融合注意力机制的改进DBN变工况齿轮箱故障诊断方法

摘要
图/表
参考文献(19)
相关文章 (15)

全文: PDF (1698 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要

针对齿轮箱在交变工况下运行时导致的故障模式难以识别、分类精度降低的问题，提出融合注意力机制的改进深度置信网络(DBN)变工况齿轮箱故障诊断方法。为解决齿轮箱单一时、频域特征反应故障信息不全面、异常不敏感问题，提取时域、频域、小波包时频域特征形成高维特征集。利用深度置信网络具有的贪心学习优势分别对其进行挖掘，同时结合注意力机制自适应对描述齿轮箱状态有效的特征给予更多“注意”，从而提高齿轮箱故障诊断精度。引进余弦损失函数降低深度置信网络对不同工况振动强度的敏感性，从而减轻网络拟合负担、提高泛化能力。齿轮箱变工况故障诊断试验结果表明，所提方法有效提高了变工况下齿轮箱故障诊断精度，同时具有很好的泛化能力。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	张智禹
	尹爱军
	谭建

关键词 ：注意力机制, 余弦损失函数, 深度置信网络(DBN), 齿轮箱, 变工况故障诊断

Abstract：

Aiming at the fact that the fault mode of gearboxes running under varying working condition is difficult to identify and the classification accuracy is reduced, an improved deep belief network (DBN) method with attention mechanism was proposed.Firstly, in order to solve the problem that single time domain or frequency domain characters are not comprehensive and insensitive for responding to gearbox fault information,the time domain, frequency domain and wavelet packet time-frequency domain features were extracted and synthesized to form a high-dimensional feature set.Then, making use of the greedy learning advantage of the DBN, the features were separately mined further.At the same time, the attention mechanism was used to adaptively give more attention to the features that effectively describe the gearbox state to improve the accuracy of gearbox fault diagnosis.Finally, the cosine loss function was introduced to reduce the sensitivity of the deep confidence network to the vibration intensity under different working conditions, thereby reduce the network fitting burden and improve the generalization ability.The fault diagnosis tests of a gearbox under varying working condition show that the proposed method effectively improves the fault diagnosis accuracy of the gearbox, and has good generalization ability.

Key words： attention mechanism;cosine loss function deep belief network(DBN) gearbox fault diagnosis under varying working condition

收稿日期: 2020-01-09 出版日期: 2021-07-28

引用本文:

张智禹，尹爱军，谭建. 融合注意力机制的改进DBN变工况齿轮箱故障诊断方法[J]. 振动与冲击, 2021, 40(14): 47-52.
ZHANG Zhiyu，YIN Aijun，TAN Jian. Improved DBN method with attention mechanism for the fault diagnosis of gearboxes under varying working condition. JOURNAL OF VIBRATION AND SHOCK, 2021, 40(14): 47-52.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2021/V40/I14/47

［1］WANG Y X, XIANG J W, RICHARD M, et al.Spectral kurtosis for fault detection, diagnosis and prognostics of rotating machines: a review with applications［J］.Mechanical Systems and Signal Processing, 2016,66/67: 679-698.

［2］段礼祥,谢骏遥,王凯,等.基于不同工况下辅助数据集的齿轮箱故障诊断［J］.振动与冲击, 2017,36(10): 104-108.
DUAN Lixiang, XIE Junyao, WANG Kai, et al.Considering the influence of kernel function of transfer component analysis and its application in variable working condition of gearbox fault diagnosi［J］.Journal of Vibration and Shock, 2017,36(10): 104-108.

［3］LIU W, GUO P, YE L.A low-delay lightweight recurrent neural network (LLRNN) for rotating machinery fault diagnosis［J］.Sensors, 2019,19(14): 3109.

［4］张小强,朱文辉,康铁宇,等.基于人工免疫算法的离散隐马尔科夫故障诊断模型优化［J］.装备环境工程, 2019,16(1): 63-67.
ZHANG Xiaoqiang, ZHU Wenhui, KANG Tieyu, et al.Optimization of discrete hidden Markov fault diagnosis model based on artificial immune algorithm［J］.Equipment Environmental Engineering, 2019,16(1): 63-67.

［5］CHEN R X, HUANG X, YANG L X, et al.Intelligent fault diagnosis method of planetary gearboxes based on convolution neural network and discrete wavelet transform［J］.Computers in Industry, 2019,106: 48-59.

［6］黄宏臣，韩振南，张倩倩，等.基于拉普拉斯特征映射的滚动轴承故障识别［J］.振动与冲击, 2015,34(5): 128-134.
HUANG Hongchen, HAN Zhennan, ZHANG Qianqian, et al.A method for fault diagnosis of rolling bearings based on laplacian eigenmap［J］.Journal of Vibration and Shock, 2015,34(5): 128-134.

［7］王奉涛,陈旭涛,闫达文,等.流形模糊C均值方法及其在滚动轴承性能退化评估中的应用［J］.机械工程学报, 2016,52(15): 59-64.
WANG Fengtao, CHEN Xutao, YAN Dawen, et al.Fuzzy C-means using manifold learning and its application to rolling bearing performance degradation assessment［J］.Journal of Mechanical Engineering, 2016,52(15): 59-64.

［8］SHARMA R R, PACHORI R B.Improved eigenvalue decomposition-based approach for reducing cross-terms in wigner-ville distribution［J］.Circuits, Systems, and Signal Processing, 2018,37: 3351-3352.

［9］JIANG G Q, HE H B, YAN J, et al.Multiscale convolutional neural networks for fault diagnosis of wind turbine gearbox［J］.IEEE Transactions on Industrial Electronics, 2018,66(4): 3196-3207.

［10］ZHUANG Z L, L H C, XU J, et al.A deep learning method for bearing fault diagnosis through stacked residual dilated convolutions［J］.Applied Sciences, 2019,9(9): 1823.

［11］时培明,梁凯,赵娜,等.基于深度学习特征提取和粒子群支持向量机状态识别的齿轮智能故障诊断［J］.中国机械工程, 2017,28(9): 1056-1061.
SHI Peiming, LIANG Kai, ZHAO Na, et al.Intelligent fault diagnosis for gears based on deep learning feature extraction and particle swarm optimization SVM state identification［J］.China Mechanical Engineering, 2017,28(9): 1056-1061.

［12］田富国,汪庆华,贾康,等.BP神经网络与Sugeno模糊积分融合的转子系统故障诊断［J］.装备环境工程, 2019,16(10): 110-114.
TIAN Fuguo, WANG Qinghua, JIA Kang, et al.Fault diagnosis of rotor system based on BP neural network and sugeno fuzzy integral［J］.Equipment Environmental Engineering, 2019,16(10): 110-114.

［13］SALAKHUTDINOY R, MURRAY I.On the quantitative analysis of deep belief networks［C］//Proceedings of the 25th International Conference on Machine Learning.Helsinki: ACM, 2008.

［14］HINTON G E.Training products of experts by minimizing contrastive divergence［J］.Neural Computation, 2002,14(8): 1771-1800.

［15］YANG Z C, YANG D Y, 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.［S.l.］: NAACL, 2016.

［16］WEN Y D, ZHANG K P, LI Z F, et al.A discriminative feature learning approach for deep face recognition［M］//Computer Vision-ECCV 2016.New York: Springer International Publishing, 2016.

［17］LU C, WANG Z Y, ZHOU B.Intelligent fault diagnosis of rolling bearing using hierarchical convolutional network based health state classi fication［J］.Advanced Engineering Informatics, 2017,32: 139-151.

［18］ZHANG R, TAO H Y, WU L F, et al.Transfer learning with neural networks for bearing fault diagnosis in changing working conditions［J］.IEEE Access, 2017,5: 14347-14357.

［19］SHAO H D, JIANG H K, LIN Y, et al.A novel method for intelligent fault diagnosis of rolling bearings using ensemble deep auto-encoders［J］.Mechanical Systems Signal Processing, 2018,102: 278-297.