期刊文献+

基于神经网络的管道泄漏检测方法及仪器 被引量:62

Pipeline Leak Detection Method and Instrument Based on Neural Networks
下载PDF
导出
摘要 研究了管道泄漏后形成多相湍射流所引发的应力波在管壁中的传播机理,分析了泄漏引发的管道横振、纵振和圆环振动,提出一系列应力波特征提取指标及其离散数据算法。首次提出了以泄漏信号特征指标构造神经网络输入矩阵,建立对管道运行状况进行分类的神经网络模型以检测管道泄漏故障的发生。 The mechanism of the stress wave propagation along the pipeline caused by turbulent ejection from pipeline leakage is researched.All of the longitudinal,transverse and circumferential eigenmodes caused by pipeline leakage are analyzed.A series of characteristic index are described in time domain or frequency domain,and compress numerical algorithm is researched for original data compression.A back propagation neural networks (BPNN) with the input matrix composed by stress wave characteristics in time domain or frequency domain is first proposed to classify various situations of the pipeline,in order to detect the leakage in the fluid flow pipelines.The capability of the new method has been proved by experiments and finally used to design a handy instrument for the pipeline leakage detection.
出处 《北京大学学报(自然科学版)》 CSCD 北大核心 1997年第3期319-327,共9页 Acta Scientiarum Naturalium Universitatis Pekinensis
基金 中国博士后科学基金
关键词 管道 神经网络 泄漏检测 检测仪 腐蚀 pipeline neural networks leak detection
  • 相关文献

参考文献1

  • 1史忠植,神经计算,1993年

同被引文献686

引证文献62

二级引证文献754

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部