基于ARCN模型的轴承故障诊断

梁海涛; 王立纲; 王亮; 张庆峰

doi:10.13224/j.cnki.jasp.20210186

基于ARCN模型的轴承故障诊断

doi: 10.13224/j.cnki.jasp.20210186

1.
四川三星通用航空有限责任公司机务工程部，成都 610051
2.
中国民用航空飞行学院广汉分院，四川广汉 618307
3.
中国民用航空飞行学院飞行技术学院，四川广汉 618307

基金项目: 青年科学基金项目（12002368）

详细信息

作者简介:
梁海涛（1976-），男，高级工程师，研究方向为航空发动机故障诊断。E-mail：lianghaitao7603@163.com

通讯作者:
张庆峰（1982-），男，副教授，硕士生，研究方向为工程力学与飞机结构健康监测。E-mail：zqfcafuc@163.com

中图分类号: V234;TH17
计量
- 文章访问数: 393
- HTML浏览量: 69
- PDF量: 189
- 被引次数: 0
出版历程
- 收稿日期: 2021-04-21
- 刊出日期: 2021-09-28

Bearing fault diagnosis based on ARCN model

1.
Mechanical Engineering Department， Sichuan Tri-star General Aviation Company Limited，Chengdu 610051，China
2.
Guanghan Flight College， Civil Aviation Flight University of China，Guanghan 618307，China
3.
Flight Technology College， Civil Aviation Flight University of China，Guanghan 618307，China

摘要

摘要: 提出注意力循环机制与胶囊网络融合的注意力循环胶囊网络（ARCN）的诊断模型。提取时序特征信息构建初级胶囊；自适应融合路由机制、注意力循环机制构建数字胶囊特征；基于西储大学轴承实验数据，验证了ARCN模型的准确率、鲁棒性、稳定性、收敛误差，其准确率相比Caps模型识别准确率提高1.2%、收敛误差达到0.2。基于实验仿真平台，采集正常、内环故障、外环故障和滚动体故障的振动信号，并通过小波基变换获取的时频图构建ARCN模型的数据集。仿真实验结果表明：ARCN模型下，每类故障被误诊的概率不超过总样本的1%。
- 轴承故障诊断 /
- 注意力循环机制 /
- 胶囊网络 /
- 小波变换 /
- 准确率
Abstract: The attention recurrent and capsule network （ARCN） diagnosis model was proposed by integrating the attention cycle mechanism and capsule network.Firstly，the bidirectional LSTM network was used to extract the time-series characteristic information to construct the primary capsule.Secondly，routing mechanism and attention cycle mechanism were used to construct adaptively digital capsule.The accuracy，robustness，stability and convergence error of ARCN model in bearing fault identification were verified by bearing experiment data of Western Reserve University.The accuracy of ARCN model was 1.2% higher than that of Caps model.The convergence error of the ARCN model reached 0.2.Based on the experimental simulation platform，the vibration signals of normal，inner ring fault，outer ring fault and rolling element fault were collected.The results showed that the misdiagnosis probability of each kind of fault was less than 1% of the total samples under ARCN model.
- bearing fault diagnosis /
- attention recurrent /
- capsule network /
- wavelet transform /
- accuracy

HTML

参考文献(18)

[1]	马圣.极限学习机在航空轴承故障诊断中的应用研究[D].天津：中国民航大学,2019.
[2]	蔡赛男,宋卫星,班利明,等.基于鲸鱼算法优化LSSVM的滚动轴承故障诊断[EB/OL].[2021-04-17].https:∥doi.org/10.13195/j.kzyjc.2020.1147.
[3]	宋霖,宿磊,李可,等.基于SSD和1DCNN的滚动轴承故障诊断方法[J].华中科技大学学报（自然科学版）,2020,48（12）:38-43.
[4]	李红贤,韩延,吴敬涛,等.基于ICA包络增强MEMD的滚动轴承故障诊断[J].航空动力学报,2021,36（2）:405-412.
[5]	皮骏,马圣,贺嘉诚,等.基于IGA-ELM网络的滚动轴承故障诊断[J].航空学报,2018,39（9）:233-244.
[6]	HAIDONG S,HONGKAI J,YING L,et al.A novel method for intelligent fault diagnosis of rolling bearings using ensemble deep auto-encoders[J].Mechanical Systems and Signal Processing,2018,102（1）:278-297.
[7]	宫文峰,陈辉,张泽辉,等.基于改进卷积神经网络的滚动轴承智能故障诊断研究[J].振动工程学报,2020,33（2）:400-413.
[8]	ZHU Z A,PENG G A,CHEN Y A,et al.A convolutional neural network based on a capsule network with strong generalization for bearing fault diagnosis[J].Neurocomputing,2019,323:62-75.
[9]	ZHANG S W,ZHANG S B,ZHANG C L,et al.Cucumber leaf disease identification with global pooling dilated convolutional neural network[J].Computers and Electronics in Agriculture,2019,162:422-430.
[10]	SABOUR S,FROSST N,HINTON G E.Dynamic routing between capsules[R].Long Beach,US：the 31st International Conference on Neural Information Processing Systems,2017.
[11]	MADHU G,GOVARDHAN A,SRINIVAS B S,et al.Imperative dynamic routing between capsules network for malaria classification[J].Computers,Materials and Continua,2021,680（1）：903-919.
[12]	CHEN T Y,WANG Z H.,YANG X,et al.A deep capsule neural network with stochastic delta rule for bearing fault diagnosis on raw vibration signals[J].Measurement,2019,148:106857.1-106857.15.
[13]	衷路生,刘东东.多级神经网络的轴承故障诊断研究[J].计算机工程与应用,2020,56（7）:193-199.
[14]	RU Y,HUANG,YI X,et al.Deep decoupling convolutional neural network for intelligent compound fault diagnosis[J].IEEE Access,2018，7:1848-1858.
[15]	沈炜域.基于自注意力与动态路由的文本建模方法[J].软件导刊,2019,18（1）:56-60,64.
[16]	张文涛.基于BiLSTM网络的领域问答系统关键技术研究[D].长沙：湖南师范大学,2020.
[17]	Case Western Reserve University Bearing Data Center.Bearing data center fault test data[EB/OL].[2020- 10-01].http:∥www.eecs.case.edu/laboratory/bearing.
[18]	朱娜,母其海,刘志邦,等.基于多尺度小波变换和时频图的微波源故障检测[J].电子测量技术,2021,44（13）:48-53.