A multi-stage semi-supervised learning approach for intelligent fault diagnosis of rolling bearing using data augmentation and metric learning

Kun Yu; Tian Ran Lin; Hui Ma; Xiang Li; Xu Li

首页> 外文期刊>Mechanical systems and signal processing >A multi-stage semi-supervised learning approach for intelligent fault diagnosis of rolling bearing using data augmentation and metric learning

【24h】

A multi-stage semi-supervised learning approach for intelligent fault diagnosis of rolling bearing using data augmentation and metric learning

机译：使用数据增强和度量学习的滚动轴承智能故障诊断多级半监控学习方法

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

Limited condition monitoring data are recorded with label information in practice, which make the fault identification task more challenging. A semi-supervised learning (SSL) approach can be employed to increase the identification performance of the classifiers under such situation. In this study, a three-stage SSL approach using data augmentation (DA) and metric learning is proposed for an intelligent bearing fault diagnosis under limited labeled data. In the first stage, a DA method comprising seven DA strategies is presented to expand the feature space for the limited labeled samples under each healthy conditions. An optimization objective combining a cross entropy loss and a triplet loss is adopted to enlarge the margin between the feature distributions of limited labeled samples under different healthy conditions. In the second stage, a K-means technique is employed to acquire the cluster centers for the limited labeled samples under different healthy conditions. In the third stage, the label information for the unlabeled samples is first estimated according to the membership between the feature distributions of the unlabeled samples and the various cluster centers for original labeled samples and then a Kullback-Leibler divergence loss is introduced to minimize the discrepancy between feature distributions for the unlabeled samples and its corresponding cluster centers. The effectiveness of the proposed method is evaluated on two case studies, one is on an experimental bearing fault dataset from our laboratory test-rig, and the other is on a publicly dataset from a bearing degradation test. The comparison results on these two case studies demonstrate that the proposed method can perform better in bearing fault diagnosis under limited labeled samples than existing diagnostic methods.

机译：有限状态监测数据在实践中记录了标签信息，这使得故障识别任务更具挑战性。可以采用半监督学习（SSL）方法来增加这种情况下分类器的识别性能。在本研究中，在有限标记数据下提出了一种使用数据增强（DA）和度量学习的三阶段SSL方法和度量学习。在第一阶段，提出了一种包括七个策略的DA方法，以扩展每个健康条件下的有限标记样品的特征空间。采用结合交叉熵损失和三重态损耗的优化目标来扩大不同健康条件下有限标记样品的特征分布之间的余量。在第二阶段，采用K-Means技术在不同的健康状况下获得有限标记样品的群集中心。在第三阶段，首先根据未标记的样本的特征分布与原始标记样品的各种群集中心之间的成员资格来估计未标记样本的标签信息，然后引入了kullback-leibler发散损失以使差异最小化在未标记的样本和相应的集群中心的特征分布之间。在两个案例研究中评估了所提出的方法的有效性，一个是从我们的实验室测试钻井平台的实验轴承故障数据集，另一个是从轴承降解测试的公开数据集上。对这两个案例研究的比较结果表明，所提出的方法可以在Limited标记样本下的轴承故障诊断方面比现有的诊断方法更好。

著录项

来源
《Mechanical systems and signal processing》 |2021年第1期|107043.1-107043.24|共24页
作者
Kun Yu; Tian Ran Lin; Hui Ma; Xiang Li; Xu Li;
展开▼
作者单位

School of Mechanical Engineering and Automation Northeastern University Shenyang Liaoning 110819 PR China;

School of Mechanical and Automotive Engineering Qingdao University of Technology Qingdao Shandong 266520 PR China;

School of Mechanical Engineering and Automation Northeastern University Shenyang Liaoning 110819 PR China Key Laboratory of Vibration and Control of Aero-Propulsion System Ministry of Education Northeastern University Shenyang Liaoning 110819 PR China;

College of Sciences Northeastern University Shenyang Liaoning 110819 PR China;

State Key Laboratory of Rolling and Automation Northeastern University Shenyang Liaoning 110819 PR China;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类
关键词
Rolling bearing; Intelligent fault diagnosis; Semi-supervised learning; Data augmentation; K-means; Kullback-Leibler divergence;

机译：滚动轴承;智能故障诊断;半监督学习;数据增强;K-means;Kullback-Leibler分歧;

相似文献

外文文献
中文文献
专利

1. A consistency regularization based semi-supervised learning approach for intelligent fault diagnosis of rolling bearing [J] . Yu Kun, Ma Hui, Lin Tian Ran, Measurement . 2020,第1期

机译：基于一致性正规化的滚动轴承智能故障诊断的半监控学习方法
2. A robust intelligent fault diagnosis method for rolling element bearings based on deep distance metric learning [J] . Li Xiang, Zhang Wei, Din Qian Neurocomputing . 2018,第OCTa8期

机译：基于深度距离学习的鲁棒智能滚动轴承故障诊断方法
3. Fault Diagnosis of Rolling Bearing Based on Modified Deep Metric Learning Method [J] . Zengbing Xu, Xiaojuan Li, Hui Lin, Shock and vibration . 2021,第a期

机译：基于改进的深度度量学习方法的滚动轴承故障诊断
4. A Novel Assessment Metric for Intelligent Fault Diagnosis of Rolling Bearings with Different Fault Severities and Orientations [C] . Bo Zhao, Xianmin Zhang, Zhenhui Zhan, International Conference on Condition Monitoring of Machinery in Non-Stationary Operations . 2021

机译：具有不同故障严重程度和方向的滚动轴承智能故障诊断的新型评估度量
5. Analysis of rolling element bearing faults in rotating machinery: Experiments, modeling, fault detection and diagnosis. [D] . Adams, Michael Louis. 2001

机译：旋转机械中滚动轴承故障的分析：实验，建模，故障检测和诊断。
6. A Novel Intelligent Fault Diagnosis Method for Rolling Bearing Based on Integrated Weight Strategy Features Learning [O] . Jun He, Ming Ouyang, Chen Yong, 2020

机译：基于综合权重策略特征学习的滚动轴承智能故障诊断新方法
7. An Intelligent Fault Diagnosis for Rolling Bearing Based on Adversarial Semi-Supervised Method [O] . Yongchao Zhang, Zhaohui Ren, Shihua Zhou 2020

机译：基于对抗半监督方法的滚动轴承智能故障诊断

A multi-stage semi-supervised learning approach for intelligent fault diagnosis of rolling bearing using data augmentation and metric learning

摘要

著录项

相似文献

相关主题

期刊订阅