基于CLIPS专家系统的自动数据判读方法  

Technology of automatic data discrimination based on CLIPS expert system

作　　者：贺宇峰[1,2] 赵光恒[2] 吕从民[2] 郭丽丽[2] 

机构地区：[1]中国科学院研究生院,北京100080 [2]中国科学院光电研究院,北京100080

出　　处：《中国科学院研究生院学报》2011年第4期505-513,共9页Journal of the Graduate School of the Chinese Academy of Sciences

基　　金：国家部委预研基金资助

摘　　要：针对空间有效载荷测试数据和遥测数据量大、判据复杂等特点,提出一种基于CLIPS专家系统的数据自动判读方法.该方法采用CLIPS专家系统语言实现了对复杂规则的描述引入有限状态机实现了对随载荷工作状态变化遥测量的动态判读.采用从频繁模式中挖掘关联规则技术设计了判读知识的辅助获取算法,通过CLIPS自身的推理机制提高了判读速度.满足了有效载荷地面集成测试及在轨运控中对数据判读的要求,提高了判读的效率和准确度,并成功应用于某卫星科研实践.Considering the mass data and complex criterions of payload telemetry,we propose a technology of automatic discrimination for payload telemetry data based on C language integrated production system（CLIPS）.This technology realizes not only the descriptions of complex discrimination rules by adopting the expert system language CLIPS but also the dynamic discrimination of telemetry data varying with the state of payloads by introducing finite state machine.Besides,we design the auxiliary learning algorithm of discrimination knowledge by mining rules from frequent patterns and improve the speed of discrimination by using reasoning mechanism of CLIPS.Thus this technology can meet the requirement of data discrimination for payload system test and flight control,and dramatically improves the efficiency and veracity of discrimination.It has been successfully applied to some satellite projects.

关 键 词：有效载荷 自动判读 专家系统 CLIPS 频繁模式挖掘 

分 类 号：TP277[自动化与计算机技术—检测技术与自动化装置]