沈长青,雷飘,冯毅雄,黄伟国,江星星,朱忠奎.基于自适应流形嵌入动态分布对齐的轴承故障诊断[J].电子测量与仪器学报,2021,35(2):33-40 |
基于自适应流形嵌入动态分布对齐的轴承故障诊断 |
Bearing fault diagnosis based on adaptive manifold embedded dynamic distribution alignment |
|
DOI: |
中文关键词: 故障诊断 迁移学习 自适应分布对齐 流形学习 |
英文关键词:fault diagnosis transfer learning adaptive distribution alignment manifold learning |
基金项目:国家自然科学基金(51875375,51875376)、流体动力与机电系统国家重点实验室开放基金(GZKF 202022)项目资助 |
|
Author | Institution |
Shen Changqing | 1.School of Rail Transportation, Soochow University, Suzhou 215131, China; |
Lei Piao | 1.School of Rail Transportation, Soochow University, Suzhou 215132, China; |
Feng Yixiong | 2.State Key Laboratory of Fluid Power and Mechatronic Systems, Zhejiang University, Hangzhou 310027, China |
Huang Weiguo | 1.School of Rail Transportation, Soochow University, Suzhou 215131, China; |
Jiang Xingxing | 1.School of Rail Transportation, Soochow University, Suzhou 215132, China; |
Zhu Zhongkui | 1.School of Rail Transportation, Soochow University, Suzhou 215133, China; |
|
摘要点击次数: 920 |
全文下载次数: 4 |
中文摘要: |
智能故障诊断技术能有效保障机械设备安全运行,传统的轴承故障诊断通常假设标记的源域和未标记的目标域数据服从同一分布。然而,在实际的诊断场景中,轴承数据的条件分布和边缘分布往往不满足同分布假设。此外,在原始欧氏空间执行自适应分布对齐时,特征扭曲难以消除,从而影响故障诊断性能。通过提出一种具有流形特征学习和动态分布对齐的自适应轴承故障诊断模型,来解决上述问题。首先,在格拉斯曼流形中构造测地线流式核,提取与轴承故障信息相关的固有流形特征表示,以避免数据特征扭曲;其次,通过 distance定义一个跨域自适应因子来动态评估流形特征的条件分布和边缘分布;最后,基于结构风险最小化原则迭代求解一个跨域分类器,进而预测目标域样本标签。通过多个指标的实验分析,表明该模型能够有效避免特征扭曲,并利用动态权值调整跨域数据条件分布和边缘分布的相对重要性,验证了所提方法的有效性。 |
英文摘要: |
Intelligent fault diagnosis technology can effectively guarantee the safe operation of mechanical equipment. Traditional bearing fault diagnosis generally assumes that the labeled source and unlabeled target domain data follow the same distribution. However, the conditional and marginal distributions of bearing data usually do not satisfy the same distribution assumption in actual diagnosis scenarios. Moreover, feature distortions are difficult to eliminate when performing adaptive distribution alignment in the original Euclidean space, which affects the fault diagnosis performance. In this paper, an adaptive bearing fault diagnosis model based on manifold feature learning and dynamic distribution alignment is proposed to address these challenges. First, we construct a geodesic flow kernel in the Grassmann manifold and extract the inherent manifold feature representation associated with the bearing fault information, avoiding data feature distortions. Second, a cross domain adaptive factor is defined by distance to dynamically evaluate the conditional and marginal distributions of manifold features. Finally, a cross domain classifier is solved iteratively to predict the target domain samples under the principle of structural risk minimization. The experimental analysis of multiple indicators shows that the model can effectively avoid feature distortions and use dynamic weights to adjust the relative importance of conditional and marginal distributions between cross domain data, which verifies the effectiveness of the proposed method. |
查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|