【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.更多还原

【Abstract】 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.更多还原