BEARING FAULT DIAGNOSIS METHOD BASED ON MULTI⁃SCALE AND MULTI⁃PATH ENSEMBLE NETWORK

QI BoWei; LI YuanYuan; SONG LiYuan

doi:10.16579/j.issn.1001.9669.2024.04.003

您当前的位置：

首页 >

文章列表页 >

BEARING FAULT DIAGNOSIS METHOD BASED ON MULTI⁃SCALE AND MULTI⁃PATH ENSEMBLE NETWORK

Vibration · Noise · Monitoring · Diagnosis | 更新时间：2024-12-26

- BEARING FAULT DIAGNOSIS METHOD BASED ON MULTI⁃SCALE AND MULTI⁃PATH ENSEMBLE NETWORK
- Journal of Mechanical Strength Vol. 46, Issue 4, Pages: 778-786(2024)
- 作者机构：
  
  1. 上海工程技术大学电子电气工程学院
- 作者简介：
- 基金信息：
- DOI：10.16579/j.issn.1001.9669.2024.04.003
  CLC： TH133
- Published：15 August 2024，
- 稿件说明：
移动端阅览
QI BOWEI, LI YUANYUAN, SONG LIYUAN. BEARING FAULT DIAGNOSIS METHOD BASED ON MULTI⁃SCALE AND MULTI⁃PATH ENSEMBLE NETWORK. [J]. Journal of mechanical strength , 2024, 46(4): 778-786.
DOI：

QI BOWEI, LI YUANYUAN, SONG LIYUAN. BEARING FAULT DIAGNOSIS METHOD BASED ON MULTI⁃SCALE AND MULTI⁃PATH ENSEMBLE NETWORK. [J]. Journal of mechanical strength , 2024, 46(4): 778-786. DOI： 10.16579/j.issn.1001.9669.2024.04.003.

摘要

针对卷积神经网络参数量大、层数深、泛化性能弱的问题

提出了一种基于多尺度多路径集成网络(Multi⁃scale Multi⁃path Convolutional Neural Network

MCS⁃CNN)的轴承故障诊断方法。首先

提出多尺度卷积块

利用深度卷积和逐点卷积来降低网络参数量、增加网络宽度

有效提取多尺度特征;其次

提出集成块

利用多路径的连接方式将低级和高级特征连接起来以增加网络深度

进而提高模型诊断精度;最后

在凯斯西储大学轴承数据集上进行验证。结果表明

在高噪声和跨负载场景下的故障诊断精度分别可达97.5%和98.25%

在混合场景下相较于现有的诊断方法精度提高了15百分点以上

有效表明了此方法的鲁棒性和泛化性。

Abstract

To address the problems such as complex convolutional neural network parameters

deep layers and weak generalization performance

a multi⁃scale multi⁃path convolutional neural network(MCS⁃CNN)based bearing fault diagnosis method cas proposed.Firstly

a multi⁃scale convolution block was proposed to reduce the number of network parameters and increase the network width by using depthwise convolution and pointwise convolution

so as to extract multi⁃scale features effectively.Secondly

an ensemble block was proposed to increase the network depth by connecting low⁃level and high⁃level features through multiple paths

thereby improving the diagnostic accuracy of the model.Finally

the effectiveness of the method was verified on the Case Western Reserve University bearing dataset.The results show that the fault diagnosis accuracy of the proposed method can reach 975%and 9825%in high⁃noise and cross⁃load scenarios

and the accuracy in mixed scenarios is improved by more than 15%compared to existing diagnosis methods

which prove the robustness and generalisability of the proposed method.

关键词

轴承卷积神经网络多尺度多路径故障诊断集成网络

Keywords

BearingConvolution neural networkMulti-scale and multi-pathFault diagnosisEnsemble network

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

RESEARCH ON ROLLING BEARING FAULT DIAGNOSIS BASED ON MA OPTIMIZATION OF CNN

Bearing fault diagnosis method based on improved compressed sensing and deep multi-kernel extreme learning machine

RESEARCH ABOUT FAULT DIAGNOSIS OF BEARING BASED ON INSTRINSIC TIME SCALE DECOMPOSITION AND CONVOLUTIONAL NEURAL NETWORK

NEW METHOD FOR BEARING INTELLIGENT DIAGNOSIS BASED ON COMPRESSED SENSING AND MULTILAYER EXTREME LEARNING MACHINE

FAULT DIAGNOSIS METHOD OF ROLLING BEARING BASED ON EEMD-CNN

Related Author

TIAN LiYong

ZHAO JianJun

YU Ning

FU Qiang

HU Dong

YANG Tongliang

LUO Guoqing

TAN Weimin

Related Institution

School of Mechanical Engineering,Liaoning Technical University

College of Engineering and Technology, Southwest University

Energy and Power Engineering Institute,University of Shanghai for Science and Technology

Shanghai Key Laboratory of Multiphase Flow and Heat Transfer in Power Engineering

School of Mechanical Engineering,University of Dalian

⁰