基于混沌理论与SVM的内燃机振动信号趋势预测

针对内燃机振动信号信噪比低且呈非线性、非平稳的特性,提出将经验模态分解(emprical mode decomposition,简称EMD)相空间重构理论与支持向量机(support vector machine,简称SVM)相结合,实现内燃机振动监测数据的建模及预测.首先,将含噪声的振动信号经验模式分解,去掉主要干扰因素所对应的固有模态函数(intrinsic mode function,简称IMF)分量,再将剩余IMF分量进行重构,得到去噪声后振动信号时间序列;然后应用混沌理论,选择合适的嵌入维数和时间延迟对去噪后的振动信号时间序列进行相空间重构;最后采用SVM对其进行建模预测,并与径向基函数(radial basis function,简称RBF)神经网络的预测结果进行比较.试验数据表明,该方法能够预测内燃机振动信号的变化趋势,性能优于传统的分析方法,具有一定的工程实用性.

Trend Prediction Of Engine Vibration Signals Using Chaotic Theory and Support Vector Machine

For the low signal to noise ratio,non-linear and non-stationary characteristics of engine vibration signals,a modeling and forecasting technique is put forward by integrating the empirical mode decomposition(EMD) de-noising,the theory of phase space reconstruction and support vector machine(SVM).Firstly, the vibration signals were decomposed by using the EMD method and the intrinsic mode function(IMF) components related to main interference factors were eliminated.Then,the true vibration signal was obtained...