搜索资源列表
EWT
- 经验小波变换,将信号分解为多个子特征的子序列。性能较EMD、EEMD、WD等有所提升。(Empirical wavelet transform decomposes the signal into sub sequences of multiple sub features. The performance is improved compared with EMD, EEMD, WD and so on.)
1
- 针对矿浆管道工况调整给泄漏检测带来的干扰,准确提取泄漏信号的特征量是降低泄漏误报、漏报的关键。为此,提出了一种基于经验模态分解(EMD)、Hilbert能量谱与变量预测模型(VPMCD)相结合的泄漏检测方法。该方法首先将压力信号分解成若干个固有模态函数(IMF)之和,然后将IMF分量进行Hilbert变换得到局部Hilbert能量谱,依据能量分布的标准差选择最能准确反映矿浆管道运行工况的局部能量谱作为特征值向量,最后通过VPMCD分类器建立泄漏识别模型。将该方法应用于泄漏检测中,实验结果表明,矿
LMD分解
- LMD分解程序 能有效解决EMD的模态混叠现象,LMD结合样本熵,里面有个例子(The LMD decomposition program can effectively solve the modal aliasing phenomenon of EMD. LMD combines with sample entropy, and there is an example)
NA-MEMD
- 多元经验模式分解(MEMD)算法是EMD算法从单个变量到任意数量的变量的扩展,其与经验模态分解一样存在模式混合问题,基于噪声辅助的多元经验模式分解(NAMEMD)就在对MEMD的改进,解决其问题。(The multiple empirical mode decomposition (MEMD) algorithm is an extension of the EMD algorithm from a single variable to any number of variables. Like
iceemdan.m
- 信号iceemdan模态分解,包含测试信号,简单易实现,需要自己安装emd工具箱((It can be used for signal EMD, EEMD, VMD decomposition. Because the algorithm adds its own annotations, it's easy to understand))