基于过程信息融合的管线泄漏诊断  

Pipeline leak detection based on process information fusion

作　　者：秦先勇[1] 张来斌[1] 王朝晖[1] 梁伟[1] 

机构地区：[1]中国石油大学机电工程学院,北京102249

出　　处：《中国石油大学学报（自然科学版）》2008年第4期82-86,共5页Journal of China University of Petroleum(Edition of Natural Science)

基　　金：教育部新世纪优秀人才支持计划项目(NCET.05.0110);中国石油天然气集团公司创新基金

摘　　要：根据管线泄漏瞬态过程持续时间较短以及干扰工况较多的特点,提出了基于过程信息融合的管线泄漏检测方法。对管线泄漏特征进行了分析,并介绍了基于过程平稳熵、双通道奇异谱熵和双通道能谱熵的过程信息熵特征提取方法。将过程信息熵应用于对管线泄漏的识别,并利用GPS时间标签定位法结合G IS定位信息进行精确诊断。利用该方法对西部成品油管线进行泄漏监测,结果显示,基于过程信息融合的管线泄漏监测方法具有较好的实时性和抗干扰能力,提高了泄漏诊断的准确性和定位的精确性。Considering the transient features of pipeline leak, a leak detection method based on process information fusion was presented, The pipeline leak features were analyzed. The extracting method of process information entropy based on process steady entropy, double channel singular spectrum entropy and double channel power speetrum entropy was introduced. The process fusion entropy was used to detect pipeline leak, combining GPS time label location method with GIS information. This method was used for leak monitoring of west products pipeline. The results show that this method has good performance on the accuracy of leak recognition and leak location.

关 键 词：过程信息融合 泄漏检测 过程信息熵 

分 类 号：TE973[石油与天然气工程—石油机械设备]