采用多尺度注意力机制的旋转机械故障诊断方法

吴静然 1; 丁恩杰 2; 3; 崔冉 1; 刘建华 1

doi:10.7652/xjtuxb202002007

您当前的位置：

首页 >

文章列表页 >

采用多尺度注意力机制的旋转机械故障诊断方法

更新时间：2025-05-08

- 采用多尺度注意力机制的旋转机械故障诊断方法
- A Diagnostic Approach for Rotating Machinery Using Multi-Scale Feature Attention Mechanism
- 西安交通大学学报 2020年54卷第2期页码：51-58
- 作者机构：
  
  中国矿业大学徐海学院,江苏,徐州,221008
- 作者简介：
- 基金信息：
  
  : 2019-05-29。作者简介: 吴静然(1989—),女,讲师;丁恩杰(通信作者),男,教授,博士生导师。基金项目: “十三五”国家重点研发计划资助项目(2017YFC0804400);江苏省高等学校自然科学研究资助项目(19KJB510064)
- DOI：10.7652/xjtuxb202002007
  中图分类号： TP18;TH133.33
- 网络首发：2020-02-10，
  
  纸质出版：2020
- 稿件说明：
移动端阅览
吴静然 1, 丁恩杰 2, 3, 等. 采用多尺度注意力机制的旋转机械故障诊断方法[J]. 西安交通大学学报, 2020,54(2):51-58.

A Diagnostic Approach for Rotating Machinery Using Multi-Scale Feature Attention Mechanism[J]. 2020, 54(2): 51-58.
吴静然 1, 丁恩杰 2, 3, 等. 采用多尺度注意力机制的旋转机械故障诊断方法[J]. 西安交通大学学报, 2020,54(2):51-58. DOI： 10.7652/xjtuxb202002007.

A Diagnostic Approach for Rotating Machinery Using Multi-Scale Feature Attention Mechanism[J]. 2020, 54(2): 51-58. DOI： 10.7652/xjtuxb202002007.

摘要

针对旋转机械故障诊断需要复杂特征提取过程

且对混有噪声的信号故障识别准确率偏低的问题

提出了一种基于注意力机制的多尺度端到端故障诊断方法。该方法在输入端引入随机丢弃抑制输入噪声

然后利用故障信号具有多个固有振动模态的特点

通过多尺度粗粒度层获取不同尺度下振动信号

进而利用全卷积网络实现多尺度特征提取

接着采用注意力机制将多尺度特征进行融合

最后利用多分类函数实现旋转机械故障诊断。分别在凯斯西储大学轴承数据集和变速箱数据集对该方法的有效性进行验证

结果表明:该方法的故障识别率高达100%; 人为引入噪声信号的信噪比为-4 dB时

在凯斯西储大学轴承数据集F上的故障识别正确率为84.77%

在齿轮箱数据集上的识别正确率为78.365%

识别正确率明显高于其他机器学习算法

证明了该方法具有较强的抗噪声干扰能力。

Abstract

A multi-scale end-to-end fault diagnosis method based on attention mechanism is proposed to deal with the problem that rotating machinery fault diagnosis needs complex feature extraction process and the diagnostic accuracy is low for noise-containing samples. A random dropout mechanism is introduced to suppress input noise at the input end. Taking advantage of the fact that fault signal has multiple modals

the vibration signals under different scales are obtained by using coarse-grained layer. Then multi-scale features are extracted by using fully convolutional networks and fused by using an attention mechanism. Finally

rotating machinery fault classification is reali-ed based on a multi-classification function. The validity of the model is verified with the Case Western Reserve University bearing dataset and gearbox dataset

respectively. Experiments show that the fault recognition rate of the method is up to 100%. When the ratio of signal to noise is -4 dB

the fault recognition ac

关键词

Keywords

references

张雪英, 栾忠权, 刘秀丽. 基于深度学习的滚动轴承故障诊断研究综述 [J]. 设备管理与维修, 2017(18): 130-133.

ZHANG Xueying, LUAN Zhongquan, LIU Xiuli. Research review of rolling bearing fault diagnosis based on deep learning [J]. Equipment Management and Maintenance, 2017(18): 130-133.

WANG D, TSUI K L. Statistical modeling of bearing degradation signals [J]. IEEE Transactions on Reliability, 2017, 66(4): 1331-1344.

LIU Tao, CHEN Jin, DONG Guangming. Rolling element bearing fault diagnosis based on frequency band entropy [J]. Journal of Vibration and Shock, 2014, 33(1): 77-80.

邓飞跃, 强亚文, 杨绍普, 等. 一种自适应频率窗经验小波变换的滚动轴承故障诊断方法 [J]. 西安交通大学学报, 2018, 52(8): 22-29.

DENG Feiyue, QIANG Yawen, YANG Shaopu, et al. A fault diagnosis method of rolling element bearings with adaptive frequency window empirical wavelet transform [J]. Journal of Xi’an Jiaotong University, 2018, 52(8): 22-29.

俞啸. 数据驱动的滚动轴承故障特征分析与诊断方法研究 [D]. 徐州: 中国矿业大学, 2017: 16-84.

ZHANG Wei, LI Chuanhao, PENG Gaoliang, et al. A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load [J]. Mechanical Systems and Signal Processing, 2018, 100: 439-453.

肖雄, 王健翔, 张勇军, 等. 一种用于轴承故障诊断的二维卷积神经网络优化方法 [J]. 中国电机工程学报, 2019, 39(15): 4558-4568.

XIAO Xiong, WANG Jiangxiang, ZHANG Yongjun, et al. A two-dimensional convolution neural network optimization method for bearing fault diagnosis [J]. Proceedings of the CSEE, 2019, 39(15): 4558-4568.

QIN Yi, WANG Xin, ZOU Jingqiang. The optimized deep belief networks with improved logistic sigmoid units and their application in fault diagnosis for planetary gearboxes of wind turbines [J]. IEEE Transactions on Industrial Electronics, 2019, 66(5): 3814-3824.

ZHOU Funa, HU Po, YANG Shuai, et al. A multimodal feature fusion-based deep learning method for online fault diagnosis of rotating machinery [J]. Sensors, 2018, 18(10): 3521.

YUAN Binhang, WANG Chen, JIANG Fei, et al. Wavelet FCNN: a deep time series classification model for wind turbine blade icing detection [EB/OL]. [2019-02-01]. https:∥arxiv.org/pdf/1902.05625vl.pdf.

JIANG Guoqian, HE Haibo, YAN Jun, et al. Multiscale convolutional neural networks for fault diagnosis of wind turbine gearbox [J]. IEEE Transactions on Industrial Electronics, 2019, 66(4): 3196-3207.

XU K, BA J, KIROS R, et al. Show, attend and tell: neural image caption generation with visual attention [C]∥32nd International Conference on Machine Learning. Feriburg, Germany: IMLS, 2015: 2048-2057.

LUONG M T, PHAM H, MANNING C D. Effective approaches to attention-based neural Machine translation [C]∥Conference on Empirical Methods in Natural Language Processing. Dartmouth, MA, USA: ACL, 2015: 1412-1421.

Case Western Reserve University Bearing Data Center. Bearing data file [DB/OL]. [2018-01-11]. http: ∥csegroups.case.edu/bearingdatacenter/pages.

SHAO Siyu, STEPHEN M A, YAN Ruqiang, et al. Highly-accurate machine fault diagnosis using deep transfer learning [J]. IEEE Transactions on Industrial Informatics, 2019, 15(4): 2446-2455.

LI Weihua, ZHANG Shaohui, HE Guolin. Semisupervised distance-preserving self-organizing map for machine-defect detection and classification [J]. IEEE Transactions on Instrumentation and Measurement, 2013, 62(5): 869-879.

ZHANG Xiaoyuan, LIANG Yitao, ZHOU Jianzhong, et al. A novel bearing fault diagnosis model integrated permutation entropy, ensemble empirical mode decomposition and optimized SVM [J]. Measurement, 2015, 69: 164-179.

LEI Yaguo, JIA Feng, LIN Jing, et al. An intelligent fault diagnosis method using unsupervised feature learning towards mechanical big data [J]. IEEE Transactions on Industrial Electronics, 2016, 63(5): 3137-3147.

ZHAO Rui, WANG Dongzhe, YAN Ruqiang, et al. Machine health monitoring using local feature-based gated recurrent unit networks [J]. IEEE Transactions on Industrial Electronics, 2018, 65(2): 1539-1548.

DING Xiaoxi, HE Qingbo. Energy-fluctuated multiscale feature learning with deep convNet for intelligent spindle bearing fault diagnosis [J]. IEEE Transactions on Instrumentation and Measurement, 2017, 66(8): 1926-1935.

李潇潇,闫柯,葛临风,等.高速球轴承喷油润滑流场特性研究.2019,53(12):17-24.[doi:10.7652/xjtuxb201912003]

陈飞,金英泽,袁小阳.载荷方向对立式转子导轴承润滑性能的影响.2019,53(12):25-30,37.[doi:10.7652/xjtuxb2019 12004]

李亚倩,杨攀,陈渭.考虑紊流和滑移影响的液态金属润滑螺旋槽轴承设计.2019,53(8):15-23.[doi:10.7652/xjtuxb 201908003]

胥永刚,田伟康,曹金鑫,等.精细谱负熵及其在滚动轴承故障诊断中的应用.2019,53(8):31-39,128.[doi:10.7652/xjtuxb201908005]

任佟,陈东菊,李彦生,等.气体轴承的动态特性分析及实验研究.2019,53(8):68-75.[doi:10.7652/xjtuxb201908009]

刘锐,邹俊荣,任超,等.采用规范化局部保持投影的轴承故障诊断方法.2019,53(6):54-61.[doi:10.7652/xjtuxb2019 06008]

朱永生,陈凯达,闫柯,等.利用打印条码的转子轴向位移径向监测方法.2019,53(4):1-8.[doi:10.7652/xjtuxb201904 001]

李昊,耿海鹏,孙岩桦,等.拱箔成型工艺对箔片轴承性能影响的仿真分析.2019,53(4):9-14.[doi:10.7652/xjtuxb2019 04002]

李昊,耿海鹏,孙岩桦,等.箔片安装位置对气体轴承性能影响的仿真分析.2019,53(3):81-87.[doi:10.7652/xjtuxb 201903012]

刘学婧,刘磊,徐华,等.滚子分布方式对球面滚子轴承服役性能的影响.2018,52(12):9-17.[doi:10.7652/xjtuxb201812 002]

邓飞跃,强亚文,杨绍普,等.一种自适应频率窗经验小波变换的滚动轴承故障诊断方法.2018,52(8):22-29.[doi:10.7652/xjtuxb201808004]

韦祥,李本威,张赟.采用符号时间序列分析的轴承早期微弱故障预警.2018,52(6):84-90.[doi:10.7652/xjtuxb201806 013]

张胜伦,裴世源,徐华,等.考虑瞬态冲击和弹性变形的滑动轴承特性与动力学响应.2018,52(1):100-106.[doi:10.7652/xjtuxb201801015]

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

利用改进卷积神经网络的滚动轴承变工况故障诊断方法

机械滥用场景下锂离子电池温度多模态神经网络预测方法

电力变压器故障诊断多智能体大模型构建与应用

采用双小波字典的齿轮箱复合故障特征提取方法

一维卷积神经网络在机械故障特征提取中的可解释性研究