中文说明：
针对矿浆管道工况调整给泄漏检测带来的干扰，准确提取泄漏信号的特征量是降低泄漏误报、漏报的关键。为此，提出了一种基于经验模态分解（EMD）、Hilbert能量谱与变量预测模型（VPMCD）相结合的泄漏检测方法。该方法首先将压力信号分解成若干个固有模态函数（IMF）之和，然后将IMF分量进行Hilbert变换得到局部Hilbert能量谱，依据能量分布的标准差选择最能准确反映矿浆管道运行工况的局部能量谱作为特征值向量，最后通过VPMCD分类器建立泄漏识别模型。将该方法应用于泄漏检测中，实验结果表明，矿浆管道在正常运行、泄漏和工况调整状态下，识别率达到95%，并综合分析流量信号，提高了泄漏检测精度。
English Description：
According to the interference to leak detection of mineral slurry pipeline caused by work condition adjustment,effectively extracting the characteristics of leak signal is the key to reduce the leakage of the false negatives and false positives.In this paper,a leak detection method based on EMD and VPMCD is proposed. In this method,the pressure signals are decomposed into several IMF components, and then take local Hilbert energy spectrum which most accurately reflect the pipeline operation conditions as feature values, Finally the leak identification model is established by VPMCD classifier.When the method is applied to the leak detection,the experimental results show that under the conditions of normal operation,leakage and work condition adjustment, the recognition rate of the mineral slurry pipeline reaches 95%,and by comprehensively analyzing the flow signals, it also improves the accuracy of leak detection.