[1]傅锦涛,张弓,张树忠.基于迁移学习的磨倒机轴承故障诊断[J].福建理工大学学报,2024,22(04):393-400.[doi:10.3969/j.issn.2097-3853.2024.04.013]
　FU Jintao,ZHANG Gong,ZHANG Shuzhong.Bearing fault diagnosis of cross-working grinding mill based on transfer learning[J].Journal of Fujian University of Technology;,2024,22(04):393-400.[doi:10.3969/j.issn.2097-3853.2024.04.013]
点击复制

基于迁移学习的磨倒机轴承故障诊断
分享到：

《福建理工大学学报》[ISSN:2097-3853/CN:35-1351/Z]

卷:
第22卷
期数:
2024年04期
页码:
393-400
栏目:
出版日期:
2024-08-25

文章信息/Info

Title:
Bearing fault diagnosis of cross-working grinding mill based on transfer learning
作者:
傅锦涛; 张弓; 张树忠
福建理工大学机械与汽车工程学院
Author(s):
FU Jintao1;  ZHANG Gong1; 2;  ZHANG Shuzhong
School of Mechanical and Automotive Engineering, Fujian University of Technology
关键词:
轴承故障; 迁移学习; 多核最大均值差异; 故障诊断
Keywords:
bearing fault; transfer learning; multi-core maximum mean difference; fault diagnosis
分类号:
TH18；TH133.33
DOI:
10.3969/j.issn.2097-3853.2024.04.013
文献标志码:
A
摘要:
提出一种基于多核最大均值差异的一维卷积迁移学习方法。利用一维卷积网络直接从原始振动信号中提取故障特征信息;应用对抗策略迁移技术辅助网络提取两个域之间的共同特征;以多核最大均值差异作为评价源域和目标域的距离指标,实现域不变特征提取并在凯斯西储大学轴承数据集的4种工况下进行迁移学习。研究表明,相比于传统方法,该文所提方法在故障分类精度上提高了6%,具有良好的应用前景。
Abstract:
A one-dimensional convolution transfer learning method based on multi-core maximum mean difference is proposed. Firstly, one-dimensional convolutional networks are utilized to directly extract fault feature information from the original vibration signals. Secondly, an adversarial strategy migration technique is employed to assist the network in extracting common features between the two domains. Finally, the multi-core maximum mean difference is used to evaluate the distance between the source domain and target domain, enabling extraction of domain invariant features and facilitating transfer learning under four working conditions of the bearing dataset from Case Western Reserve University. Compared with traditional methods, the proposed approach can enhance fault classification accuracy by 6%, which has a good application prospect.

参考文献/References:

［1］ SUN Y J，WANG J，WANG X H. Fault diagnosis of mechanical equipment in high energy consumption industries in China：a review［J］. Mechanical Systems and Signal Processing，2023，186：109833.［2］ LI Z X，LI J M，DING W M，et al. A sparsityenhanced periodic OGS model for weak feature extraction of rolling bearing faults［J］. Mechanical Systems and Signal Processing，2022，169：108733.［3］ ZHANG S，ZHANG S B，WANG B N，et al. Deep learning algorithms for bearing fault diagnostics—a comprehensive review［J］. IEEE Access，2020，8：29857-29881.［4］ HUANG T，ZHANG Q，TANG X A，et al. A novel fault diagnosis method based on CNN and LSTM and its application in fault diagnosis for complex systems［J］. Artificial Intelligence Review，2022，55（2）：1289-1315.［5］ ZHU J，CHEN N，SHEN C Q. A new deep transfer learning method for bearing fault diagnosis under different working conditions［J］. IEEE Sensors Journal，2020，20（15）：8394-8402.［6］ CAO Z J，MA L J，LONG M S，et al. Partial adversarial domain adaptation［M］∥Computer VisionECCV 2018. Cham：Springer International Publishing，2018：139-155.［7］ GRETTON A，SRIPERUMBUDUR B，SEJDINOVIC D，et al. Optimal kernel choice for largescale twosample tests［C］∥Proceedings of the 25th International Conference on Neural Information Processing SystemsVolume 1. Lake Tahoe，Nevada: ACM，2012：1205-1213.［8］ BENDAVID S，BLITZER J，CRAMMER K，et al. A theory of learning from different domains［J］. Machine Learning，2010，79（1）：151-175.［9］ CAO X C，WANG Y，CHEN B Q，et al. Domainadaptive intelligence for fault diagnosis based on deep transfer learning from scientific test rigs to industrial applications［J］. Neural Computing and Applications，2021，33（9）：4483-4499.［10］ CHOUDHARY A，MIAN T，FATIMA S. Convolutional neural network based bearing fault diagnosis of rotating machine using thermal images［J］. Measurement，2021，176：109196.［11］ 王功鹏，段萌，牛常勇. 基于卷积神经网络的随机梯度下降算法［J］. 计算机工程与设计，2018，39（2）：441-445，462.［12］ SMITH W A，RANDALL R B. Rolling element bearing diagnostics using the Case Western Reserve University data：a benchmark study［J］. Mechanical Systems and Signal Processing，2015，64：100-131.

更新日期/Last Update: 2024-08-25