Open AccessResearch on Application of Transfer Learning in Equipment Fault Diagnosis
Author(s) -
Tian Xiang,
Daming Wu,
Huaiguang Wang
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1986/1/012099
Subject(s) - transfer of learning , fault (geology) , computer science , domain (mathematical analysis) , field (mathematics) , fault detection and isolation , artificial intelligence , systems engineering , engineering , mathematical analysis , mathematics , pure mathematics , actuator , seismology , geology
In view of the complex and changeable operating conditions of equipment, and the different distribution of measured data, it is difficult to promote the application of fault diagnosis technology. Many scholars have introduced transfer learning to overcome the lack of training data for deep learning by transferring existing data and models in similar domains into the target domain, it has expanded the application of fault diagnosis technology. This paper introduces the related concepts of transfer learning, summarizes the current applications and existing problems of transfer learning in the field of fault diagnosis, and finally puts forward further research directions and suggestions in general detection, real-time detection, etc. The purpose is to better improve equipment support capabilities.