基于改进BP网络的管道安全监测技术研究  

Research on pipeline secure monitor based on improved BP neural networks

作　　者：孙洁娣[1] 温江涛[2] 靳世久[1] 

机构地区：[1]天津大学精密测试技术及仪器国家重点实验室 [2]燕山大学电气工程学院,秦皇岛066004

出　　处：《仪器仪表学报》2006年第z2期1647-1649,共3页Chinese Journal of Scientific Instrument

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,通过对信号特征的分析,实现震动信号的特征提取和关联,在特征级实现目标特性融合,并提出一种改进的神经网络方法进行融合及分类识别,在对实际目标信号的处理中得到较好的效果。Pipeline secure monitor can finish early monitor, location and advance alarm for the threatening actions to pipeline security. The key technology is to accurately classify and recognize the targets around the pipeline. Because moving targets over ground generate a succession of impacts, the soil disturbances propagate away from the source as seismic waves. The data characters were investigated and processed by means of multi-sensors data fusion, feature extraction, data association and etc. An improved BP algorithm is presented to fuse, classify and recognize the targets generating the seismic signals. The experiments indicate this method is effective to recognize these different targets.

关 键 词：管道安全监测 地震动信号 数据融合 神经网络 目标识别 

分 类 号：TH7-55[机械工程—仪器科学与技术]