基于IMF复杂度和RBF网络的配气机构故障诊断

摘要

According to the non-stationarity characteristics of the vibration signals from diesel engine, a fault diagnosis method based on Empirical Mode Decomposition (EMD), complexity and RBF neural network is proposed. Firstly, the given vibration signals were decomposed into a finite number of Intrinsic Mode Functions (IMF), then the Lempel- Ziv complexity feature of the fore five IMF components were calculated as faulty eigenvector. RBF neural network has the capacity to quickly close any nonlinear function and has the ability of classification. It is advantageous for diesel engine diagnosis. Finally, practical experimental data is used to verify this method, and the diagnosis results and comparative tests fully validate its effectiveness.%针对柴油机振动信号的非平稳特性,提出一种经验模态分解(Empirical Mode Decomposition,EMD)、复杂度和RBF(radi-cal basis function)神经网络相结合的故障诊断方法;运用经验模态分解方法对特定时段的振动信号进行分析,计算前5个固有模式分量(Intrinsic Mode Functions,IMF)的Lempel--Ziv相对复杂度作为故障特征向量,并利用RBF神经网络可以快速逼近任意非线性函数及良好分类能力的特点,来实现对柴油机工作状态和故障类型的判别;最后,利用实际柴油机试验数据的诊断和对比试验验证了该方法的有效性.