TCQI-YOLOv5: A Terminal Crimping Quality Defect Detection Network
Yingjuan Yu, Dawei Ren, Lingwei Meng, Chiman Kwan · 2025
Read TCQI-YOLOv5: A Terminal Crimping Quality Defect Detection Network by Yingjuan Yu, Dawei Ren, Lingwei Meng, Chiman Kwan (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12736603.txt.
Description
Crimped wire terminals decide whether car electronics stay reliable, and Yingjuan Yu and co-authors automate their inspection with a tuned vision network. Workers now check crimps by eye, which is slow, tiring, and prone to misses. The team adapts the YOLOv5 detector with a stronger feature module, an attention block that spots small targets, and a better box-fitting loss.
The upgraded network catches hard defects such as shallow insulation crimps far better than rivals. Its mean average precision reached 98.3 percent in tests. Speed stayed fast enough for live factory use. The authors present the system as ready for real production lines, where it could replace much manual checking.
Catalog record
| CREATOR | Yingjuan Yu, Dawei Ren, Lingwei Meng, Chiman Kwan |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 47 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |