基于GAF-MTF-CNN的滚动轴承故障诊断

宋乾坤; 周孟然

doi:10.3969/j.issn.1671-7872.2022.04.013

基于GAF-MTF-CNN的滚动轴承故障诊断

宋乾坤¹,
周孟然²

1. 安徽理工大学人工智能学院, 安徽淮南 232001;
2. 安徽理工大学电气与信息工程学院, 安徽淮南 232001

详细信息

作者简介:
宋乾坤(1999-),男,安徽阜阳人,硕士生,主要研究方向为故障诊断。

中图分类号: TP181
计量
- 文章访问数: 263
- HTML全文浏览量: 13
- PDF下载量: 26
出版历程
- 收稿日期: 2022-02-27
- 网络出版日期: 2022-10-26
- 刊出日期: 2022-10-29

Fault Diagnosis of Rolling Bearings Based on GAF-MTF-CNN

SONG Qiankun¹,
ZHOU Mengran²

1. School of Artificial Intelligence, Anhui University of Science and Technology, Huainan 232001, China;
2. School of Electrical and Information Engineering, Anhui University of Science and Technology, Huainan 232001, China

摘要

摘要: 针对传统图像编码方式与神经网络轴承故障诊断方法测试准确率不高、模型泛化能力差等问题，提出一种基于格拉姆角场(GAF)和马尔可夫变迁场(MTF)与卷积神经网络(CNN)的滚动轴承故障诊断方法。对采样的每段轴承振动数据分别进行 GAF和 MTF变换生成二维图像，对其采用水平方向拼接的方法构建数据集，再将其导入搭建的加入批量归一化及随机失活操作的多层CNN中进行诊断测试。结果表明：相比于仅用GAF和MTF的数据处理方法，采用本文数据处理方法构建的数据集在搭建的 CNN中训练出的模型测试准确率高，可达 99.87%，搭建的 CNN有较好的泛化能力与较高的网络模型准确率，证明了本文数据集构建方法在轴承故障诊断中的可行性。
- 格拉姆角场(GAF) /
- 马尔可夫变迁场(MTF) /
- 卷积神经网络(CNN) /
- 滚动轴承 /
- 故障诊断
Abstract: Aiming at the problems of low test accuracy and poor model generalization ability of traditional image coding method and neural network method for bearing fault diagnosis, a rolling bearing fault diagnosis method based on Gramian angular field (GAF), Markov transition field (MTF) and convolutional neural network (CNN) was proposed. GAF and MTF transformation were performed on the sampled vibration data of each section of bearing to generate two-dimensional images, and the data set was constructed by horizontal stitching method, and then it was imported into the multi-layer CNN with batch normalization and random inactivation operation for diagnostic testing. The results show that, compared with the data processing method using only GAF and MTF, the data set constructed by the data processing method in this paper has a high accuracy of model test trained in the built CNN, up to 99.87%. The built CNN has good generalization ability and high accuracy of network model, which proves the feasibility of the data set construction method in bearing fault diagnosis.
- Gramian angular field (GAF) /
- Markov transition field (MTF) /
- convolutional neural network (CNN) /
- rolling bearing /
- fault diagnosis

HTML全文

下载: 全尺寸图片幻灯片

参考文献(21)

[1]	赵志宏,杨绍普.基于小波包变换与样本熵的滚动轴承故障诊断[J].振动、测试与诊断,2012, 32(4):640-644.
[2]	徐卫晓,谭继文,温国强.滚动轴承故障信号处理方法与诊断试验研究[J].机床与液压,2014(17):182-186.
[3]	QU J, ZHANG Z, GONG T. A novel intelligent method for mechanical fault diagnosis based on dual-tree complex wavelet packet transform and multiple classifier fusion[J]. Neurocomputing, 2016, 171(c):837-853.
[4]	詹君,程龙生,彭宅铭.基于VMD和改进多分类马田系统的滚动轴承故障智能诊断[J].振动与冲击,2020, 39(2):32-39.
[5]	SHAO H, JIANG H, ZHANG X, et al.Rolling bearing fault diagnosis using an optimization deep belief network[J].Measurement Science and Technology, 2015, 26(11):115002.
[6]	李恒,张氢,秦仙蓉,等.基于短时傅里叶变换和卷积神经网络的轴承故障诊断方法[J].振动与冲击,2018, 37(19):124-131.
[7]	LU C, WANG Y, RAGULSKTS M, et a1. Fault diagnosis for rotating machinery:a method based on image processing[J]. Plos One, 2016, 11(10):e0164111.
[8]	孙岩,彭高亮.改进胶囊网络的滚动轴承故障诊断方法[J].哈尔滨工业大学学报,2021, 53(1):23-28.
[9]	仝钰,庞新宇,魏子涵.基于GADF-CNN的滚动轴承故障诊断方法[J].振动与冲击,2021, 40(5):247-253.
[10]	曹洁,马佳林,黄黛麟,等.一种基于多通道马尔可夫变迁场的故障诊断方法[J].吉林大学学报(工学版),2022, 52(2):491-496.
[11]	LIU L, WANG Z. Encoding temporal markov dynamics in graph for time series visualization[J/OL]. CoRR, 2016, abs/1610.07273.(2016-01-01)[2022-02-28]. https://kns.cnki.net/kcms/detail/detail.aspx?FileName=DBLPAE567356DBC62FBB641F9DD57E12EE85&DbName=GARJ2016.
[12]	IOFFE S, SZEGEDY C. Batch normalization:accelerating deep network training by reducing internal covariate shift[J/OL]. CoRR, 2015, abs/1502.03167.(2015-01-01)[2022-02-28]. https://kns.cnki.net/kcms/detail/detail.aspx?FileName=DBLPB1DF658B6FEE6BCFD4FCF7D3B0BB4C31&DbName=GARJ2015.
[13]	HINTON G E, SRIVASTAVA N, KRIZHEVSKY A, et al. Improving neural networks by preventing co-adaptation of feature detectors[J].Computer Science, 2012, 3(4):212-223.
[14]	KINGMA D, BA J. ADAM:a method for stochastic optimization[J]. CoRR, 2014, abs/1412.6980.(2015-01-01)[2022-02-28]. https://kns.cnki.net/kcms/detail/detail.aspx?FileName=DBLPBF860593E28DFDD9E5C947B61AEA9499&DbName=GARJ2014.
[15]	程军圣,史美丽,杨宇.基于LMD与神经网络的滚动轴承故障诊断方法[J].振动与冲击,2010, 29(8):141-144.
[16]	YU Y, JUN S C. A roller bearing fault diagnosis method based on EMD energy entropy and ANN[J]. Journal of Sound and Vibration, 2006, 294(1/2):269-277.
[17]	ZHANG Q, CHEN S, FAN Z P. Bearing fault diagnosis based on improved particle swarm optimized VMD and SVM models[J]. Advances in Mechanical Engineering, 2021, 13(6):1-12.
[18]	任朝晖,于天壮,丁东,等.基于VMD-DBN的滚动轴承故障诊断方法[J].东北大学学报(自然科学版),2021, 42(8):1105-1110.
[19]	谷玉海,朱腾腾,饶文军,等.基于EMD二值化图像和CNN的滚动轴承故障诊断[J].振动、测试与诊断,2021, 41(1):105-113.
[20]	薛妍,沈宁,窦东阳.基于一维卷积神经网络的滚动轴承故障程度诊断[J].轴承,2021(4):48-54.
[21]	赵凯辉,吴思成,李涛,等.基于Inception-BLSTM的滚动轴承故障诊断方法研究[J].振动与冲击,2021, 40(17):290-297.

施引文献(6)

期刊类型引用(2)

1.	李俊卿，刘若尧，何玉灵. 基于NGO-VMD和改进GoogLeNet的齿轮箱故障诊断方法. 机床与液压. 2024(12): 193-201 . 百度学术
2.	范佳鹏，陈曦晖，李勇，陈志帮，邢子豪. 基于MTF和AM-MSCNN的滚动轴承故障诊断方法. 轴承. 2024(12): 74-79 . 百度学术