摘要
In machinery fault diagnosis,labeled data are always difficult or even impossible to obtain.Transfer learning can leverage related fault diagnosis knowledge from fully labeled source domain to enhance the fault diagnosis performance in sparsely labeled or unlabeled target domain,which has been widely used for cross domain fault diagnosis.However,existing methods focus on either marginal distribution adaptation(MDA)or conditional distribution adaptation(CDA).In practice,marginal and conditional distributions discrepancies both have significant but different influences on the domain divergence.In this paper,a dynamic distribution adaptation based transfer network(DDATN)is proposed for cross domain bearing fault diagnosis.DDATN utilizes the proposed instance-weighted dynamic maximum mean discrepancy(IDMMD)for dynamic distribution adaptation(DDA),which can dynamically estimate the influences of marginal and conditional distribution and adapt target domain with source domain.The experimental evaluation on cross domain bearing fault diagnosis demonstrates that DDATN can outperformance the state-of-the-art cross domain fault diagnosis methods.
基金
Supported by National Natural Science Foundation of China(Grant Nos.51875208,51475170)
National Key Research and Development Program of China(Grant No.2018YFB1702400).
作者简介
Yixiao Liao,born in 1992,is currently a PhD candidate at School of Mechanical&Automotive Engineering,South China University of Technology,China,where he received his bachelor’s degree in 2015.His research interests include deep learning,transfer learning,and adversarial learning for fault diagnosis and prognostics;Ruyi Huang,born in 1992,is currently a PhD candidate at School of Mechani-cal&Automotive Engineering,South China University of Technology,China.He received his B.S degree on mechanical engineering in Qingdao University,China,in 2014.His current research interests include deep learning and transfer learning methods for intelligent fault diagnostics and prognostics of rotating machinery;Jipu Li,born in 1994,is currently a PhD candidate at School of Mechanical&Automotive Engineering,South China University of Technology,China.He received his B.S.and M.S.degree on mechanical engineering from Lanzhou University of Technology,China,in 2015 and 2018,respectively.His current research interests include deep learning and deep transfer learning methods for fault diagnosis and prognostics;Zhuyun Chen,born in 1991,is currently a post doctor at School of Mechani-cal&Automotive Engineering,South China University of Technology,China.He received his B.S degree on mechanical design,manufacturing,and automation from Nanjing Agricultural University,China,in 2013.His current research interests include dynamic signal processing and deep learning methods for mechanical fault diagnosis and prognostics.His current research interests include deep learning and deep transfer learning methods for fault diagnosis and prognostics;Correspondence:Weihua Li,born in 1973,is currently a professor at School of Mechanical&Automotive Engineering,South China University of Technology,China.His main research interests include nonlinear time series analysis,dynamic signal processing,autonomous driving,and machine learning methods for condition monitoring and health diagnosis of complex dynamical systems.whlee@scut.edu.cn。
