管道系统泄漏检测神经网络与模式识别方法

提出了以管道系统泄漏后形成多相湍射流所引发的应力波信号时域和频域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。并提出以波峰、波谷、水平线、主导峰、支配强度、从属度等模式基元抽取负压波形特征，采用上下文无关文法对管道负压波进行描述，进而建立了管道负压波形结构模式分类系统，用于区别管道正常状态和泄漏状态。实验研究了这些新理论的有效性。

FLUID PIPELINE SYSTEM LEAK DETECTION BASED ON NEURAL NETWORK AND PATTERN RECOGNITION

In this paper the mechanism of the stress wave propagation along the pipeline system of NPP, caused by turbulent ejection from pipeline leakage, is researched. A series of characteristic index are described in time domain or frequency domain, and compress numerical algorithm is developed 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 had been demonstrated by experiments and finally used to design a handy instrument for the pipeline leakage detection. Usually a pipeline system has many inner branches and often in adjusting dynamic condition, it is difficult for traditional pipeline diagnosis facilities to identify the difference between inner pipeline operation and pipeline fault. This paper first proposed pipeline wave propagation identification by pattern recognition to diagnose pipeline leak. A series of pattern primitives such as peaks, valleys, horizon lines, capstan peaks, dominant relations, slave relations, etc., are used to extract features of the negative pressure wave form. The context free grammar of symbolic representation of the negative wave form is used, and a negative wave form parsing system with application to structural pattern recognition based on the representation is first proposed to detect and localize leaks of the fluid pipelines.