基于参数迁移和一维卷积神经网络的海水泵故障诊断

摘要
图/表
参考文献(22)
相关文章 (15)

全文: PDF (1960 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要为解决海水泵工况多变、故障数据少、振动特征提取困难等故障诊断问题，本文利用一维卷积神经网络(one-dimensional convolutional neural network，1DCNN)强大的表征能力自动学习故障特征，并引入参数迁移将源域数据集上的模型参数迁移到目标域故障分类识别任务。首先，构建1DCNN基模型，运用Dropout、正则化、学习率等深度训练技巧防止模型过拟合，在源域数据集上训练得到模型参数；然后将其模型参数迁移到目标域故障诊断模型，并进行参数微调，构建1DCNN参数迁移模型进行故障识别。实验结果表明，与传统1DCNN相比，1DCNN参数迁移模型能够显著提高模型的收敛速度和分类性能。该方法在三个变工况海水泵数据集上的平均识别准确率高达95.93%，具有较高的识别准确率和较强的泛化能力。

	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
	崔石玉
	朱志宇

关键词 ：参数迁移, 一维卷积神经网络, 故障诊断, 海水泵, 振动

Abstract：This paper solves the seawater pump’s problem of insufficient fault samples, complex and variable operating conditions and difficult extraction of vibration features. A fault diagnosis model based on one-dimensional convolution neural network(1DCNN) was proposed and parameter transfer was used to improve model’s performance. CNN has powerful capacities of feature learning and feature expression, which was used to automatically learn fault features. Parameter transfer was added to transfer model parameters learned from source domain dataset to the identification tasks of target domain fault. Firstly, 1DCNN based model is constructed and trained on the source domain dataset to obtain model parameters. The deep learning training techniques are applied to prevent model overfitting, such as dropout, regularization and adaptive learning rate, etc. Then its model parameter knowledge was transferred to the target domain fault diagnosis model to construct 1DCNN parameter transfer model to identify the faults, while adding the step of fine-tune the parameters. Experimental results show that, compared traditional 1DCNN, 1DCNN transfer model can significantly improve the convergence speed and classification performance of the model. The average recognition accuracy of this method under three variable operating condition seawater pump datasets was as high as 95.93%, and it could have higher recognition accuracy and stronger generalization ability.

Key words： parameter transfer one-dimensional convolutional neural network fault diagnosis seawater pumps vibration

收稿日期: 2020-08-18 出版日期: 2021-12-28

引用本文:

崔石玉，朱志宇. 基于参数迁移和一维卷积神经网络的海水泵故障诊断[J]. 振动与冲击, 2021, 40(24): 180-189.
CUI Shiyu,ZHU Zhiyu. Seawater pump fault diagnosis based on parameter transfer and one-dimensional convolutional neural network. JOURNAL OF VIBRATION AND SHOCK, 2021, 40(24): 180-189.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2021/V40/I24/180

[1] 王珲，彭彦平，庞桂兵，等.海水泵的振动与模态分析[J].大连工业大学学报，2016，35(4):308-312.
WANG Hui, PENG Yan-ping,Pang Gui-bing, et al . Vibration and modal analysis of seawater hydraulic pump[J]. Journal of Dalian Polytechnic University 2016, 35(4), 308-312.
[2] 蔡艳平，徐光华，张恒，等.基于内燃机振动信号的可视化识别诊断[J].振动与冲击，2019, 38(24)：150-157.
Cai Yan-ping, Xu Guang-hua, Zhang Heng, et al. Visual identification and diagnosis based on IC engine vibration signals [J]. Journal of Vibration and Shock, 2019, 38(24): 150-157.
[3] Bao Zhang, Chunyu Zhao. Dynamic turning force prediction and feature parameters extraction of machine tool based on ARMA and HHT. Proceedings of the Institution of Mechanical Engineers, Part C:Journal of Mechanical Engineering Science, 2020,234(5): 1044-1056.
[4] 李海平，赵建民，张鑫，等.行星齿轮箱齿轮磨损故障诊断[J].振动与冲击，2019，38(23)：84-89.
Li Hai-ping, Zhao Jian-min, Zhang Xin, et al. Fault diagnosis for gear wear of planetary gearbox [J]. Journal of Vibration and Shock, 2019, 38(23): 84-89.
[5] R. Zhao, D. Wang, R. Yan, et al. Machine health monitoring using local feature-based gated recurrent unit networks[J]. IEEE Transactions on Industrial Electronics,2018, 65 (2) : 1539–1548.
[6] J. Zheng, H. Pan, J. Cheng.Rolling bearing fault detection and diagnosis based on composite multiscale fuzzy entropy and ensemble support vector machines[J]. Mechanical Systems and Signal Processing,2017, 85 :746–759.
[7] M. Gong, J. Zhao, J. Liu,et al. Change detection in synthetic aperture radar images based on deep neural networks[J]. IEEE Transactions on Neural Networks and Learning Systems, 2016,27(1):125–138.
[8] 任浩，屈剑锋，柴毅等.深度学习在故障领域中的研究现状与挑战[J].控制与决策，2017，32（8）：1345-1358.
Ren Hao, Qu Jian-feng, Chai Yi, et al. Deep learning for fault diagnosis: The state of the art and challenge [J]. Control and Decision, 2017, 32(8): 1345-1358.
[9] 李彦冬，郝宗波，雷航.卷积神经网络研究综述[J].计算机应用，2016，36（9）:2508-2515,2565.
Li Yan-dong, Hao Zong-bo, Lei Hang. Survey of convolutional neural network [J]. Journal of Computer Applications, 2016, 36(9): 2508-2515,2565.
[10] CHEN Z Q, LI C, SANCHEZ R. Gearbox fault identification and classification with convolutional neural networks[J]. Shock and Vibration,2015(2):1-10.
[11] Zhang W, Peng G L, Li C H. Bearing fault diagnosis based on convolutional neural networks with 2D representation of vibration signals as input[C]. MATEC Web of Conferences, 2017,95(8):13001.
[12] 曲建玲，余路，袁涛，等.基于一维卷积神经网络的滚动轴承自适应故障诊断算法[J].仪器仪表学报，2018，39（7）：134-143.
Qu Jian-ling, Yu Lu, Yuan Tao, et al. Adaptive fault diagnosis algorithm for rolling bearings based on one-dimensional convolutional neural network [J]. Chinese Journal of Scientific Instrument, 2018, 39(7): 134-143.
[13] EREN L,INCE T, KIRANYAZ S. A generic intelligent bearing fault diagnosis system using compact adaptive 1DCNN classifier[J].Journal of Signal Processing Systems,2019,91(2):179-189.
[14] 金列俊，詹建明，陈俊华，等.基于一维卷积神经网络的钻杆故障诊断[J].浙江大学学报（工学版），2020，54（3）：467-473.
Jin Lie-jun, Zhan Jian-ming, Chen Jun-hua, et al. Drill pipe fault diagnosis method based on one-dimensional convolutional neural network [J]. Journal of Zhejiang University (Engineering Science), 2020, 54(3): 467-473.
[15] L. Wen, L. Gao, X. Li. A new deep transfer learning based on sparse auto-encoder for fault diagnosis[J]. IEEE Transactions on Systems, Man and Cybernetics: Systems, 2019,49 (1) :136–144.
[16] J. Lu, V. Behbood, P. Hao, H. Zuo, S. Xue, G. Zhang, Transfer learning using computational intelligence: a survey[J].Knowledge-Based Systems， 80 (2015) 14–23.
[17] R. Zhang, H. Tao, L. wu, Y. Guan, Transfer Learning with Neural Networks for Bearing Fault Diagnosis in Changing Working Conditions Access, IEEE,2017, pp. 14347–14357.
[18] YOSINSKI J, CLUNE J, BENGIO Y. How transferable are features in deep neural networks[C]//Proceedings of Annual Conference on Neural Information Processing Systems. Cambridge: MIT Press, 2014: 3320-3328.
[19] H. Zheng, R. Wang, J. Yin ,et al. A new intelligent fault identification method based on transfer locality preserving projection for actual diagnosis scenario of rotating machinery[J].Mechanical Systems and Signal Processing, 135(2020) 106344.
[20] 庄福振，罗平，何清，等.迁移学习研究进展[J].软件学报，2015，26（1）：26-39.
Zhuang Fu-zhen, Luo Ping, He Qing, et al. Survey on transfer learning research [J]. Journal of Software, 2015, 26(1): 26-39.
[21] 龙满生，欧阳春娟，刘欢，等.基于卷积神经网络与迁移学习的茶油病害图像识别[J].农业工程学报，2018，34（18）：194-201.
Long Man-sheng, Ouyang Chun-juan, Liu Huan, et al. Image recognition of Camellia oleifera diseases based on convolutional neural network & transfer learning [J]. Transactions of the Chinese Society of Agricultural Engineering, 2018, 34(18): 194-201.
[22] 富雅捷，张宏立.基于迁移学习的卷积神经网络森林火灾检测方法[J].激光与光电子学进展，2020，57（4）：120-126.
Fu Yajie, Zhang Hong-li. Forest fire detection method based on transfer learning of convolutional neural network [J]. Laser & Optoelectronics Progress, 2020, 57 (4): 120-126.