基于注意力BiGRU的机械故障诊断方法研究

PDF(1532 KB)

振动与冲击 ›› 2021, Vol. 40 ›› Issue (5) : 113-118.

论文

张立鹏1，毕凤荣1,2，程建刚2，沈鹏飞2

作者信息 +

Mechanical fault diagnosis method based on attention BiGRU

ZHANG Lipeng1, BI Fengrong1,2, CHENG Jiangang2, SHEN Pengfei2

Author information +

文章历史 +

摘要

为了解决机械故障诊断领域传统方法自适应性差、参数选择过于依赖人工的问题，论文提出了一种基于循环神经网络的机械故障诊断算法。该方法利用预处理后的机械振动信号，搭建了双向门控循环单元的故障诊断模型，并进行了基于注意力机制的模型优化，提高了特征提取效率。经过美国凯斯西储大学轴承数据集以及自采集的柴油机故障实验数据验证，相比于传统神经网络算法提升了计算效率和诊断准确率，并表现出了良好的抗噪能力。结果表明，该方法可以有效适用于基于机械振动信号的故障诊断，具有一定的工程应用价值。

Abstract

In order to solve the problem that the traditional methods in the field of mechanical fault diagnosis have poor adaptability and the selection of parameters is too dependent on manual work, this paper proposes a mechanical fault diagnosis algorithm based on recurrent neural networks(RNN). This method uses the mechanical vibration signal after preprocessing to build a fault diagnosis model of bidirectional gated recurrent unit（BiGRU）, and optimizes the model based on attention mechanism to improve the efficiency of feature extraction. It has been verified by the bearing data set of Cassegrain University and the self collected diesel engine fault test data. Compared with the traditional neural network algorithm, it improves the calculation efficiency and diagnosis accuracy, and shows a good anti noise ability. The results show that the method can be effectively applied to fault diagnosis based on mechanical vibration signals, and has good engineering application value.

导出引用

张立鹏1，毕凤荣1,2，程建刚2，沈鹏飞2. 基于注意力BiGRU的机械故障诊断方法研究[J]. 振动与冲击, 2021, 40(5): 113-118

ZHANG Lipeng1, BI Fengrong1,2, CHENG Jiangang2, SHEN Pengfei2. Mechanical fault diagnosis method based on attention BiGRU[J]. Journal of Vibration and Shock, 2021, 40(5): 113-118

参考文献

[1] 毕凤荣, 李鑫, 马腾. 基于变模式分解的爆震特征识别方法[J]. 振动.测试与诊断, 2018, 38(05):27-31+200.
Bi Fengrong, Li Xin, Ma Teng. Knock Detection using the Variational Mode Decomposition[J]. Journal of Vibration, Measurement & Diagnosis, 2018, 38(05):27-31+200. (in Chinese)
[2] 王聪. 基于稀疏表达的机械信号处理方法及其在滚动轴承故障诊断中的应用研究[D]. 安徽：中国科学技术大学，2017.
Wang Cong. Mechanical signal processing based on sparse representation and its application in the diagnosis of rolling-element bearings[D]. Anhui: University of Science and Technology of China,2017. (in Chinese)
[3] Huang N E, Shen Z, Long S R, et al. The Empirical Mode Decomposition and the Hilbert Spectrum for Nonlinear and Nonstationary Time Series Analysis[J]. Proc. R. Soc. Lond. A, 1998,454:903-994.
[4] Dragomiretskiy K, Zosso D. Variational Mode Decomposition [J]. IEEE Tran on Signal Processing, 2014, 62(3): 531-544.
[5] Cho K, Van Merrienboer B, Gulcehre C,et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation［J/OL］. arXiv, 2014: arXiv: 1508.06615. (2014－09－03) ［2018－05－01］http: //arXiv.org /abs/1406.1078.
[6] Deng, Dazhi. Research on coal mine electromechanical equipment closed-loop management system based on IOT and information technology[C]// International Conference on Artificial Intelligence. IEEE, 2011.
[7] 王毅星. 基于深度学习和迁移学习的电力数据挖掘技术研究[D]. 2019.
Wang Yi-xing. Powe data mining technology based on deep learning and transfer learning[D]. 2019.(in Chinese)
[8] 宁永杰. 基于机器学习的滚动轴承状态评估与剩余寿命预测[D]. 2019.
Ning Yong-jie. Rolling bearing state evaluation and remaining useful life prediction based on machine learning[D]. 2019.(in Chinese)
[9] 牛哲文, 余泽远, 李波,等. 基于深度门控循环单元神经网络的短期风功率预测模型[J]. 电力自动化设备, 2018, v.38；No.289(05):43-49.
Niu Zhe-wen, Yu Ze-yuan, Li Bo et al. Short-term wind power forecasting model based on deep gated recurrent unit neural network[J]. Electric Power Automation Equipment, 2018, v.38；No.289(05):43-49.(in Chinese)
[10] Zhou P. , Shi W. , Tian J. , et al. Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification. Meeting of the Association for Computational Linguistics. 2016.
[11] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]//Advances in neural information processing systems. 2017: 5998-6008.
[12] Wang F, Jiang M, Qian C, et al. Residual attention network for image classification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017: 3156-3164.
[13] Yang Z, Yang D, Dyer C, et al. Hierarchical attention networks for document classification[C]//Proceedings of the 2016 conference of the North American chapter of the association for computational linguistics: human language technologies. 2016: 1480-1489.
[14] Bahdanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate[J]. arXiv preprint arXiv:1409.0473, 2014.