出现计算的相似度结果偏离工程实际的情况。文章利用一种归一化效用函数在最近邻法原理基础上提出一种改进的欧氏距离检索算法。实际工程应用结果说明,这种改进的算法不仅有效,而且简单实用。     

A hybrid metaheuristic case-based reasoning system for nurse rostering

In this paper we present a novel Case-Based Reasoning (CBR) system called CABAROST (CAsed-BAsed ROSTering) which was developed for personnel scheduling problems. CBR is used to capture and store examples of personnel manager behaviour which are then used to solve future problems. Previous examples of constraint violations in schedules and the repairs that were used to solve the violations are stored as cases. The sequence in which violations are repaired can have a great impact on schedule quality. A novel memetic algorithm is proposed which evolves good quality sequences of repairs generated by CABAROST. The algorithm was tested on instances of the real-world nurse rostering problem at the Queens Medical Centre NHS Trust in Nottingham.     

Application of AI in software and information engineering

Methodologies already exist for information systems analysis and design (e.g. SSADM, JSP, Merise, etc.) and supporting tools, namely, CASE (Computer Aided Software Engineering) and RDBMS (Relational Database Management System) and/or 4GL tools. All of these tools contain a data dictionary at the core of certain facilities.

In the underlying research and in this paper, the following questions need to be addressed:

• —How can the capability of a recently available data dictionary be enhanced with some knowledge-based modules?

• —What would be the architecture of such a system, based on the data dictionary of some CASE tools?

• —How can the informal and formal modelling approach information system design be combined?

• —What sort of knowledge-representation techniques would be suitable for the different tasks during the analysis and the design of the system?

The system outlined here would work as an intelligent assistant and workbench supporting the developer, but not as an automatic programming environment.     

CBR技术在西文图书分类中的应用

ＣＢＲ以完全不同于ＲＢＲ的方式在人工智能的众多技术中独树一帜。它尤其适用于难以总结出一般性规律，而又能提供大量历史事例的领域，该文着重介绍了以抽象层次法组织的，用类比法，联想检索的ＣＢＲ系统；西文图书分类专家系统ＦＣＣＢＲ的工作机制。     

基于事例推理的电路诊断技术研究

本文首先简要介绍了基于事例推理(CBR)和基于规则推理(RBR)的优缺点，其次建立了一个CBR和RBR相结合的电路故障诊断系统，最后说明了该系统的基本结构及设计过程。     

Multi-Modal Reasoning medical diagnosis system integrated with probabilistic reasoning

In this paper, a Multi Modal Reasoning (MMR) method integrated with probabilistic reasoning is proposed for the diagnosis support module of the open eHealth platform. MMR is based on both Rule Based Reasoning (RBR) and Case Based Reasoning (CBR). It is not only applied to the identification of diseases and syndromes based on medical guidelines, but also deals with exceptional cases and individual therapies in order to improve diagnostic accuracy. Moreover, a new rule expression frame is introduced to deal with uncertainty, which can represent and process vague, imprecise, and incomplete information. Furthermore, this system is capable of updating the attributes of rules and inducing rules with a small data sample.     

ATOS — An AI-based space mission operations system

Artificial Intelligence is generally recognised as one of the key technologies for future spaceflight, and a number of ambitious applications for on-board use have been proposed already. Such applications still require a good deal of basic research and development, but on-ground applications could make an impact already in the medium term, and will for some time represent the major part of AI use for space missions.

ESA has started the development of a future integrated and mission-independent spacecraft control data processing system called the Advanced Technology Operations System (ATOS) at the European Space Operations Centre, which will employ artificial intelligence techniques in supporting the operations staff during all mission preparation and implementation phases, in order to cope reliably with complex mission operations and to achieve optimal efficiency in the use of human resources.

ATOS will consist of a number of knowledge based software modules, such as

• Automated mission planning

• Automated operations preparation

• Computer assisted operations

• Advanced operator training,

centred around a Mission Information Base configured for the particular satellite mission, the common data repository for all information required to conduct the mission and operate the spacecraft.

The Mission Information Base will, in addition to numerical data presently found in conventional spacecraft control systems, contain a large amount of ‘knowledge’ about the spacecraft and its mission, which is currently available only in paper documents or embedded in software. It will be implemented as a physically and logically distributed set of databases each representing a particular field of mission information, such that the knowledge can be dynamically shared between different intelligent spacecraft control applications.     

基于CBR的智能答疑系统范例库的研究与实现

CBR方法是近年来人工智能领域先进和实用的方法,范例库作为智能答疑系统的核心部分,为进一步提高答疑系统的智能性,将CBR引入范例库,研究了基于CBR的智能答疑系统范例库的构建方法,对聚类方法和遗传算法在CBR范例库的检索、维护中的应用进行了分析、测试。通过CBR范例库的建立、检索和维护有效地提高了智能答疑系统的性能、进一步提高了智能答疑系统的智能性。     

基于SOA的多CBR系统应用集成研究

针对单一应用的案例推理（CBR）系统在集成基于经验的隐性知识时存在固有局限性,设计出基于面向服务的体系结构（SOA）的多CBR系统应用集成框架和集成系统的平台体系结构。该集成框架和平台体系结构在分析CBR系统演化及应用集成模型库的基础上,结合SOA封装推理模型和推理流程,开发集成系统。该系统在试点应用中,实现企业内外多维隐性知识的集成和共享。     

MRA-based revised CBR model for cost prediction in the early stage of construction projects

Accurate prediction of construction cost in the initial phase of a construction project is critical to the success of the project. Accordingly, many researchers have proposed various methodologies for predicting the cost in the initial phase with the use of limited information. This study was aimed at improving the prediction performance of a cost prediction model based on the Case-Based Reasoning (CBR) technique, which has recently become widely used. Toward this end, an improved CBR model that uses the Multiple Regression Analysis (MRA) technique in the revision phase of the CBR technique was developed. To verify the prediction performance of the proposed model, a case study was performed on 41 business facilities and 99 multi-family housing projects. The results showed that the prediction performance of the revised CBR model for business facilities and multi-family housings improved by 17.23% and 4.39%, respectively, compared to that of the existing CBR model. The proposed MRA-based revised CBR model is expected to be useful in estimating the construction cost in the initial phase of a project.     

Case-Based Reasoning System and Artificial Neural Networks: A Review

In this survey paper, the-state-of-art of the connectionist model (i.e. Artificial Neural Network (ANN)) based methodology for a Case-Based Reasoning (CBR) system design is discussed. Special emphasis is laid on how the ANN can advance CBR technology by building an ANN-based CBR system, or integrating itself as a component within a CBR system. Several ANN models proposed for constructing a CBR system and for solving some special issues involved in a CBR process are described. The main characteristics of each model are analysed, and the advantages and limitations of different models are compared. Also, future research directions are outlined.     

Hypermedia based application for space shuttle processing

In order to successfully complete routine procedures for the Space Shuttle, personnel in the Orbiter Processing Facility (OPF) at the Kennedy Space Center (KSC) are continuously checking numerous specifications and process procedures. Employees are not only faced with tedious searches for documents that frequently reference other drawings and documents, but they must correctly interpret the vast amount of information associated with each task in a timely manner.

Advances in Hypermedia and Database Management provide a solution for this problem. In a hypermedia environment, pertinent information is relationally retrieved and presented via a multitude of media avenues such as text, full-motion video, photographs, audio, and graphics display. This greatly reduces both the documentation search time and the confusion of interpretation resulting in a substantial increase in productivity.

In this paper we discuss the experience of developing a pilot project currently being conducted at the University of Central Florida. Hypermedia technology is being applied in support of Thermal Protection System (TPS) operations at KSC. The system involves the integration of several shuttle specification databases, video display of processes being performed, graphical display of drawings and specifications, and an optional audio output to provide the user with a free-hand environment if warranted.     

Internet下智能协同DSS模型实现技术

本文在介绍了作者提出的基于Ｉｎｔｅｒｎｅｔ环境下智能协同决策支持系统模型后,详细描述了该模型的原型系统－贫血病诊断系统的实现技术,通过它反映了该模型的应用前景。文中还对智能决策代理编制、基于事例的推理等方面进行了描述。     

Robot simulator in TIPS/Geometric Simulator

With the growth of factory automation, the need for off-line robot programming is increasing rapidly. Off-line programming requires a robot simulator. This is the reason for the development of a TIPS/GS (Geometric Simulator), accompanied by a robot simulator. TIPS/GS has been developed as a project in the TIPS Research Association. The goal of this project is to extend the functions and applications of the solid modeler TIPS-1. Four simulators (i.e. the assembly simulator, engineering, NC simulator and robot simulator) have been developed for these extended applications.

The robot simulator described in this paper has the following special features:

• • When a robot motion is prescribed by the VAL-G language, the result can be seen on a CRT display in several patterns.

• • High-speed dynamic display which can almost keep up with real-time movements.

• • A shaded as well as wire-frame picture is used for the high-speed display entioned above.

• • Supported by the solid modeler, any robot and environment can be used with this system.

• • The preparation of a precise interference checker based on an analytical methods.

This paper is a report on the development of the robot simulator.     

ARIANEXPERT: A knowledge based system to analyze ARIANE's mission data

The ARIANE launcher post mission analysis is done at ARIANESPACE. This activity is called the ‘level 0 post flight analysis’ (PFA) and is carried out after each launch by about 60 engineers who are working together under the leadership of ARIANESPACE.

The PFA is one of the most critical of ARIANE operations, for several reasons:

• - The launch rate (8 a year for ARIANE 4) leaves a very short time to carry out all the verification work. Moreover, the PFA is a mandatory step before authorizing the next launch.

• - The complexity of the ARIANE launcher results in a very high demand on the PFA engineers. Moreover, there are problems of availability of people with relevant expert knowledge (characterized by a substantial staff turn-over during the 10 year life duration of ARIANE 4) which could potentially result in errors or omissions.

It is very important to be able to take into account the experience of the preceding flights and to record the results and the knowledge accumulated for each launch.

• - The quality and the reliability of the PFA mainly depends on the accessibility of data and on the used methodology.

Because the PFA is still largely done manually, and does not benefit from improved methodologies and advanced technologies providing computerized support for data processing and diagnosis, ARIANESPACE has sponsored MATRA ESPACE for the development of a knowledge based system, called ARIANEXPERT, for supporting the PFA activity. This system combines AI techniques and numerical analysis techniques, together with advanced graphical capabilities.

A prototype has been delivered in April 1990 and has been used since 6 months by ARIANESPACE during real PFAs. Several lessons have been drawn from this operational experience and are described in this paper. They concern:

• - The utility and justification of the use of AI techniques mostly coming from the explanation capabilities and the stress put on capturing the expert knowledge.

• - The difficulties associated with the integration of such systems in the exploitation of ARIANE due to the introduction of very new tasks.

• - The user point of view which evolved from reluctant to convinced.