Multitarget domain adaptation with transferable hyperbolic prototypes for intelligent fault diagnosis
作者：
Highlights：
• A versatile model is proposed for multitarget domain adaptation.
• A target blending strategy is proposed to achieve pairwise domain alignment.
• Decision consistency is facilitated by prototypical score alignment in hyperbolic space.
• Extensive experiments and comparisons with frontier methods are conducted.
摘要
•A versatile model is proposed for multitarget domain adaptation.•A target blending strategy is proposed to achieve pairwise domain alignment.•Decision consistency is facilitated by prototypical score alignment in hyperbolic space.•Extensive experiments and comparisons with frontier methods are conducted.
论文关键词：Intelligent fault diagnosis,Multitarget domain adaptation,Target blending,Hyperbolic prototype,Classification consistency
论文评审过程：Received 6 June 2022, Revised 21 September 2022, Accepted 25 September 2022, Available online 30 September 2022, Version of Record 14 October 2022.
论文官网地址：https://doi.org/10.1016/j.knosys.2022.109952
