基于专家系统和神经网络的卫星故障诊断系统设计与实现  

Design and implementation of fault diagnosis system for satellite based on expert system and neural network

作　　者：郑玮[1] 杨学猛 葛宁[1] 

机构地区：[1]清华大学电子工程系,北京100084 [2]中国卫通集团有限公司,北京100094

出　　处：《燕山大学学报》2016年第1期74-80,共7页Journal of Yanshan University

基　　金：国家重点基础研究发展计划(973计划)资助项目(2014CB340206);国家自然科学基金资助项目(61132002)

摘　　要：为改善基于知识的专家系统在知识获取上的不足,提高对卫星故障的诊断能力,提出了一种专家系统与神经网络相结合的卫星故障诊断系统。首先,采用开发工具CLIPS以产生式规则搭建知识库,然后利用神经网络方法对知识库进行扩展,解决了专家系统知识获取的"瓶颈"问题,最后利用该系统对卫星故障进行诊断。仿真结果表明,该方法可以提高对卫星故障的诊断能力,有助于卫星测控人员快速定位故障,从而有效保障卫星安全。In order to overcome the shortcomings of the traditional expert system in knowledge acquisition and increase the ability for diagnosing the faults of satellites,a fault diagnosis system for satellite combined expert system with artificial neural network is designed. The knowledge base for the diagnosis system is constructed by using the expert system development tool—CLIPS,and is enlarged and updated by artificial neural network to solve the 'bottle neck'problem for knowledge acquisition in expert system,then the faults of satellites are diagnosed by this way. The simulation results show that the proposed method can improve the diagnosis ability of satellite diagnosis system and realize fast failure detection to keep the satellite safe.

关 键 词：专家系统 神经网络 卫星 故障诊断 

分 类 号：TP182[自动化与计算机技术—控制理论与控制工程]