| 引用本文: | 贾峰,李世豪,沈建军,关海宁.面向轴承智能诊断的多领域深度对抗迁移网络[J].哈尔滨工业大学学报,2022,54(7):120.DOI:10.11918/202103084 |
| JIA Feng,LI Shihao,SHEN Jianjun,GUAN Haining.Multi-domain deep adversarial transfer network for intelligent diagnosis of bearings[J].Journal of Harbin Institute of Technology,2022,54(7):120.DOI:10.11918/202103084 |
|
| 摘要: |
| 针对不同工况下轴承监测数据分布差异性导致的诊断精度下降问题,基于深度学习与迁移学习,提出一种多领域深度对抗迁移网络,用于变工况下轴承的智能诊断。将不同工况下的样本集视作属于不同的领域,在特征提取时利用深度残差网络将轴承源域的训练数据与目标域的测试数据映射到高维特征空间,提取监测数据高层抽象的特征表示；设计多领域对抗模块,以支持多故障模式的轴承样本在不同领域对抗模块上进行对抗迁移训练,保障源域与目标域数据在特征空间中的分布有效对齐；在利用源域数据训练故障分类器时引入标签平滑约束,增强故障识别的泛化能力,将源域故障诊断知识迁移到目标域数据的故障信息识别,实现变工况下的轴承智能诊断。利用变工况下的齿轮箱轴承故障数据集与电机轴承数据集对提出方法进行验证,结果表明:相比其他方法,提出的新方法考虑了轴承监测数据的多故障模式结构,更好地提取了领域不变特征,提升了变工况下轴承故障的识别精度。 |
| 关键词: 深度学习 变工况 轴承 领域对抗 迁移学习 智能诊断 |
| DOI：10.11918/202103084 |
| 分类号:TH17 |
| 文献标识码:A |
| 基金项目:陕西省自然科学基础研究计划(2020JQ-365)； 中国博士后科学基金(2020M683393)； 中央高校基本科研业务费专项资金(300102250302) |
|
| Multi-domain deep adversarial transfer network for intelligent diagnosis of bearings |
|
JIA Feng,LI Shihao,SHEN Jianjun,GUAN Haining
|
|
（Key Laboratory of Road Construction Technology and Equipment（Chang′an University）, Ministry of Education, Xi′an 710064, China）
|
| Abstract: |
| The bearing monitoring data under different working conditions have different distributions, which affect the accuracy of bearing intelligent diagnosis methods. Aiming at this issue, a multi-domain deep adversarial transfer network is proposed for intelligent diagnosis of bearings based on deep learning and transfer learning. The proposed method treats the datasets under different working conditions as belonging to different domains. In the method, firstly, the deep residual network is used to extract the features from source training data and target testing data. Then, multiple domain adversarial modules are designed to capture multi-mode structures from the source and target domain data, which enable fine-grained alignment of the distribution of the source domain and target domain data. Finally, the fault classifier is trained to transfer fault diagnosis knowledge of source domain to the target domain and ensure the diagnosis accuracy under variable working conditions. The proposed method is verified by using the two bearings dataset under variable working conditions. The results show that the proposed method can capture the multi-mode structures of the bearing data and extract domain invariant features, thus improving the fault diagnosis accuracy under variable working conditions compared with other related methods. |
| Key words: deep learning variable working condition bearing adversarial domain adaptation transfer learning intelligent diagnosis |
