• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

一种基于FCEEMD的多复杂度低维特征与有向无环图LSTSVM的新型故障诊断方法

A Novel Fault Diagnosis Method Using FCEEMD-Based Multi-Complexity Low-Dimensional Features and Directed Acyclic Graph LSTSVM.

作者信息

Lu Rongrong, Xu Miao, Zhou Chengjiang, Zhang Zhaodong, Tan Kairong, Sun Yuhuan, Wang Yuran, Mao Min

机构信息

School of Information Science and Technology, Yunnan Normal University, Kunming 650500, China.

Faculty of Information Engineering, Quzhou College of Technology, Quzhou 324000, China.

出版信息

Entropy (Basel). 2024 Nov 29;26(12):1031. doi: 10.3390/e26121031.

DOI:10.3390/e26121031
PMID:39766660
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11727493/
Abstract

Rolling bearings, as critical components of rotating machinery, significantly influence equipment reliability and operational efficiency. Accurate fault diagnosis is therefore crucial for maintaining industrial production safety and continuity. This paper presents a new fault diagnosis method based on FCEEMD multi-complexity low-dimensional features and directed acyclic graph LSTSVM. The Fast Complementary Ensemble Empirical Mode Decomposition (FCEEMD) method is applied to decompose vibration signals, effectively reducing background noise. Nonlinear complexity features are then extracted, including sample entropy (SE), permutation entropy (PE), dispersion entropy (DE), Gini coefficient, the square envelope Gini coefficient (SEGI), and the square envelope spectral Gini coefficient (SESGI), enhancing the capture of the signal complexity. In addition, 16 time-domain and 13 frequency-domain features are used to characterize the signal, forming a high-dimensional feature matrix. Robust unsupervised feature selection with local preservation (RULSP) is employed to identify low-dimensional sensitive features. Finally, a multi-classifier based on DAG LSTSVM is constructed using the directed acyclic graph (DAG) strategy, improving fault diagnosis precision. Experiments on both laboratory bearing faults and industrial check valve faults demonstrate nearly 100% diagnostic accuracy, highlighting the method's effectiveness and potential.

摘要

滚动轴承作为旋转机械的关键部件，对设备可靠性和运行效率有重大影响。因此，准确的故障诊断对于维持工业生产安全和连续性至关重要。本文提出了一种基于FCEEMD多复杂度低维特征和有向无环图LSTSVM的新型故障诊断方法。应用快速互补总体经验模态分解（FCEEMD）方法对振动信号进行分解，有效降低背景噪声。然后提取非线性复杂度特征，包括样本熵（SE）、排列熵（PE）、离散熵（DE）、基尼系数、平方包络基尼系数（SEGI）和平方包络谱基尼系数（SESGI），增强对信号复杂度的捕捉。此外，使用16个时域特征和13个频域特征来表征信号，形成一个高维特征矩阵。采用具有局部保持的稳健无监督特征选择（RULSP）来识别低维敏感特征。最后，使用有向无环图（DAG）策略构建基于DAG LSTSVM的多分类器，提高故障诊断精度。对实验室轴承故障和工业止回阀故障的实验表明，诊断准确率接近100%，突出了该方法的有效性和潜力。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/253ec44a569e/entropy-26-01031-g019a.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/becf4378ccc4/entropy-26-01031-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/afa378def7d1/entropy-26-01031-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/6b2e99ac243e/entropy-26-01031-g003a.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/ccad2ffba502/entropy-26-01031-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/527eedd9ab91/entropy-26-01031-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/daebab760050/entropy-26-01031-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/bc7ea9ab4134/entropy-26-01031-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/1cd902b1d2dd/entropy-26-01031-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/857a8725edfa/entropy-26-01031-g009a.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/e42f75109f20/entropy-26-01031-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/66b273b7d465/entropy-26-01031-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/c311eb4ac6ec/entropy-26-01031-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/0424a32efe4b/entropy-26-01031-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/ea29adbd6d68/entropy-26-01031-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/c895d7635cc8/entropy-26-01031-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/bd1580b22617/entropy-26-01031-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/4d284206a976/entropy-26-01031-g017a.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/8bafd284eda1/entropy-26-01031-g018.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/253ec44a569e/entropy-26-01031-g019a.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/becf4378ccc4/entropy-26-01031-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/afa378def7d1/entropy-26-01031-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/6b2e99ac243e/entropy-26-01031-g003a.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/ccad2ffba502/entropy-26-01031-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/527eedd9ab91/entropy-26-01031-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/daebab760050/entropy-26-01031-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/bc7ea9ab4134/entropy-26-01031-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/1cd902b1d2dd/entropy-26-01031-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/857a8725edfa/entropy-26-01031-g009a.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/e42f75109f20/entropy-26-01031-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/66b273b7d465/entropy-26-01031-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/c311eb4ac6ec/entropy-26-01031-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/0424a32efe4b/entropy-26-01031-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/ea29adbd6d68/entropy-26-01031-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/c895d7635cc8/entropy-26-01031-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/bd1580b22617/entropy-26-01031-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/4d284206a976/entropy-26-01031-g017a.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/8bafd284eda1/entropy-26-01031-g018.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e7a4/11727493/253ec44a569e/entropy-26-01031-g019a.jpg

相似文献

1
A Novel Fault Diagnosis Method Using FCEEMD-Based Multi-Complexity Low-Dimensional Features and Directed Acyclic Graph LSTSVM.一种基于FCEEMD的多复杂度低维特征与有向无环图LSTSVM的新型故障诊断方法
Entropy (Basel). 2024 Nov 29;26(12):1031. doi: 10.3390/e26121031.
2
Application of FCEEMD-TSMFDE and adaptive CatBoost in fault diagnosis of complex variable condition bearings.FCEEMD - TSMFDE与自适应CatBoost在复杂变工况轴承故障诊断中的应用
Sci Rep. 2024 Dec 16;14(1):30448. doi: 10.1038/s41598-024-78845-x.
3
A Novel Bearing Multi-Fault Diagnosis Approach Based on Weighted Permutation Entropy and an Improved SVM Ensemble Classifier.基于加权排列熵和改进的 SVM 集成分类器的新型轴承多故障诊断方法。
Sensors (Basel). 2018 Jun 14;18(6):1934. doi: 10.3390/s18061934.
4
A Comprehensive Fault Diagnosis Method for Rolling Bearings Based on Refined Composite Multiscale Dispersion Entropy and Fast Ensemble Empirical Mode Decomposition.一种基于精细化复合多尺度散布熵和快速集成经验模态分解的滚动轴承综合故障诊断方法
Entropy (Basel). 2019 Jul 11;21(7):680. doi: 10.3390/e21070680.
5
A Novel Method Based on Multi-Island Genetic Algorithm Improved Variational Mode Decomposition and Multi-Features for Fault Diagnosis of Rolling Bearing.一种基于多岛遗传算法改进的变分模态分解及多特征的滚动轴承故障诊断新方法。
Entropy (Basel). 2020 Sep 7;22(9):995. doi: 10.3390/e22090995.
6
Graph Multi-Scale Permutation Entropy for Bearing Fault Diagnosis.用于轴承故障诊断的图多尺度排列熵
Sensors (Basel). 2023 Dec 21;24(1):56. doi: 10.3390/s24010056.
7
Early Fault Detection Method for Rotating Machinery Based on Harmonic-Assisted Multivariate Empirical Mode Decomposition and Transfer Entropy.基于谐波辅助多变量经验模态分解和转移熵的旋转机械早期故障检测方法
Entropy (Basel). 2018 Nov 13;20(11):873. doi: 10.3390/e20110873.
8
Fault Diagnosis for Rolling Element Bearings Based on Feature Space Reconstruction and Multiscale Permutation Entropy.基于特征空间重构和多尺度排列熵的滚动轴承故障诊断
Entropy (Basel). 2019 May 23;21(5):519. doi: 10.3390/e21050519.
9
Rotating Machinery Fault Diagnosis Based on Improved Multiscale Amplitude-Aware Permutation Entropy and Multiclass Relevance Vector Machine.基于改进的多尺度幅度感知排列熵和多类相关向量机的旋转机械故障诊断。
Sensors (Basel). 2019 Oct 18;19(20):4542. doi: 10.3390/s19204542.
10
A new fault feature extraction method of rolling bearings based on the improved self-selection ICEEMDAN-permutation entropy.一种基于改进的自选择ICEEMDAN-排列熵的滚动轴承故障特征提取新方法。
ISA Trans. 2023 Dec;143:536-547. doi: 10.1016/j.isatra.2023.09.009. Epub 2023 Sep 19.

本文引用的文献

1
Discriminative and Robust Autoencoders for Unsupervised Feature Selection.用于无监督特征选择的判别性和鲁棒自编码器
IEEE Trans Neural Netw Learn Syst. 2025 Jan;36(1):1622-1636. doi: 10.1109/TNNLS.2023.3333737. Epub 2025 Jan 7.
2
Fault diagnosis of anti-friction bearings based on Bi-dimensional ensemble local mean decomposition and optimized dynamic least square support vector machine.基于二维总体局部均值分解和优化动态最小二乘支持向量机的减摩轴承故障诊断
Sci Rep. 2023 Oct 18;13(1):17784. doi: 10.1038/s41598-023-44996-6.
3
Bearing Fault Diagnosis Method Based on Improved Singular Value Decomposition Package.
基于改进奇异值分解包的轴承故障诊断方法。
Sensors (Basel). 2023 Apr 5;23(7):3759. doi: 10.3390/s23073759.
4
A graph neural network-based bearing fault detection method.基于图神经网络的轴承故障检测方法。
Sci Rep. 2023 Mar 31;13(1):5286. doi: 10.1038/s41598-023-32369-y.
5
Nonstationary feature extraction based on stochastic resonance and its application in rolling bearing fault diagnosis under strong noise background.基于随机共振的非平稳特征提取及其在强噪声背景下滚动轴承故障诊断中的应用。
Rev Sci Instrum. 2023 Jan 1;94(1):015110. doi: 10.1063/5.0121593.
6
-Norm-Based Robust Feature Extraction Method for Fault Detection.用于故障检测的基于规范的鲁棒特征提取方法
ACS Omega. 2022 Nov 25;7(48):43440-43449. doi: 10.1021/acsomega.2c03295. eCollection 2022 Dec 6.
7
Fault Diagnosis of Balancing Machine Based on ISSA-ELM.基于 ISSA-ELM 的动平衡机故障诊断
Comput Intell Neurosci. 2022 Oct 15;2022:4981022. doi: 10.1155/2022/4981022. eCollection 2022.
8
Weak Fault Feature Extraction Method Based on Improved Stochastic Resonance.基于改进型随机共振的微弱故障特征提取方法
Sensors (Basel). 2022 Sep 2;22(17):6644. doi: 10.3390/s22176644.
9
Improved Variational Mode Decomposition and CNN for Intelligent Rotating Machinery Fault Diagnosis.用于智能旋转机械故障诊断的改进变分模态分解与卷积神经网络
Entropy (Basel). 2022 Jun 30;24(7):908. doi: 10.3390/e24070908.
10
Weak Fault Feature Extraction of Rolling Bearings Based on Adaptive Variational Modal Decomposition and Multiscale Fuzzy Entropy.基于自适应变分模态分解和多尺度模糊熵的滚动轴承微弱故障特征提取
Sensors (Basel). 2022 Jun 14;22(12):4504. doi: 10.3390/s22124504.