| 张金汇,谢林柏.基于改进域对抗网络的轴承故障迁移诊断方法[J].电子测量与仪器学报,2022,36(11):107-115 |
| 基于改进域对抗网络的轴承故障迁移诊断方法 |
| Bearing fault migration diagnosis method based onimproved domain adversarial network |
| |
| DOI： |
| 中文关键词: 轴承故障 智能故障诊断 无标签数据 对抗迁移网络 |
| 英文关键词:bearing fault intelligent fault diagnosis unlabeled data adversarial network |
| 基金项目:国家自然科学基金（61873112）项目资助 |
|
|
|
|
| 摘要点击次数: 809 |
| 全文下载次数: 884 |
| 中文摘要: |
| 针对工业场景下复杂工况导致的轴承故障数据特征分布差异,以及难以获得大量有标签数据的问题,提出一种基于
Wasserstein 距离与局部最大平均偏差(LMMD)改进的一维卷积子域适应对抗迁移网络(SANN)。 该网络首先构建 CNN 特征提
取器进行预训练,学习领域特征表示,在对抗训练阶段,对抗层引入 Wasserstein 距离来度量源域与目标域的差异,实现边缘分
布的对齐,固化训练结果。 在特征提取层引入 LMMD 计算模块捕获每个类别的细粒度信息,实现条件分布的对齐。 通过两种
变工况下的轴承故障数据集对该模型性能进行验证。 实验结果表明,无监督的条件下,本文所提方法在目标数据集上相较于基
础域对抗网络分别提高了 5. 0% 和 6. 9% 的识别精度,性能优于现有的迁移算法。 |
| 英文摘要: |
| Aiming at the difference of bearing fault data feature distribution caused by complex working conditions in industrial scenes
and the difficulty of obtaining a large number of labeled data, an one-dimensional convolution subdomain adaptive adversarial neural
network (SANN) based on Wasserstein distance and local maximum mean discrepancy ( LMMD) is proposed. Firstly, the network
constructs a feature extractor based on CNN for pre-training and learning the domain feature representation. In the adversarial training
stage, the adversarial layer introduces Wasserstein distance to measure the difference between the source domain and the target domain,
realize the alignment of marginal distribution and solidify the training results. In the feature extraction layer, LMMD calculation module
is introduced to capture the fine-grained information of each category to realize the alignment of conditional distribution. The performance
of the model is verified by the bearing fault data sets under two different working conditions. The experimental results show that under
unsupervised conditions, the proposed method improves the recognition accuracy by 5. 0% and 6. 9% respectively compared with the
basic domain adversarial network on the target data set, and the performance is better than the existing migration algorithms. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
