• 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

基于声发射信号和改进多特征融合卷积神经网络的可倾瓦推力轴承故障诊断

Tilting Pad Thrust Bearing Fault Diagnosis Based on Acoustic Emission Signal and Modified Multi-Feature Fusion Convolutional Neural Network.

作者信息

Mao Meijiao, Jiang Zhiwen, Tan Zhifei, Xiao Wenqiang, Du Guangchao

机构信息

School of Mechanical Engineering and Mechanics, Xiangtan University, Xiangtan 411105, China.

Engineering Research Center of Complex Trajectory Machining Process and Equipment, Ministry of Education, Xiangtan University, Xiangtan 411105, China.

出版信息

Sensors (Basel). 2025 Feb 2;25(3):904. doi: 10.3390/s25030904.

DOI:10.3390/s25030904
PMID:39943544
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11820162/
Abstract

Tilting pad thrust bearings are widely utilized in large rotating machinery such as steam turbines and hydraulic turbines. Defects in their shaft tiles directly impact lubrication characteristics, thereby influencing the overall safety performance of the entire unit. To address this issue, this paper presents a fault diagnosis method for tilting pad thrust bearings using a modified multi-feature fused convolutional neural network (MMFCNN). Initially, an experimental bench for diagnosing faults in tilting pad thrust bearings was developed to collect multi-channel acoustic emission (AE) signals from both normal and faulty pads. Subsequently, the squeeze-and-excitation (SE) module was employed to reallocate the weights of each channel and fuse the features of multi-channel signals. Learning was then conducted on the signal fused with multiple features using the inverse-add module and spanning convolution. Next, a comparative analysis was carried out among the CNN1D, ResNet, and DFCNN models, and the MMFCNN model proposed in this study. The results show that under consistent operating conditions, the MMFCNN model achieves an average fault diagnosis accuracy of 99.58% when utilizing AE signal data from tilting pad thrust bearings in four states as inputs. Furthermore, when different operational conditions are introduced, the MMFCNN model also outperforms other models in terms of accuracy.

摘要

可倾瓦推力轴承广泛应用于汽轮机和水轮机等大型旋转机械中。其轴瓦缺陷直接影响润滑特性,进而影响整个机组的整体安全性能。为解决这一问题,本文提出一种基于改进的多特征融合卷积神经网络(MMFCNN)的可倾瓦推力轴承故障诊断方法。首先,搭建了可倾瓦推力轴承故障诊断实验台,用于采集正常和故障轴瓦的多通道声发射(AE)信号。随后,采用挤压激励(SE)模块对各通道权重进行重新分配,并融合多通道信号特征。然后利用逆加法模块和跨度卷积对融合了多个特征的信号进行学习。接下来,对一维卷积神经网络(CNN1D)、残差网络(ResNet)、深度可分离卷积神经网络(DFCNN)模型以及本文提出的MMFCNN模型进行了对比分析。结果表明,在相同运行条件下,以可倾瓦推力轴承四种状态的AE信号数据作为输入时,MMFCNN模型的平均故障诊断准确率达到99.58%。此外,在引入不同运行条件时,MMFCNN模型在准确率方面也优于其他模型。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/bee1449073bd/sensors-25-00904-g017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/4dc60c8dbed3/sensors-25-00904-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/ea4c251f60b6/sensors-25-00904-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/578c64fd3bb2/sensors-25-00904-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/13648f0142fc/sensors-25-00904-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/3140bbe7ec2f/sensors-25-00904-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/6cb15bbf5c79/sensors-25-00904-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/90eae81597d1/sensors-25-00904-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/e7ed1e4d486c/sensors-25-00904-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/3a3e23ad7185/sensors-25-00904-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/9987026aeac3/sensors-25-00904-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/822b17b1370f/sensors-25-00904-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/023b8b5627eb/sensors-25-00904-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/713a10e0ac47/sensors-25-00904-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/b81a5e7b5116/sensors-25-00904-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/d6c295b43fcd/sensors-25-00904-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/2af9b678b565/sensors-25-00904-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/bee1449073bd/sensors-25-00904-g017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/4dc60c8dbed3/sensors-25-00904-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/ea4c251f60b6/sensors-25-00904-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/578c64fd3bb2/sensors-25-00904-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/13648f0142fc/sensors-25-00904-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/3140bbe7ec2f/sensors-25-00904-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/6cb15bbf5c79/sensors-25-00904-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/90eae81597d1/sensors-25-00904-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/e7ed1e4d486c/sensors-25-00904-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/3a3e23ad7185/sensors-25-00904-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/9987026aeac3/sensors-25-00904-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/822b17b1370f/sensors-25-00904-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/023b8b5627eb/sensors-25-00904-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/713a10e0ac47/sensors-25-00904-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/b81a5e7b5116/sensors-25-00904-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/d6c295b43fcd/sensors-25-00904-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/2af9b678b565/sensors-25-00904-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8f37/11820162/bee1449073bd/sensors-25-00904-g017.jpg

相似文献

1
Tilting Pad Thrust Bearing Fault Diagnosis Based on Acoustic Emission Signal and Modified Multi-Feature Fusion Convolutional Neural Network.基于声发射信号和改进多特征融合卷积神经网络的可倾瓦推力轴承故障诊断
Sensors (Basel). 2025 Feb 2;25(3):904. doi: 10.3390/s25030904.
2
Enhanced Feature Extraction Network Based on Acoustic Signal Feature Learning for Bearing Fault Diagnosis.基于声学信号特征学习的增强型特征提取网络用于轴承故障诊断
Sensors (Basel). 2023 Oct 25;23(21):8703. doi: 10.3390/s23218703.
3
The Fault Diagnosis of Rolling Bearings Is Conducted by Employing a Dual-Branch Convolutional Capsule Neural Network.采用双分支卷积胶囊神经网络进行滚动轴承的故障诊断。
Sensors (Basel). 2024 May 24;24(11):3384. doi: 10.3390/s24113384.
4
Bearing fault diagnosis based on wavelet sparse convolutional network and acoustic emission compression signals.基于小波稀疏卷积网络和声发射压缩信号的轴承故障诊断
Math Biosci Eng. 2022 Jun 2;19(8):8057-8080. doi: 10.3934/mbe.2022377.
5
Bearing Fault Diagnosis with a Feature Fusion Method Based on an Ensemble Convolutional Neural Network and Deep Neural Network.基于集成卷积神经网络和深度神经网络的特征融合方法的轴承故障诊断
Sensors (Basel). 2019 Apr 30;19(9):2034. doi: 10.3390/s19092034.
6
Intelligent Diagnosis of Rolling Bearings Fault Based on Multisignal Fusion and MTF-ResNet.基于多信号融合与MTF-ResNet的滚动轴承故障智能诊断
Sensors (Basel). 2023 Jul 10;23(14):6281. doi: 10.3390/s23146281.
7
Fault Diagnosis Method for Centrifugal Pumps in Nuclear Power Plants Based on a Multi-Scale Convolutional Self-Attention Network.基于多尺度卷积自注意力网络的核电站离心泵故障诊断方法
Sensors (Basel). 2025 Mar 5;25(5):1589. doi: 10.3390/s25051589.
8
Multi-Domain Entropy-Random Forest Method for the Fusion Diagnosis of Inter-Shaft Bearing Faults with Acoustic Emission Signals.基于声发射信号的多域熵-随机森林法用于中间轴轴承故障融合诊断
Entropy (Basel). 2019 Dec 31;22(1):57. doi: 10.3390/e22010057.
9
Convolutional Neural Network with Attention Mechanism and Visual Vibration Signal Analysis for Bearing Fault Diagnosis.基于注意力机制的卷积神经网络与视觉振动信号分析在轴承故障诊断中的应用
Sensors (Basel). 2024 Mar 13;24(6):1831. doi: 10.3390/s24061831.
10
Intelligent Fault Diagnosis of Hydraulic Multi-Way Valve Using the Improved SECNN-GRU Method with mRMR Feature Selection.基于mRMR特征选择的改进型SECNN-GRU方法的液压多路阀智能故障诊断
Sensors (Basel). 2023 Nov 23;23(23):9371. doi: 10.3390/s23239371.

引用本文的文献

1
Fault Diagnosis of Rolling Bearings Based on HFMD and Dual-Branch Parallel Network Under Acoustic Signals.基于声信号下的手足口病和双分支并行网络的滚动轴承故障诊断
Sensors (Basel). 2025 Aug 28;25(17):5338. doi: 10.3390/s25175338.
2
Bearing Fault Diagnosis Based on Time-Frequency Dual Domains and Feature Fusion of ResNet-CACNN-BiGRU-SDPA.基于时频双域和ResNet-CACNN-BiGRU-SDPA特征融合的轴承故障诊断
Sensors (Basel). 2025 Jun 21;25(13):3871. doi: 10.3390/s25133871.
3
A Digital Signal Processing-Based Multi-Channel Acoustic Emission Acquisition System with a Simplified Analog Front-End.

本文引用的文献

1
A Method for the Pattern Recognition of Acoustic Emission Signals Using Blind Source Separation and a CNN for Online Corrosion Monitoring in Pipelines with Interference from Flow-Induced Noise.一种利用盲源分离和卷积神经网络进行声发射信号模式识别的方法,用于在线监测存在流动噪声干扰的管道腐蚀情况。
Sensors (Basel). 2024 Sep 15;24(18):5991. doi: 10.3390/s24185991.
2
ResNet and its application to medical image processing: Research progress and challenges.ResNet 及其在医学图像处理中的应用:研究进展与挑战。
Comput Methods Programs Biomed. 2023 Oct;240:107660. doi: 10.1016/j.cmpb.2023.107660. Epub 2023 Jun 8.
3
A Fault Diagnosis Approach for Rolling Bearing Integrated SGMD, IMSDE and Multiclass Relevance Vector Machine.
一种具有简化模拟前端的基于数字信号处理的多通道声发射采集系统。
Sensors (Basel). 2025 May 20;25(10):3206. doi: 10.3390/s25103206.
4
Fault Diagnosis Method for Main Pump Motor Shielding Sleeve Based on Attention Mechanism and Multi-Source Data Fusion.基于注意力机制和多源数据融合的主泵电机屏蔽套故障诊断方法
Sensors (Basel). 2025 Mar 13;25(6):1775. doi: 10.3390/s25061775.
一种基于集成SGMD、IMSDE和多类相关向量机的滚动轴承故障诊断方法
Sensors (Basel). 2020 Aug 4;20(15):4352. doi: 10.3390/s20154352.
4
Real-Time Patient-Specific ECG Classification by 1-D Convolutional Neural Networks.基于一维卷积神经网络的实时患者特异性心电图分类
IEEE Trans Biomed Eng. 2016 Mar;63(3):664-75. doi: 10.1109/TBME.2015.2468589. Epub 2015 Aug 14.
5
Interfacial Aspects of Electrodeposited Carbon Fiber-Reinforced Epoxy Composites Using Monomeric and Polymeric Coupling Agents.使用单体和聚合物偶联剂的电沉积碳纤维增强环氧树脂复合材料的界面特性
J Colloid Interface Sci. 2000 Nov 1;231(1):114-128. doi: 10.1006/jcis.2000.7113.