基于优化VMD和BP神经网络液压管路故障诊断研究

Research on Fault Diagnosis of Hydraulic Pipeline Based on Optimized VMD and BP Neural Network

针对航空发动机液压管路故障信号易受噪声干扰、管路故障诊断准确率不高等问题,提出基于优化变分模态分解和BP神经网络的故障诊断方法。利用遗传算法自适应确定变分模态分解K、α的最优参数,然后采用优化后的变分模态分解方法对航空液压管路的振动信号进行分解,最后将故障特征明显的故障分量输入BP神经网络模型中进行训练和分类。结果表明:提出的基于变分模态分解与BP神经网络的航空液压管路故障诊断方法能够精准识别出航空液压管路多种不同的故障状态。

Aiming at the problem that the fault signal of aero-engine hydraulic pipeline is easily disturbed by noise and the accuracy of pipeline fault diagnosis is not high,a fault diagnosis method of aero-engine hydraulic pipeline based on optimized variational mode decomposition(VMD)and BP neural network was proposed.Genetic algorithm was used to determine the optimal parameters of VMD adaptively.Then,the vibration signal of aviation hydraulic pipeline was decomposed by the optimized VMD method.Finally,the fault components with obvious fault characteristics were input into BP neural network model for training and classification.The experimental results show that the aviation hydraulic pipeline fault diagnosis method based on optimized VMD and BP neural network is can be used to accurately identify a variety of different fault states of aviation hydraulic pipeline.