基于ICA技术和波形结构模式识别的管线泄漏诊断方法  

Leakage Diagnosis for Pipelines Based on ICA and Wave Structure Recognition

作　　者：陈志刚[1] 张来斌[1] 王朝晖[1] 梁伟[1] 

机构地区：[1]中国石油大学(北京)机电学院,北京102249

出　　处：《化工自动化及仪表》2007年第2期52-55,共4页Control and Instruments in Chemical Industry

基　　金：国家自然科学基金资助项目(50375103);教育部新世纪优秀人才支持计划资助项目(NCET-05-0110);中国石油天然气集团公司创新基金资助

摘　　要：针对强背景噪声下负压波特征信号难以准确提取的难题,提出采用独立分量分析技术(ICA)对负压波原始信号进行分解提取,以实现信号中弱目标信号和强背景噪声的有效分离,实验结果显示处理后的负压波信号信噪比大幅提高。分析不同工况下压力信号波形特征,提出采用波形结构模式识别方法判断管道运行状态,针对性地选取了波形特征参数指标,同时在有限样本情况下实现管道运行状态模式库的构建,从而达到波形自动匹配和识别的目标。现场测试结果表明了该方法的可行性。For solving the difficulty of feature signal extraction with strong noise in negative pressure wave, a new method based on Independent Component Analysis （ICA） is proposed to realize separation and filtering between weak aim signal and strong noise. The experiment shows that signal-to-noise ratio of processed pressure signals is raised obviously. The pressure wave in different operation modes are analyzed and the wave structure recognition is proposed to judge pipeline condition. The characteristic wave vectors are selected and then the mode base of pipeline conditions is established in limit samples. The testing results show the reliability and validity of this method.

关 键 词：管线泄漏 负压波 独立分量分析 降噪 波形结构 状态库 

分 类 号：TE973[石油与天然气工程—石油机械设备]