自适应随机共振和DEMD的单向阀早期故障诊断

摘要

In view of the low SNR (Signal Noise Ratio) of the early fault signals of the high pressure diaphragm pump check valve,it is difficult to extract the fault feature.In this paper,an early fault diagnosis method based on adaptive stochastic resonance and DEMD (Differential Empirical Mode Decomposition) is proposed.First of all,the original signal is processed,and the compression ratio is set for variable scale processing.Then,SNR is used as the adaptive degree function,and the PSO (Particle Swarm Optimization) algorithm is used to optimize the parameters of SR (Stochastic Resonance) system,the optimized parameters and the processed signals are input into the SR system.Finally,the signal output from the system is decomposed by DEMD algorithm;the components are analyzed by spectrum analysis,and the component synthesis with characteristic frequency is selected to carry out envelope analysis to extract the fault feature information.The results of simulation analysis and engineering experiment show the method can better extract the early fault feature information of the check valve.%针对高压隔膜泵单向阀的早期故障振动信号信噪比(SNR)低,故障特征提取困难的问题,本文提出一种自适应随机共振和微分经验模态分解(DEMD)的早期故障诊断方法.首先对原信号进行预处理,设置压缩比进行变尺度处理;然后将SNR作为自适应度函数,利用粒子群(PSO)算法优化随机共振(SR)系统参数,将优化后参数及处理后的信号输入SR系统中;最后对系统输出的信号进行DEMD算法分解,对各分量进行频谱分析,选取含特征频率的分量合成进行包络分析,以提取故障特征信息.经仿真分析与工程实验表明,该方法能够较好地提取出单向阀的早期故障特征信息.