JOURNAL ARTICLE

Fault Diagnosis Based on FVMD Multi-scale Permutation Entropy and GK Fuzzy Clustering

Dongning Chen

Year: 2018 Journal:   Journal of Mechanical Engineering Vol: 54 (1)Pages: 16-16

Abstract

摘要: 针对设备故障信号的非线性、非平稳特征,提出了基于快速变分模态分解、参数优化多尺度排列熵和特征加权GK模糊聚类的故障诊断方法。首先,在变分模态分解的基础上,引入快速迭代的思想,提出快速变分模态分解方法,以减少算法运行时间与迭代次数;其次,针对多尺度排列熵算法的参数确定问题,综合考虑参数之间的交互影响,提出一种基于多作用力微粒群算法的参数优化方法,并通过快速变分模态分解和参数优化多尺度排列熵算法提取故障特征;之后,考虑到样本特征矢量中各维特征在聚类过程中的贡献不同,提出基于ReliefF特征加权的GK模糊聚类方法,由特征加权GK模糊聚类确定标准聚类中心,通过择近原则实现故障模式的分类识别;最后,以在机械故障试验平台上采集到的轴承不同故障类型的振动信号为研究对象,应用所提方法进行分析。结果表明,相对于改进前的变分模态分解、多尺度排列熵和GK模糊聚类方法,本文所提方法不仅能够有效提取故障特征,还能准确实现故障模式的分类识别,而且故障识别率得到提高。

Keywords:
Cluster analysis Fuzzy logic Permutation (music) Scale (ratio) Computer science Entropy (arrow of time) Fuzzy clustering Data mining Mathematics Artificial intelligence Geography Physics Cartography

Metrics

20
Cited By
2.67
FWCI (Field Weighted Citation Impact)
0
Refs
0.90
Citation Normalized Percentile
Is in top 1%
Is in top 10%

Citation History

Topics

Fault Detection and Control Systems
Physical Sciences →  Engineering →  Control and Systems Engineering
Advanced Sensor and Control Systems
Physical Sciences →  Engineering →  Control and Systems Engineering
Advanced Algorithms and Applications
Physical Sciences →  Engineering →  Control and Systems Engineering
© 2026 ScienceGate Book Chapters — All rights reserved.