Prior Knowledge-Assisted Self-Supervised Learning for Soft Fault Diagnosis with Limited Fault Samples in Optical Networks
We proposed a prior knowledge-assisted self-supervised learning scheme for soft fault diagnosis in optical networks with limited fault samples, achieving the highest average F1-score of 0.9902 and FNR of 0.0891 through prior knowledge embedding.
Authors
- Qian Guo (ORCID: https://orcid.org/0000-0003-0930-3174)
- Danshi Wang (ORCID: https://orcid.org/0000-0001-9815-4013)
- Xiao Xue (ORCID: https://orcid.org/0000-0001-5396-3909)
- Min Zhang (ORCID: https://orcid.org/0000-0002-8186-9159)
- Chunyu Zhang (ORCID: https://orcid.org/0000-0002-5682-1647)
- Zhiming Sun (ORCID: https://orcid.org/0009-0007-8524-4651)
Institutions
- Beijing University of Posts and Telecommunications (CN)
- State Key Laboratory of Information Photonics and Optical Communications
Publication Details
- Published
- 2025-06-29
- DOI
- https://doi.org/10.23919/oecc/psc62146.2025.11109540
- Primary Topic
- Fault Detection and Control Systems
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China