当我们在进行故障诊断、回归预测或者时间序列预测等模型建模时,采集的实际输入信号有时比较复杂,难以直接对这些复杂信号进行分析都,为此,我们需要将这些复杂信号简单化,这就有了信号分解的产生,选择合适的信号分解技术对于提取有用信息、提高数据处理精度至关重要.本文系统总结了26种信号分解的技术方法:具体如下:
1. EMD(经验模态分解,Empirical Mode Decomposition)
2. TVF-EMD(时变滤波的经验模态分解,Time-Varying Filtered Empirical Mode Decomposition)
3. EEMD(集成经验模态分解,Ensemble Empirical Mode Decomposition)
4. VMD(变分模态分解,Variational Mode Decomposition)
5. CEEMDAN(完全自适应噪声集合经验模态分解,Complementary Ensemble Empirical Mode Decomposition with Adaptive Noise)
6. LMD(局部均值分解,Local Mean Decomposition)
7. RLMD(鲁棒局部均值分解, Robust Local Mean Decomposition)
8. ITD(固有时间尺度分解,Intrinsic Time Decomposition)
9. SVMD(逐次变分模态分解,Sequential Variational Mode Decomposition)
10. ICEEMDAN(改进的完全自适应噪声集合经验模态分解,Improved Complementary Ensemble Empirical Mode Decomposition with Adaptive Noise)
11. FMD(特征模式分解,Feature Mode Decomposition)
12. REMD(鲁棒经验模态分解,Robust Empirical Mode Decomposition)
13. SGMD(辛几何模态分解,Spectral-Grouping-based Mode Decomposition)
14. RLMD(鲁棒局部均值分解,Robust Intrinsic Time Decomposition)
15. BA-ACMD(带宽感知的自适应Chirp模式分解,Bandwidth-aware adaptive chirp mode decomposition)
16. CEEMD(互补集合经验模态分解,Complementary Ensemble Empirical Mode Decomposition)
17. SSA(奇异谱分析,Singular Spectrum Analysis)
19. RPSEMD(再生相移正弦辅助经验模态分解,Regenerated Phase-shifted Sinusoids assisted Empirical Mode Decomposition)
20. EWT(经验小波变换,Empirical Wavelet Transform)
21. DWT(离散小波变换,Discraete wavelet transform)
22. TDD(时域分解,Time Domain Decomposition)
23. MODWT(最大重叠离散小波变换,Maximal Overlap Discrete Wavelet Transform)
24. MEMD(多元经验模态分解,Multivariate Empirical Mode Decomposition)
25. MVMD(多元变分模态分解,Multivariate Variational Mode Decomposition)
26. WPD(小波包分解,Wavelet Packet Decomposition)
信号分解效果图如下: