首页|Label Recovery and Trajectory Designable Network for Transfer Fault Diagnosis of Machines With Incorrect Annotation
Label Recovery and Trajectory Designable Network for Transfer Fault Diagnosis of Machines With Incorrect Annotation
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
国家科技期刊平台
NETL
NSTL
万方数据
The success of deep transfer learning in fault diag-nosis is attributed to the collection of high-quality labeled data from the source domain.However,in engineering scenarios,achieving such high-quality label annotation is difficult and expensive.The incorrect label annotation produces two negative effects:1)the complex decision boundary of diagnosis models lowers the generalization performance on the target domain,and 2)the distribution of target domain samples becomes misaligned with the false-labeled samples.To overcome these negative effects,this article proposes a solution called the label recovery and tra-jectory designable network(LRTDN).LRTDN consists of three parts.First,a residual network with dual classifiers is to learn features from cross-domain samples.Second,an annotation check module is constructed to generate a label anomaly indicator that could modify the abnormal labels of false-labeled samples in the source domain.With the training of relabeled samples,the com-plexity of diagnosis model is reduced via semi-supervised learning.Third,the adaptation trajectories are designed for sample distri-butions across domains.This ensures that the target domain sam-ples are only adapted with the pure-labeled samples.The LRTDN is verified by two case studies,in which the diagnosis knowledge of bearings is transferred across different working conditions as well as different yet related machines.The results show that LRTDN offers a high diagnosis accuracy even in the presence of incorrect annotation.
Deep transfer learningdomain adaptationincor-rect label annotationintelligent fault diagnosisrotating machines
Bin Yang、Yaguo Lei、Xiang Li、Naipeng Li、Asoke K.Nandi
展开 >
Key Laboratory of Education Ministry for Modern Design and Rotor-Bearing System, the School of Mechanical Engineering, Xi'an Jiaotong Univeristy, Xi'an 710049
Hunan Provincial Key Labortory of Health Maintenance for Mechanical Equipment, Hunan Univeristy of Science and Technology, Xiangtan 411201, China
Key Laboratory of Education Ministry for Modern Design and Rotor-Bearing System, Xi'an Jiaotong Univeristy, Xi'an 710049, China
Department of Electronic and Electrical Engineering, Brunel University London, Uxbridge UB8 3PH, UK
展开 >
国家重点研发计划国家杰出青年科学基金国家自然科学基金中国博士后科学基金China Postdoctoral Innovative Talents Support ProgramOpen Foundation of Hunan Provincial Key Laboratory of Health Maintenance for Mechanical Equipment中央高校基本科研业务费专项
国家科技期刊平台
NSTL
万方数据
