系统级故障诊断的研究现状与发展前景

随着大数据时代的到来,人们对于计算机系统的稳定性要求日益增高,如何快速而准确地找出系统中的故障点,成为了人们的研究热题,对系统级故障诊断算法的研究逐渐受到了人们的重视。本文首先对现有的系统级故障诊断算法进行了分类,进而阐述了系统级故障诊断算法的近期主要研究成果,最后预测了该领域的未来研究方向与发展前景。     

Autonomous power expert system

The Autonomous Power Expert (APEX) system has been designed to monitor and diagnose fault conditions that occur within the Space Station Freedom Electrical Power System (SSF/EPS) Testbed. The APEX system is being developed at the NASA Lewis Research Center by the Space Electronics Division (SED) in conjunction with the Space Station Directorate and Power Technology Division (PTD). APEX is designed to interface with SSF/EPS testbed power management controllers to provide enhanced autonomous operation and control capability.

The APEX architecture consists of three components: (1) a rule-based expert system, (2) a testbed data acquisition interface, and (3) a power scheduler interface. Fault detection, fault isolation, justification of probable causes, recommended actions, and incipient fault analysis are the main functions of the expert system component. The data acquisition component requests and receives pertinent parametric values from the EPS testbed and asserts the values into a knowledge base. Power load profile information is obtained from a remote scheduler through the power scheduler interface component.

This paper will discuss the current APEX design and development work. Operation and use of APEX by way of the user interface screens will also be covered.     

Maintenance strategies for PCM circuit switching

During all the system design phase of an SPC switching system, a considerable effort is devoted to maintenance, both from a hardware and software point of view. The maintenance phases include fault detection, fault analysis (e.g., identification of the faulty security block within the switching system), fault isolation, fault reporting, fault localization, fault clearance, and restoration to service with the eventual requalification and reinitialization of the repaired security block. The paper mainly discusses fault detection and fault analysis strategies with specific reference to PCM digital switching systems. Different means leading to fault detection are presented with reference to central control, network access devices (scanners, drivers, markers), and digital switching network (duplicated or not duplicated). These means include automatic on-line tests (monitoring and routining), on-demand on-line tests, and alarm handling. Fault analysis can be accomplished by means of a deductive or a statistical method. As the latter seems more attractive, three basic methods of statistical fault analysis are presented. They use, respectively, two counters (operation and fault counter) per security block; one fault counter per security block; one "historical" fault stack, in which all the identities of security blocks involved in faulty operations are stored. The above fault analysis strategies are compared mainly in terms of core memory occupancy, processor time, and software complexity.     

Intelligent fault isolation and diagnosis for communication satellite systems

NASA-Lewis Research Center recently completed the design of a Ka-band satellite transponder system, as part of the Advanced Communication Technology Satellite (ACTS) System. To enhance the reliability of this satellite, NASA funded The University of Akron to explore the application of an expert system, in order to provide this satellite with autonomous diagnosis capability. The result of this research was the development of a prototype diagnosis expert system, called Fault Isolation and Diagnosis EXpert (FIDEX). FIDEX is a frame-based system that uses hierarchical structures to represent such items as the satellite's subsystems, components, sensors, and fault states. This overall frame architecture integrates these hierarchical structures into a lattice that provides a flexible representation scheme and facilitates system maintenance. To overcome limitations on the availability of sensor information, FIDEX uses an inexact reasoning technique based on the incrementally acquired evidence approach that was developed by Shortliffe during his MYCIN project. The system is also designed with a primitive learning ability through which it maintains a record of past diagnosis studies. This permits it to search first for those faults that are most likely to occur. And finally, FIDEX can detect abnormalities in the sensors that provide information on the transponder's performance. This ability is used to first rule out simple sensor malfunctions. The overall design of the FIDEX system, with its generic structures and innovative features, makes it an applicable example for other types of diagnostic systems. This article discusses these aspects of FIDEX, and illustrates how they can be applied to fault diagnostics in other types of space systems.     

Development of an expert system prototype for determining software functional requirements for command management activities at NASA goddard

At NASA Goddard, the role of the command management system (CMS) is to transform general requests for spacecraft operations into detailed operational plans to be uplinked to the spacecraft. The CMS is part of the NASA Data System which entails the downlink of science and engineering data from NASA near-earth satellites to the user, and the uplink of command and control data to the spacecraft. Presently, it takes one to three years, with meetings once or twice a week, to determine functional requirements for CMS software design. As an alternative approach to the present technique of developing CMS software functional requirements, an expert system prototype was developed to aid in this function. Specifically, the knowledge base was formulated through interactions with domain experts, and was then linked to an existing expert system application generator called “Knowledge Engineering System.” Knowledge base development focused on four major steps: (1) develop the problem-oriented attribute hierarchy; (2) determine the knowledge management approach; (3) encode the knowledge base; and (4) validate, test, certify, and evaluate the knowledge base and the expert system prototype as a whole. Backcasting was accomplished for validating and testing the expert system prototype. Knowledge refinement, evaluation, and implementation procedures of the expert system prototype were then transacted.     

Built-in-test in support system maintenance

This article looks at the state of BIT (built-in-test) in test and measurement instruments, explains BIT's effect on system readiness, and presents ideas on how to improve BIT technologies and standards. The following topics are discussed: circuit level BIT (built-in self-test); module level and line replaceable units (LRU); system-level self-contained testing; instrumentation BIT history; BIT fault coverage and isolation in support system maintenance; BIT development process; pitfalls and limitations of BIT; BIT effectiveness in support system maintenance and availability.     

Redex: The ranging equipment diagnostic expert system

This paper describes REDEX, an advanced prototype expert system that diagnoses hardware failures in the Ranging Equipment (RE) at NASA's Ground Network tracking stations. REDEX will help the RE technician identify faulty circuit cards or modules that must be replaced, and thereby reduce troubleshooting time. It features a highly graphical user interface that uses color block diagrams and layout diagrams to illustrate the location of a fault. A semantic network knowledge representation technique was used to model the design structure of the RE. A catalog of generic troubleshooting rules was compiled to represent heuristics that are applied in diagnosing electronic equipment. Specific troubleshooting rules were identified to represent additional diagnostic knowledge that is unique to the RE Over 50 genetic and 250 specific troubleshooting rules have been derived. REDEX is implemented in Prolog on an IBM PC AT-compatible workstation. Block diagram graphics displays are color-coded to identify signals that have been monitored or inferred to have nominal values, signals that are out of tolerance, and circuit cards and functions that are diagnosed as faulty. A hypertext-like scheme is used to allow the user to easily navigate through the space of diagrams and tables. Over 50 graphic and tabular displays have been implemented. REDEX is currently being evaluated in a stand-alone mode using simulated RE fault scenarios. It will soon be interfaced to the RE and tested in an online environment. When completed and fielded, REDEX will be a concrete example of the application of expert systems technology to the problem of improving performance and reducing the lifestyle costs of operating NASA's communications networks in the 1990's.     

VP—Expert及其不确定性推理的实现

VP-Expert是一种能在IBM PCXT/AT及其兼容机上运行的具有双向推理的骨架型专家系统开发工具.本文简介VP-Expert的主要特点和工作原理,并讨论了用VP-Expert实现不确定性推理的技术.     

Evaluation Mo del and Method of Margin in Electromagnetic Environmental Effects for Complex Systems

Margin is an important index in the control of Electromagnetic environmental effects (E3) and Electromagnetic compatibility (EMC) design for systems. How to define and verify the E3 margins of complex systems such as ships and airplanes is a difficult problem. A new method of system-level E3 margin evaluation is proposed. Based on the theory of fault tree, the evaluation model of system-level margin is constructed. The complex system function is transformed into the equipment and subsystem that affect the function, and the relationship between margin of system-level and equipment is established. The change from margin of equipment to system-level margin is realized. According to the action process of Electromagnetic environment (EME), the verification and evaluation methods of EME domain, response domain and effect domain are put forward. The margin calculation formula of EME domain and typical electromagnetic energy coupling response are deduced. The problem of margin evaluation for equipment under different input parameters is solved. A typical application example is given. The verification test scheme is designed. The methods of electromagnetic energy radiation and injection are adopted. The system-level margin is analyzed by the data obtained from the effective test verification. The results show that the model and method are reasonable and feasible.     

智能烟草工厂底层物联设备远程检修系统设计

针对烟草工厂底层物联设备检修体系落后,设备检修效率低的问题,设计智能烟草工厂底层物联设备远程检修系统.采集现场设备运行数据,并将采集的数据存储至设备故障经验知识库,应用故障专家子系统调用设备故障经验知识库的数据信息,实时监控现场设备运行状态;利用故障树最小割集的故障诊断方法,诊断智能烟草工厂底层物联现场设备,依据诊断结...     

Modellbasierte Diagnose — Überblick und technische Anwendung

Model-based diagnosis deals with a set of methods for finding faults in (usually technical) systems by examining the way these systems operate when functioning correctly, instead of using the classical “expert system” approach of painstakingly collecting all individual fault cases. The types of components occurring in a problem domain have their behavior described in a generic catalogue and can then be simply combined to describe any system from that domain. If faulty behavior is observed, a general solution algorithm can be applied to identify the set of components whose misbehavior explains the fault.     

基于故障树分析的雷达故障诊断专家系统设计

快速进行故障诊断是保证雷达装备综合保障能力的前提,建立一套故障诊断专家系统来不断总结专家经验,从而使维修工作更加科学、有效。以某舰载搜索雷达系统为例,给出了雷达系统故障树的构建方法、故障诊断专家系统知识库的建立及推理机的设计,并简要介绍其实现方法。     

综合化CNI设备测试系统的设计

针对综合化通信导航识别( ICNI)设备与传统CNI设备在体系架构、信息传输方式的差异以及现有测试方法的不足,设计了一种综合测试系统。该系统借鉴综合模块化设计思想实现专用模拟器模块化,采用专家系统实现自动测试,通过机内测试( BIT)提高机内故障诊断能力,不仅满足ICNI设备功能指标测试要求,也为故障检测及诊断提供了方法。该系统可对ICNI设备全频段覆盖性自动测试,故障隔离率达到100%,是验证ICNI设备性能的有效技术手段。     

基于知识图谱的信号智能运维故障树模型实现方案

城市轨道交通信号系统存在设备繁多、日常报警和故障数据量大、种类繁杂等特点,智能运维故障处置功能急需新的技术来实现。文中提出了一种基于知识图谱的信号智能运维故障树模型实现方案,针对现有故障数据建立信号系统专家知识库,使用图数据库进行存储,界面则使用故障树模型对专家系统进行可视化输出,为日常设备维护、报警分析和故障排查等提供了技术支持。     

一种电子设备故障库的设计

故障库是专家系统的核心,体现着专家系统水平的高低。从故障库技术结构,构建方法出发,对电子设备多故障诊断信息进行归纳、总结,针对某电子设备构建了一种故障库并对其推理过程进行设计。该方法为电子装备故障诊断快速性和准确性上提供了一条有效途径。     

雷达便携式维修辅助系统软件设计与实现

针对外场雷达设备的故障维修,文中提出了便携式维修辅助系统（PMA）平台的软件设计与实现方法,简要介绍了PMA的背景和意义。在此基础上给出了它的软件框架结构,并且对交互式电子手册,基于专家系统的故障诊断和远程通信等关键内容进行了研究,并通过雷达的外场应用对系统进行了验证。     

Avionics Maintenance 2010

This paper postulates an avionics maintenance concept for the year 2010. The concept recognizes the change that is occurring in new systems toward internal fault isolation using built-in test. Currently, fault isolation data are held in the failed system or within the aircraft computer for subsequent analysis by maintenance personnel. Under the Maintenance 2010 concept, fault data would be analyzed as soon as possible during a mission to identify replacement components needed. A data link from the aircraft to a ground maintenance support system is proposed to permit further diagnosis of faults and to expedite preparation for immediate corrective maintenance action on the flight line when the aircraft returns. The concept is designed to eliminate aircraft down time while awaiting maintenance and thereby improve operational readiness.     

Knowledge-based maintenance in networks

A prototype expert system for maintenance of Northern Telecom's DMS-family digital switches is presented. The prototype is based on using product documentation and experience obtained from craftspeople and field technical support to create the knowledge base for an expert system which diagnoses and chooses corrective actions for DMS-100 problems. Operation of the expert system, and how this has changed since the initial prototype was completed, implementation of the system, and further development of the system in a network maintenance role is also discussed