基于集合经验模态分解和排列熵的核电厂信号降噪研究

Study on the Nudear Power Station Signal Analysis Based on Ensemble Empirical Mode Decomposition and Permutation Entropy

本文提出了一种基于集合经验模态分解和排列熵的电站信号降噪方法。该方法流程如下,首先,采用集合经验模态分解对电站典型实测信号进行了分解,获得对应的本征模态分量。其次,采用排列熵对本征模态分量进行混沌度的定量评价,从而实现实测信号中的有用信号和噪声信号的区分。对于后者,采用改进的小波软阈值降噪法进行降噪。最后,根据排列熵筛分后的有用信号和改进的小波软阈值降噪后的噪声信号进行重构,得到降噪后的信号。另外,本文也采用了主流的经验模态分解和局部均值分解对该信号进行了处理,并将分析结果进行对比。对比结果表明,基于本文所提方法得到的降噪后信号排列熵较小,表明降噪效果要优于以上两种方法。

A de-noising method based on ensemble empirical mode decomposition(EEMD)and permutation entropy is proposed for power station signal in the present paper.The procedure of this method is as follows.Firstly,a typical measured signal of a power station is decomposed by EEMD and the corresponding intrinsic mode functions are obtained.Secondly,the permutation entropy is used to quantitatively evaluate the chaotic degree of the intrinsic mode functions,so as to distinguish the useful signals and the noises in the measured signal.For the latter,they are de-noised by the wavelet threshold de-noising method.Finally,the useful signals filtered by the permutation entropy and the noises de-noised by the wavelet threshold de-noising method are reconstructed to obtain the de-noised signal.In addition,the mainstream empirical mode decomposition and local mean decomposition are also used to process the signal,and the analysis results are compared.The comparison results show that the permutation entropy of the de-noised signal based on the proposed method in the present paper is smaller,indicating that the denoising effect is better than the above two methods.