Domain generalization for cross-domain fault diagnosis: An application-oriented perspective and a benchmark study

•The first taxonomy for domain generalization-based fault diagnosis is proposed.•A basic and reproducible code framework is provided.•A broad discussion of critical challenges and future directions is presented. Most data-driven methods for fault diagnostics rely on the assumption of independently a...

Full description

Saved in:
Bibliographic Details
Published in:Reliability engineering & system safety Vol. 245; p. 109964
Main Authors: Zhao, Chao, Zio, Enrico, Shen, Weiming
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.05.2024
Elsevier
Subjects:
Deep learning
Domain generalization
Domain shift
Engineering Sciences
Fault diagnosis
Fault diagnosis
Domain shift
Deep learning
Domain generalization
ISSN:0951-8320, 1879-0836
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•The first taxonomy for domain generalization-based fault diagnosis is proposed.•A basic and reproducible code framework is provided.•A broad discussion of critical challenges and future directions is presented. Most data-driven methods for fault diagnostics rely on the assumption of independently and identically distributed data of training and testing. However, domain shift between the phases of training and testing is common in practice. Recently, domain generalization-based fault diagnosis (DGFD) has gained widespread attention for learning fault diagnosis knowledge from multiple source domains and applying it to unseen target domains. This paper summarizes the developments in DGFD from an application-oriented perspective. Firstly, basic definitions of DGFD and its variant applications are formulated. Then, motivations, goals, challenges and state-of-the-art solutions for different applications are discussed. The limitations of existing technologies are highlighted. A comprehensive benchmark study is carried out on eight open-source and two self-collected datasets to provide an understanding of the existing methods and a unified framework for researchers. Finally, several future directions are given. Our code is available at https://github.com/CHAOZHAO-1/DG-PHM.
ISSN:0951-8320
1879-0836
DOI:10.1016/j.ress.2024.109964