MATLAB改进的自适应时频峰值滤波算法实现
首先，本文在介绍了时频分析研究背景的基础上，引出了短时傅立叶变换、Wigner-Ville分布等几种常用的时频分布的基本理论和性质。之后，本文着重介绍了时频峰值滤波。从对不同的信号能够实现窗长的自适应考虑，介绍了窗长选择的改进方案，即基于滑动成对置信区间准则（SPICI）的自适应选择。基于上述分析，运用MATLAB仿真分析了该改进算法的性能。通过仿真分析得出，对于非平稳信号，该算法具有较好的性能，其去噪效果好，能有效降低均方差，具有广阔的应用前景。19793
关键词 时频分析 时频峰值滤波 自适应 SPICI WVD
毕业论文设计说明书（论文）外文摘要
Title Improved Adaptive Time-Frequency Peak Filtering algorithm
Abstract
Time-frequency peak filtering is a new method to solve non-stationary signals in time-frequency analysis. For the time varying signal , the tradition analysis methods like time domain or frequency domain can not fully reflect the characteristics of the signal, but the time-frequency distribution form provides an effective means to study the non-stationary signals . This paper studies the adaptive time-frequency peak filtering algorithms and applications in the time-frequency analysis.
First,this paper based on the introduction of the time-frequence analysis, describes the basic theory of several commonly used time-frequence distributions ,like the short-time Fourier transform and the Wigner-Ville distribution.After that, this paper focuses on introducing time-frequency peak filtering.Considering to achieve adaptation of the window length when the signals are different,this paper describes the improvement of window length selections.It is based on the sliding pair-wise intersection
of confidence intervals(SPICI).Based on the above analysis, this paper uses MATLAB to analyze the performance of the improved algorithm. Through simulation results, for non-stationary signals, the algorithm has good performance because of its good denoising effects, and the reduction the mean square error.So it has broad application prospects.
Keywords Time-frequency analysis TFPF adaptive SPICI WVD
目 次
1 绪论 1
1.1 课题研究的背景和意义 1
1.2 国内外研究现状 2
1.3 本文研究的内容和组织安排 4
2 时频分析与时频峰值滤波 5
2.1 时频分析 5
2.2 Wigner-Ville分布 7
2.3 时频峰值滤波算法原理 13
2.4 本章小结 15
3 自适应时频峰值滤波算法原理及改进算法 16
3.1 自适应时频峰值滤波算法原理 16
3.2 自适应时频峰值滤波算法的实现 18
3.3 改进的自适应时频峰值滤波算法原理 20
3.4 本章小结 23
4 算法实现及仿真实验 24
4.1 算法实现步骤 24
4.2 算法仿真实验 25
4.3 本章小结 32
5 全文总结和展望 33
5.1 全文总结 33