基于自适应VMD-Hilbert的球磨机负荷参数预测

Load parameter prediction of ball mill based on adaptive VMD-Hilbert

提出一种自适应变分模态分解(VMD)—希尔伯特(Hilbert)边际谱样本熵和最小二乘支持向量机(LSSVM)提取球磨机振动信号组合特征并预测负荷参数的方法。首先,使用自适应VMD的振动敏感信号调制来分解振动,得到反映振动特性的本征模态函数(IMF)分量;之后,进行Hilbert变换,得到边际谱样本熵;最后,将其作为输入特征向量输入到LSSVM,实现球磨机负荷参数预测。试验结果表明:该方法可以有效地提取球磨机的非线性不稳定的信号特征,较为精确地预测球磨机负荷参数。

An adaptive variational mode decomposition(VMD)-Hilbert marginal spectrum sample entropy and least square support vector machine(LSSVM)method is proposed to extract the combination characteristics of ball mill vibration signals and predict the load parameters.Firstly,the vibration sensitive modulation of the adaptive VMD is used to decompose the vibration,intrinsic mode function(IMF)components,which reflects the vibration characteristics followed by the Hilbert transform,the marginal spectrum sample entropy is obtained.Finally,it is input to the LSSVM as input feature vectors to realize forecasting of ball mill load parameters.The experimental results show that this method can effectively extract the nonlinear and unstable signal characteristics of ball mill and accurately predict the load parameters of ball mill.