基于D-S证据理论的管道安全监测数据融合技术的研究
详细信息 本馆镜像全文    |  推荐本文 | | 获取馆网全文
摘要
管道安全监测技术能够对管道安全构成威胁的行为进行早期监测、定位和预警,对管道周围目标进行正确的分类识别是其中的关键.采用多个地震信号传感器对管道周围的人、车辆等目标发出的震动信号进行采集,为了解决目标识别问题并提高目标的识别率,针对多个传感器采集的数据,本文中提出了采用D-S证据理论方法对数据进行融合处理,实验结果证明基于融合后的识别结果较单个传感器的识别结果有了较好的改善.
Pipeline secure monitor can finish early monitor,loc at ion and advance alarm for the threatening actions to pipeline security.The key technology is to accurately classify and recognize the targets around the pipel ine.Because moving targets over ground generate a succession of impacts,the so il disturbances propagate away from the source as seismic waves.The seismic sig nals obtained from many separate geophones.To recognize the target and improve the radio of recognition,the D-S evidence theory was used to fuse the data.Th e data characters were investigated and processed by means of multi-sensors dat a fusion,feature extraction,data association and etc.The characteristic fusio n finished in the decision level.The experiments indicate this data fusion meth od is effective to improve these different targets recognition.The result is be tter than single sensor.
引文
[1]陈仁文.小波变换在输油管道漏油实时监测中的应用[J].仪器仪表学报2005,26(3):242-245.
    [2]蒋酝晨,吴海霞.输油管道泄漏监测SCADA系统的设计与实现[J].仪表技术与传感器,2004,2:24-26..
    [3]蓝金辉,李虹,周兆英.目标地震动信号的特征提取及识别研究[J].振动与冲击,2001,20(4):42-44.
    [4]Jinhui Lan,Saeid Nahavandi,Tian Lan et al.Recognition of Moving Ground Targets by Measuring and Processing Seismic Signal[J].Measurement,2005,37:189-199.
    [5]徐从富等.面向数据融合的DS方法综述[J].电子学报,2001,29(3):393-396.
    [6]何友,王国宏,彭应宁.多传感器信息融合及应用[M].北京:电子工业出版社,2000.11.
    [7]Bogler.Shafer-Dempster Reasoning with Applicationto Multi-sensor Target identification System[J].IEEE SMC.1987,17(6):968-977.
    [8]聂伟荣,朱继男,夏虹.D-S证据理论在目标识别中的应用[J].弹道学报,2002,14(4):40-44.

版权所有:© 2023 中国地质图书馆 中国地质调查局地学文献中心