基于VMD和RBF的舰船管路泄漏识别和定位

针对工作环境恶劣、维护保养不便的舰船管路难以迅速定位泄漏点并对其进行损害管制,提出了一种基于VMD和RBF的舰船管路泄漏识别和定位方法。首先,对管路泄漏产生的空化现象、湍流和流体与管路的摩擦进行分析,研究影响泄漏产生激励的因素；然后,提出一种基于变分模态分解(VMD)与径向基函数(RBF)神经网络的管路泄漏识别和定位方法,通过VMD得到有效分量的中心频率和能量值分别构造特征向量,输入RBF神经网络以达到泄漏识别和定位目的；最后,模拟舰船环境,搭建泄漏管路试验平台,分析泄漏管路不同工况下的振动信号,并对RBF神经网络的诊断准确率进行验证。实测舰船管路故障信号分析表明,泄漏识别的准确率为90%,泄漏定位的准确率为87.5%。

Warship Pipeline Leakage Identification and Location based on VMD-RBF

In view of the difficulty in locating the leakage point and controlling the damage in the warship pipeline with bad working environment and inconvenient maintenance, a method of identifying and locating the leakage point in warship pipeline based on VMD-RBF was proposed. Firstly, the cavitation phenomenon, turbulence and friction between fluid and pipeline caused by leakage fault are analyzed, and the factors influencing the excitation of pipeline leakage are studied. Then, a pipeline leakage identification and location method based on variational mode decomposition (VMD) and radial basis function (RBF) neural network is proposed, and the effective component center frequency and energy value obtained by VMD are used to construct signal feature vectors, which are input into RBF neural network to achieve the purpose of leakage identification and location. Finally, the test platform of leakage pipeline was built to simulate the ship environment, and the vibration signals of leakage pipeline under different conditions were analyzed, and the diagnostic accuracy of RBF neural network was verified. The analysis of measured pipeline leakage fault signals shows that the accuracy rate of leakage identification is 90% and that of leakage location is 87.5%.