【作者】 黄增双；

【导师】 李斌； 叶伯生；

【作者基本信息】 华中科技大学 ， 机械电子工程， 2006， 硕士

【摘要】 本文首先分析了当前设备故障智能诊断技术、设备远程监控的发展现状。针对现代数控设备故障的需求,详细介绍了基于规则推理(RBR)及基于案例推理(CBR)的设备故障诊断技术,并将其与数控设备故障相结合,提出了基于RBR及CBR的数控设备故障诊断策略。对基于规则的推理的数控设备故障诊断,提出了将产生式规则与故障树相集合的诊断策略并给出其详细的实现思路;对基于CBR的数控设备故障诊断,提出了最近相邻法检索匹配策略;对RBR与CBR混合诊断的策略作了初步的探讨。随着计算机网络技术的飞速发展,实现设备的远程监控和故障诊断已经成为可能。本文又以武汉华中数控有限公司生产的华中数控系统(网络版)为平台,结合已经搭建的基于网络环境的数控设备故障智能诊断系统框架,对数控设备故障诊断技术做了详细深入的探讨,对于诊断系统中的现场服务器,本文着重分析了其中应用的RBR和CBR数控设备诊断技术。同时,本文对现场服务器的各功能模块参数模块、信息采集模块、显示模式模块、档案维护模块、诊断工具模块、远程服务模块、用户管理模块、帮助模块作了一定的说明并给出了其设计运行界面。该诊断系统采用两种软件设计模式即客户端/服务器(C/S)、浏览器/服务器(B/S)模式,采用两种诊断模式:专家系统辅助诊断及远程专家诊断,系统采用多种诊断方式如基于规则推理的诊断、基于案例推理的诊断及远程专家在线诊断等。更多还原

【Abstract】 In this thesis, the up-to-date development of device fault intelligent diagnosis and remote monitoring technologies are firstly described in detail. In order to meet the demands of modern NC device fault diagnosis, the Rule-Based Reasoning and Case-Based Reasoning device fault diagnosis technologies are introduced with its particular reference to NC device default. Based on that, the Case-Based Reasoning and Rule-Based Reasoning strategies are proposed for NC device fault diagnosis, and the method of production rule combined with fault tree analysis is constructively suggested for Rule-Based Reasoning NC fault diagnosis system, and nearest neighbor retrieval method is also suggested for Case-Based Reasoning NC fault diagnosis system. In addition, a reasoning method combining RBR with CBR is probed for NC device fault diagnosis.With the rapid development of computer network technology, it has been possible to realize remote monitoring and fault-diagnosis of device. In this thesis, Huazhong NC device (net version) is taken as the research object and has been used as a partly–developed intelligent diagnosis system based on computer network. The field server in this expert system is developed, its functional modules such as parameter module, information collecting module, display model module, archives maintenance module, diagnostic tools module, remote service module, system user management module and system direction for user module are designed and developed.The fault diagnosis system has such characteristics as follows: Both C/S and B/S software design models are used in the system, and the system assisted diagnosis model and remote expert diagnosis model are used in the system, and at the same time, several fault diagnosis methods are implemented in this system such as CBR diagnostic method, RBR diagnostic method and remote expert diagnostic method and etc. .更多还原