基于IMF能量特征的输油管道内流型识别新方法

Novel Method of Pipeline Flow Pattern Identification Based on Energy Characteristics of IMF

应用经验模态分解(EMD)对输油管道内流型的压差波动信号进行分析、提取特征,然后将IMF能量特征作为概率神经网络(PNN)的输入,提出一种新的流型识别方法。实验结果表明:该方法能很好地识别水平管内的4种流型,为流型识别开辟了一条新的途径;另外,该方法优于BP网络且稳定、识别率高,具有可行性。

In this article, a novel flow pattem identification method of two-phase flow was proposed. Firstly the method analyzes the pressure-difference fluctuation signals of a flow regime by utilizing the empirical mode decomposition （EMD） and extracts the intrinsic mode function （IMF） energy feature, then IMF energy feature is put into probabilistic neural network （PNN） and flow regime intelligent identification can be performed. The experimental result shows that this method can identify the four flow regimes of gas-liquid two-phase flow in horizontal pipe. This method develops a new direction for the flow regime identification. In addition, the experimental result shows that this method is superior to BP neural network, and it is not only stable but also higher identification. The result also proves that the method is feasible.