关键词: 管道流动, 神经网络, 泄漏检测

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