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

TIAN LiYong; ZHAO JianJun; YU Ning

doi:10.16579/j.issn.1001.9669.2024.04.005

您当前的位置：

首页 >

文章列表页 >

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

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

- RESEARCH ON ROLLING BEARING FAULT DIAGNOSIS BASED ON MA OPTIMIZATION OF CNN
- Journal of Mechanical Strength Vol. 46, Issue 4, Pages: 795-801(2024)
- 作者机构：
  
  1. 辽宁工程技术大学机械工程学院
- 作者简介：
- 基金信息：
- DOI：10.16579/j.issn.1001.9669.2024.04.005
  CLC： TH133.3
- Published：15 August 2024，
- 稿件说明：
移动端阅览
TIAN LIYONG, ZHAO JIANJUN, YU NING. RESEARCH ON ROLLING BEARING FAULT DIAGNOSIS BASED ON MA OPTIMIZATION OF CNN. [J]. Journal of mechanical strength , 2024, 46(4): 795-801.
DOI：

TIAN LIYONG, ZHAO JIANJUN, YU NING. RESEARCH ON ROLLING BEARING FAULT DIAGNOSIS BASED ON MA OPTIMIZATION OF CNN. [J]. Journal of mechanical strength , 2024, 46(4): 795-801. DOI： 10.16579/j.issn.1001.9669.2024.04.005.

摘要

针对基于卷积神经网络(Convolution Neural Network

CNN)的滚动轴承状态识别中超参数选用对于人工经验的高度依赖性问题

提出一种基于蜉蝣算法(Mayfly Algorithm

MA)优化CNN的故障诊断模型CNN⁃MA。首先

该模型利用MA强大的寻优能力

以CNN的诊断精度作为优化目标

自适应调节CNN中的超参数;其次

采用归一化后的原始信号图像集

尽可能保留了信号的特征;最后

为了评估参数在优化模型中的有效性

与粒子群优化(Particle Swarm Optimization

PSO)算法的CNN模型进行对比。所提模型拥有更稳定的性能和更高的识别精度

同时具备良好的抗噪能力

充分显示了在滚动轴承故障诊断应用中的可行性和可靠性。

Abstract

Aiming at the high dependence of super parameter selection on artificial experience in rolling bearing state identification based on convolution neural network(CNN)

a fault diagnosis model(CNN⁃MA)based on mayfly algorithm(MA)was proposed.Firstly

the model used the powerful optimization ability of MA

took the diagnostic accuracy of CNN as the optimization objective

and adaptively adjusted the super parameters in CNN.Secondly

the normalized original signal image set was used to preserve the characteristics of the signal as much as possible.Finally

in order to evaluate the effectiveness of the parameters in the optimization model

compared with the CNN model optimized by particle swarm optimization(PSO)algorithm.The results show that the proposed model has more stable performance

higher recognition accuracy and good anti⁃noise ability.It fully shows the feasibility and reliability of CNN⁃MA model in fault diagnosis of rolling bearings.

关键词

卷积神经网络蜉蝣算法滚动轴承故障诊断

Keywords

Convolution neural networkMayfly algorithmRolling bearingFault diagnosis

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

FAULT DIAGNOSIS OF ROLLING BEARINGS BASED ON SDP AND IMPROVED SAM⁃MobileNetv2

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

ROLLING BEARING FAULT DIAGNOSIS MЕТHOD BASED ON MORLET WAVELET AND CART DECISION TREE

WIND TURBINE ROLLING BEARING FAULT DIAGNOSIS METHOD BASED ON 1D-CNN AND SWLSTM

ROLLING BEARING FAULT DIAGNOSIS BASED ON FUSION CNN AND PSO-SVM

Related Author

ZHANG TianYuan

SUN HuEr

ZHU JiYang

ZHAO Yang

QI BoWei

LI YuanYuan

SONG LiYuan

LIU JunLi

Related Institution

School of Mechanical Engineering,North University of China

School of Electronic and Electrical Engineering,Shanghai University of Engineering Science

西南交通大学牵引动力国家重点实验室

五邑大学轨道交通学院

School of Information and Intelligence, Xiangxi National Vocational and Technical College

⁰