Abstract: In fluid pipeline leak detection and location, noise in the pressure signal collected both ends of the pipeline will affects the accuracy of leak detection and the error of leakage location. To reduce the noise interference an improved local mean decomposition (LMD) signal analysis method is proposed. The production functions (PF) that were related to the leak signal can be exacted, and it was necessary to know the characteristics of leak signals or noise in advance. According to the cross⁃correlation function, there is a significant peak between the measured signals which are decomposed into a number of PFs. These reconstructed principles PF components were obtained, and a wavelet analysis was used to remove the noise in the reconstructed signal. On this basis, the signal features were extracted according to the time⁃domain feature and waveform feature, which were input into Least Squares Twin Support Vector Machine (LSTSVM), LSTSVM to distinguished different working conditions. According to the reconstructed signal after wavelet de⁃noising, the time delay estimate of the negative pressure signal at the end of the pipeline is obtained by the cross⁃correlation function, and the leak location was ultimately calculated by combining the time delay with the leak signal propagation velocity. A leak simulation for pipeline was proposed , where the collected data of the different working conditions was processed. The experimental results show that the proposed method can effectively identify different working conditions and accurately locate the leakage point.

Key words: Local mean decomposition, Wavelet analysis, Least squares twin support vector machine, Leak aperture, Leak localization

摘要： 在管道泄漏检测中，管道首末两端采集压力信号的噪声会影响泄漏检测的准确性和泄漏定位的误差。为了最大程度地降低噪声的干扰，提出改进局域均值分解(LMD)方法，该方法在外界噪声特征未知的情况下，有效提取与泄漏信号相关的乘积函数(PF)。根据测试信号的PF和参考信号相关分析的峰值,获取包含主要泄漏信息的PF分量并进行信号重构,重构信号再经过小波分析进一步消噪。在此基础上，按照时域特征和波形特征提取信号特征值输入最小二乘双支持向量机(LSTSVM)中，用以区分不同工况。根据经过小波消噪后的重构信号，采用广义相关分析法获取泄漏信号到达首末两端负压波信号的时延估计，并结合泄漏信号传播速度实现泄漏点定位。通过环道现场实验，对管道各种工况信号进行处理分析。结果表明，该方法能有效识别不同工况及泄漏定位。

关键词: 局域均值分解, 小波分析, 最小二乘双支持向量机, 泄漏孔径, 泄漏定位