• 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

机器学习 ICA-VMD 在低信噪比环境中的智能诊断系统中的应用。

The Application of Machine Learning ICA-VMD in an Intelligent Diagnosis System in a Low SNR Environment.

机构信息

Graduate Institute of Vehicle Engineering, National Changhua University of Education, No. 1, Jin-De Road, Changhua City 50007, Taiwan.

出版信息

Sensors (Basel). 2021 Dec 14;21(24):8344. doi: 10.3390/s21248344.

DOI:10.3390/s21248344
PMID:34960438
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC8708876/
Abstract

This paper proposes a new method called independent component analysis-variational mode decomposition (ICA-VMD), which combines ICA and VMD. The purpose is to study the application of ICA-VMD in low signal-to-noise ratio (SNR) signal processing and data analysis. ICA is a very important method in the field of machine learning. It is an unsupervised learning algorithm that can dig out the independent factors hidden in the observation signal. The VMD method estimates each signal component by solving the frequency domain variational optimization problem, and it is very suitable for mechanical fault diagnosis. The advantage of ICA-VMD is that it requires two sensory cues to distinguish the original source from the unwanted noise. In the three cases studied here, the original source was first contaminated by white Gaussian noise. The three cases in this study are under different SNR conditions. The SNR in the first case is -6.46 dB, the SNR in the second case is -21.3728, and the SNR in the third case is -46.8177. The simulation results show that the ICA-VMD method can effectively recover the original source from the contaminated data. It is hoped that, in the future, there will be new discoveries and advances in science and technology to solve the noise interference problem through this method.

摘要

本文提出了一种新的方法，称为独立成分分析-变分模态分解（ICA-VMD），它结合了 ICA 和 VMD。目的是研究 ICA-VMD 在低信噪比（SNR）信号处理和数据分析中的应用。ICA 是机器学习领域非常重要的方法。它是一种无监督学习算法，可以挖掘出隐藏在观测信号中的独立因素。VMD 方法通过求解频域变分优化问题来估计每个信号分量，非常适合机械故障诊断。ICA-VMD 的优点在于它需要两个感官线索来区分原始信号和不需要的噪声。在本研究中，研究了三种情况，第一种情况是原始信号首先被高斯白噪声污染。本研究中的三种情况是在不同 SNR 条件下进行的。第一种情况下的 SNR 为-6.46dB，第二种情况下的 SNR 为-21.3728，第三种情况下的 SNR 为-46.8177。仿真结果表明，ICA-VMD 方法可以有效地从污染数据中恢复原始信号。希望未来能够在科学技术上有新的发现和进步，通过这种方法解决噪声干扰问题。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/6997345e7e67/sensors-21-08344-g025.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/eaf804e072aa/sensors-21-08344-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/dcdc0b40adf7/sensors-21-08344-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/374462dfdb13/sensors-21-08344-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/ff52a9f85087/sensors-21-08344-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/e42da666595c/sensors-21-08344-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/ea35ea0f0dc5/sensors-21-08344-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/a3a782368097/sensors-21-08344-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/abae813c923e/sensors-21-08344-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/37ff37059dc2/sensors-21-08344-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/9c05dc3a7d04/sensors-21-08344-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/78497671249d/sensors-21-08344-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/76495e6eeca7/sensors-21-08344-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/f1aa644341d4/sensors-21-08344-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/43fb6d17ab12/sensors-21-08344-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/dd8aa99008af/sensors-21-08344-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/bcf0f528705b/sensors-21-08344-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/f902035375ad/sensors-21-08344-g017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/6e642e5fe920/sensors-21-08344-g018.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/1708afa09636/sensors-21-08344-g019.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/9abca220b401/sensors-21-08344-g020.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/854d9496a2e2/sensors-21-08344-g021.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/9bcdfecde557/sensors-21-08344-g022.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/7440d34c441e/sensors-21-08344-g023.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/02e4de666184/sensors-21-08344-g024.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/6997345e7e67/sensors-21-08344-g025.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/eaf804e072aa/sensors-21-08344-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/dcdc0b40adf7/sensors-21-08344-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/374462dfdb13/sensors-21-08344-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/ff52a9f85087/sensors-21-08344-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/e42da666595c/sensors-21-08344-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/ea35ea0f0dc5/sensors-21-08344-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/a3a782368097/sensors-21-08344-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/abae813c923e/sensors-21-08344-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/37ff37059dc2/sensors-21-08344-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/9c05dc3a7d04/sensors-21-08344-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/78497671249d/sensors-21-08344-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/76495e6eeca7/sensors-21-08344-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/f1aa644341d4/sensors-21-08344-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/43fb6d17ab12/sensors-21-08344-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/dd8aa99008af/sensors-21-08344-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/bcf0f528705b/sensors-21-08344-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/f902035375ad/sensors-21-08344-g017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/6e642e5fe920/sensors-21-08344-g018.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/1708afa09636/sensors-21-08344-g019.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/9abca220b401/sensors-21-08344-g020.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/854d9496a2e2/sensors-21-08344-g021.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/9bcdfecde557/sensors-21-08344-g022.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/7440d34c441e/sensors-21-08344-g023.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/02e4de666184/sensors-21-08344-g024.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5b02/8708876/6997345e7e67/sensors-21-08344-g025.jpg

相似文献

1
The Application of Machine Learning ICA-VMD in an Intelligent Diagnosis System in a Low SNR Environment.机器学习 ICA-VMD 在低信噪比环境中的智能诊断系统中的应用。
Sensors (Basel). 2021 Dec 14;21(24):8344. doi: 10.3390/s21248344.
2
Research on Fault Diagnosis of Gearbox with Improved Variational Mode Decomposition.基于改进变分模态分解的齿轮箱故障诊断研究。
Sensors (Basel). 2018 Oct 18;18(10):3510. doi: 10.3390/s18103510.
3
Research on Fault Diagnosis of Rolling Bearings Based on Variational Mode Decomposition Improved by the Niche Genetic Algorithm.基于小生境遗传算法改进的变分模态分解的滚动轴承故障诊断研究
Entropy (Basel). 2022 Jun 14;24(6):825. doi: 10.3390/e24060825.
4
EMG Signal Filtering Based on Variational Mode Decomposition and Sub-Band Thresholding.基于变分模态分解和子带阈值处理的肌电图信号滤波
IEEE J Biomed Health Inform. 2021 Jan;25(1):47-58. doi: 10.1109/JBHI.2020.2987528. Epub 2021 Jan 5.
5
A solution for co-frequency and low SNR problems in heart rate estimation based on photoplethysmography signals.一种基于光电容积脉搏波信号的心率估计中同频和低信噪比问题的解决方案。
Med Biol Eng Comput. 2022 Dec;60(12):3419-3433. doi: 10.1007/s11517-022-02678-x. Epub 2022 Oct 3.
6
Rolling Bearing Fault Diagnosis Based on WGWOA-VMD-SVM.基于 WGWOA-VMD-SVM 的滚动轴承故障诊断。
Sensors (Basel). 2022 Aug 21;22(16):6281. doi: 10.3390/s22166281.
7
Application of sparsity-oriented VMD for gearbox fault diagnosis based on built-in encoder information.基于内置编码器信息的面向稀疏性的变分模态分解在齿轮箱故障诊断中的应用
ISA Trans. 2020 Apr;99:496-504. doi: 10.1016/j.isatra.2019.10.005. Epub 2019 Oct 11.
8
Empirical Variational Mode Decomposition Based on Binary Tree Algorithm.基于二叉树算法的经验模态分解。
Sensors (Basel). 2022 Jun 30;22(13):4961. doi: 10.3390/s22134961.
9
A Novel Deep Transfer Learning Method for Intelligent Fault Diagnosis Based on Variational Mode Decomposition and Efficient Channel Attention.一种基于变分模态分解和高效通道注意力的智能故障诊断深度迁移学习新方法。
Entropy (Basel). 2022 Aug 6;24(8):1087. doi: 10.3390/e24081087.
10
Research on Ship-Radiated Noise Denoising Using Secondary Variational Mode Decomposition and Correlation Coefficient.基于二次变分模态分解和相关系数的舰船辐射噪声去噪研究
Sensors (Basel). 2017 Dec 26;18(1):48. doi: 10.3390/s18010048.

引用本文的文献

1
Bearing Fault Feature Extraction Method Based on Enhanced Differential Product Weighted Morphological Filtering.基于增强型差分积加权形态滤波的轴承故障特征提取方法
Sensors (Basel). 2022 Aug 18;22(16):6184. doi: 10.3390/s22166184.
2
Multi-Sensor Fusion by CWT-PARAFAC-IPSO-SVM for Intelligent Mechanical Fault Diagnosis.基于 CWT-PARAFAC-IPSO-SVM 的多传感器融合智能机械故障诊断。
Sensors (Basel). 2022 May 10;22(10):3647. doi: 10.3390/s22103647.

本文引用的文献

1
Intelligent Fault Diagnosis and Forecast of Time-Varying Bearing Based on Deep Learning VMD-DenseNet.基于深度学习 VMD-DenseNet 的时变轴承智能故障诊断与预测。
Sensors (Basel). 2021 Nov 10;21(22):7467. doi: 10.3390/s21227467.
2
Application Combining VMD and ResNet101 in Intelligent Diagnosis of Motor Faults.应用 VMD 和 ResNet101 于电机故障智能诊断。
Sensors (Basel). 2021 Sep 10;21(18):6065. doi: 10.3390/s21186065.
3
On the Performance of Variational Mode Decomposition-Based Radio Frequency Fingerprinting of Bluetooth Devices.
基于变分模态分解的蓝牙设备射频指纹识别性能研究
Sensors (Basel). 2020 Mar 19;20(6):1704. doi: 10.3390/s20061704.
4
Data analysis using a combination of independent component analysis and empirical mode decomposition.使用独立成分分析和经验模态分解相结合的数据分析方法。
Phys Rev E Stat Nonlin Soft Matter Phys. 2009 Jun;79(6 Pt 2):066705. doi: 10.1103/PhysRevE.79.066705. Epub 2009 Jun 12.
5
Image coding using wavelet transform.基于小波变换的图像编码。
IEEE Trans Image Process. 1992;1(2):205-20. doi: 10.1109/83.136597.
6
The cocktail party problem.鸡尾酒会问题。
Neural Comput. 2005 Sep;17(9):1875-902. doi: 10.1162/0899766054322964.
7
Network component analysis: reconstruction of regulatory signals in biological systems.网络组件分析：生物系统中调控信号的重建
Proc Natl Acad Sci U S A. 2003 Dec 23;100(26):15522-7. doi: 10.1073/pnas.2136632100. Epub 2003 Dec 12.
8
Learning overcomplete representations.学习超完备表示。
Neural Comput. 2000 Feb;12(2):337-65. doi: 10.1162/089976600300015826.
9
Natural gradient learning for over- and under-complete bases In ICA.独立成分分析中用于过完备和欠完备基的自然梯度学习
Neural Comput. 1999 Nov 15;11(8):1875-83. doi: 10.1162/089976699300015990.
10
Independent component analysis using an extended infomax algorithm for mixed subgaussian and supergaussian sources.使用扩展信息最大化算法对混合次高斯和超高斯源进行独立成分分析。
Neural Comput. 1999 Feb 15;11(2):417-41. doi: 10.1162/089976699300016719.