基于信号空间压缩感知算法的机械故障诊断

发布时间：2018-03-06 07:26

  本文选题：压缩感知(CS)　切入点：稀疏性　出处：《北京化工大学学报(自然科学版)》2017年05期 　论文类型：期刊论文

【摘要】：为了解决压缩感知(CS)重构算法通过重构稀疏系数求解原始信号的重构精度不高的问题,提出一种基于信号空间的压缩采样匹配追踪算法。首先在冗余字典中求解原始信号的最优表示空间,然后在最优表示空间中利用迭代算法直接求解原始信号,最后以轴承故障振动信号为例进行实验验证。结果证明本文算法提高了信号的重构精度,可以为增强机械振动信号的故障检测能力提供依据。
[Abstract]:In order to solve the problem that the reconstruction accuracy of the original signal is not high by the reconstruction sparse coefficient, A compression sampling matching tracking algorithm based on signal space is proposed. Firstly, the optimal representation space of the original signal is solved in the redundant dictionary, and then the iterative algorithm is used to solve the original signal directly in the optimal representation space. Finally, the experimental results show that the proposed algorithm improves the reconstruction accuracy of the signal, and can provide the basis for enhancing the fault detection ability of the mechanical vibration signal.
【作者单位】： 北京化工大学机电工程学院;
【基金】：国家自然科学基金(51405012)
【分类号】：TH17
，

本文编号：1573888