Abstract: 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.

Key words: pipeline, neural networks, leak detection

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。实验研究了这一新理论的有效性并设计了适用于工业应用的管道检测仪器。

关键词: 管道流动, 神经网络, 泄漏检测