BLIND SOURCE SEPARATION OF MECHANICAL FAULT BASED ON BAT ALGORITHM

SUN YiJie; LI FuSheng; LIANG MingLiang; DONG LiSheng

doi:10.16579/j.issn.1001.9669.2018.05.006

您当前的位置：

首页 >

文章列表页 >

BLIND SOURCE SEPARATION OF MECHANICAL FAULT BASED ON BAT ALGORITHM

更新时间：2022-09-22

- BLIND SOURCE SEPARATION OF MECHANICAL FAULT BASED ON BAT ALGORITHM
- Journal of Mechanical Strength Vol. 40, Issue 5, Pages: 1050-1055(2018)
- 作者机构：
  
  1. 郑州铁路职业技术学院
- 作者简介：
- 基金信息：
- DOI：10.16579/j.issn.1001.9669.2018.05.006
  CLC：
扫描看全文
SUN YiJie, LI FuSheng, LIANG MingLiang, et al. BLIND SOURCE SEPARATION OF MECHANICAL FAULT BASED ON BAT ALGORITHM. [J]. 40(5):1050-1055(2018)
DOI：

SUN YiJie, LI FuSheng, LIANG MingLiang, et al. BLIND SOURCE SEPARATION OF MECHANICAL FAULT BASED ON BAT ALGORITHM. [J]. 40(5):1050-1055(2018) DOI： 10.16579/j.issn.1001.9669.2018.05.006.

摘要

基于蝙蝠算法实现容易、求解速度快、效率高、通用性强等优点,将蝙蝠算法与盲源分离相结合,提出了基于蝙蝠算法的机械故障盲源分离方法(BA-BSS)。BA-BSS方法以峭度的绝对值之和作为目标函数,通过BA寻找到目标函数的最大值,进而确定最优的分离矩阵。仿真结果表明,BA-BSS方法在分离性能、算法收敛性以及运算速度方面都明显地优于传统的基于遗传算法的机械故障盲源分离方法(GA-BSS)。最后成功地将BA-BSS方法应用于实际的滚动轴承内、外圈复合故障盲源分离中,分离效果是非常有效的。

Abstract

Based on the advantages of Bat Algorithm（ BA） that is easily to be realized,fast convergence speed,high efficiency and high universality,combining BA and blind source separation,a new method of mechanical failure blind source separation based on BA is proposed（ BA-BSS）. The BA-BSS method,as the target function of the sum of the absolute value of the kurtosis,seeks the maximum of the target function by BA,and then determines the optimal separation matrix. Simulation results show that the BA-BSS method is significantly superior to the traditional mechanical failure blind source separation based on Genetic Algorithm（ GA-BSS） in separation performance,algorithm convergence and operation speed. Finally,the BA-BSS method is successfully applied to the actual rolling bearing inner and outer mixing fault blind source separation,and the separation effect is very effective

关键词

蝙蝠算法盲源分离轴承复合故障

Keywords

Bat algorithmBlind source separationRolling bearingMixing fault

references

Views

174

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

ANALYSIS METHOD AND PROCESS OPTIMIZATION OF VIBRATION SIGNAL IN PRECISION MILLING BASED ON BLIND SOURCE SEPARATION

Related Author

No data

Related Institution

School of Mechanical Engineering, University of Shanghai for Science and Technology

School of Mechanical Engineering,Donghua University

⁰