| 乔万,刘秀丽,吴国新,黄金鹏.时变小样本条件下基于对比学习的故障诊断[J].电子测量与仪器学报,2024,38(8):113-123 |
| 时变小样本条件下基于对比学习的故障诊断 |
| Fault diagnosis based on contrastive learning undertime-varying small sample conditions |
| |
| DOI： |
| 中文关键词: 对比学习 时变工况 小样本 深度卷积网络 故障诊断 |
| 英文关键词:contrastive learning time varying operating conditions small sample deep convolutional neural networks fault diagnosis |
| 基金项目:国家自然科学基金(62303065)、机电系统测控北京市重点实验室开放课题（KF20222223201）项目资助 |
|
|
|
|
| 摘要点击次数: 34 |
| 全文下载次数: 107 |
| 中文摘要: |
| 时变工况下的故障诊断往往具有高度动态性，而小样本下模型学习受限使得问题更加棘手。针对上述情况，提出了基于对比深度卷积网络的故障诊断方法：首先，针对数据样本量小的特点，利用速度变化引起的振动数据分布差异，无需进行人工操作自然实现数据增强；然后，在数据处理过程中，采用不同转速下相同健康状态的振动数据作为正样本，同时将不同健康状态下的振动数据作为负样本，通过比较样本之间的相似度来提取关键特征，从而缩小正样本之间的距离，同时增大负样本之间的距离；最后采用对比训练方式进行训练优化，将对比损失和交叉熵损失加权组合作为综合损失函数，使模型在学习特征表示的同时能有效进行分类任务。将该方法分别应用于两种不同时变转速下轴承故障数据集进行案例研究。试验结果表明，所提模型不仅在特征提取和分类任务中表现优异，而且在数据匮乏和时变转速工况下均能实现高准确率的故障诊断。验证了所提模型在处理时变小样本数据方面表现出较高的可行性和有效性，且优于其他先进诊断方法。 |
| 英文摘要: |
| In the context of time-varying operating conditions, fault diagnosis often exhibits high dynamism, while the limited model learning under small samples makes the issue more challenging. For the above situation, a fault diagnosis method based on contrastive deep convolutional networks is proposed. Firstly, considering the characteristic of small data samples, take advantage of differences in vibration data distribution caused by speed changes, and naturally realize data enhancement without manual operation. Subsequently, in the process of data processing, the vibration data of the same healthy state at different rotational speeds are used as positive samples, while the vibration data from different health states are used as negative samples. The key features are extracted by comparing the similarity between the samples so as to reduce the distance between the positive samples while increasing the distance between the negative samples. Finally, the feature extractor is trained and optimized by comparative training method, where a weighted combination of contrastive loss and cross-entropy loss is used as the composite loss function, enabling the model to effectively perform classification tasks while learning feature representations. The method is applied to two different bearing failure datasets at different time-varying rotational speeds for case studies respectively. The experimental results show that the proposed model not only performs well in the feature extraction and classification tasks, but also realizes high accuracy fault diagnosis under both data scarcity and time-varying speed conditions. It is verified that the proposed model shows high feasibility and effectiveness in dealing with time-varying small-sample data, and outperforms other advanced diagnostic methods. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
