PulseTrendingJournal ClubResearchersJournalsExplore
Instagram
HomeTrendingJournal ClubExplore
Synapse
⌘+K
Synapse
April 10, 2026Structural durability & health monitoringOpen Access

An Intelligent Assessment of Rail Surface Defects over the Life-Cycle Based on Improved Transformer Networks

View Full Paper
Ask AI
Bookmark
Share

Authors

ZYZiliang YangMSMykola SysynJLJin Li

Discussion

Loading...

Member takes

Overview

Introduces deep learning evaluation for rail defects, enhancing maintenance predictions for better safety.

Key Points

  • The aim is to accurately assess rail rolling contact fatigue stages to guide maintenance and enhance safety.
  • Developed an improved deep learning network based on Swin Transformer.
  • Divided the rail rolling contact fatigue failure process into five life-cycle stages.
  • Applied image processing to evaluate rail surface conditions.
  • Achieved a recognition rate of 98.48% using the improved Transformer compared to other models.
  • Identified potential failure hazards on rail surfaces.
  • Provided early warning predictions for rolling contact fatigue failure.

Cite This Study

Yang et al. (2026) studied this question.

synapsesocial.com/papers/69d895486c1944d70ce0640ehttps://doi.org/10.32604/sdhm.2026.078140
View Full Paper
Ask AI
Bookmark
Share