中文摘要：

针对天然气管道泄漏受孔径、传感器距离、管道内压力等多种因素影响,特征提取及识别算法较为复杂的问题,提出了基于总体局域均值分解-相对熵的特征提取算法并结合稀疏表示分类的泄漏孔径识别新方法。该方法采用总体局域均值分解方法对泄漏信号进行自适应分解,得到不同孔径泄漏信号的特征信息,并根据KL散度选择包含主要泄漏信息的PF分量,在此基础上提取多种时频特征参数,获取全面准确表征泄漏信号的特征向量;针对小样本复杂信号的分类,提出稀疏表示分类器实现泄漏孔径准确分类。该分类器采用过完备字典求得测试信号的最稀疏解,并以此解作为测试信号的稀疏重构系数,以获取测试信号在不同类别中的重构信号,最终通过判断测试信号与重构信号的残差值大小完成泄漏孔径分类。实验结果表明,所提出的算法比传统的SVM及BP分类算法识别准确率高。

英文摘要：

Abstract： Natural gas pipeline leakage was influenced by the aperture？ the sensor distance？ the pressures in the pipeline and many factors,so the feature extraction and recognition algorithm is rela-tively complicated. A novel leak aperture identification method which combined feature extraction based on ELMD-KL model with SRC was proposed. ELMD was applied to adaptively decompose leak signals, to obtain characteristic informations of different aperture leak signals, and to extract the prin-cipal product function（PF） components based on KL divergence which contained the main leakage in-formations. The method extracted multiple characteristic parameters in time domain and frequency d〇- main as the feature vectors. For the classification of small sample complex signals？ a SRC was put for-ward to realize the accurate classification of leak apertures. The classifier obtained the most sparse so-lutions of the test signals with overcomplete dictionary. The solutions were used as the sparse coeffi-cient to reconstruct the test signals and obtain reconstruction signals in different classes of the test signals. Finally, classification of leak apertures was accomplished by judging the residual values be-tween test signals and reconstruction signals. The experimental results show that the proposed algo-rithm has higher recognition accuracy compared with the traditional classification algorithm of SVM and BP.Key words： leakage aperture identification; ensemble local mean decomposition （ELMD）; KL di-vergence; sparse representation classifier （SRC） ; overcomplete dictionary