TIG welding defect detection using ResNet and Random Forest
Vu Quang Huy, Vu Minh Thuan, Hoang Van Huong, Tran Minh The Uyen, Van-Thuc Nguyen, Pham Son Minh · 2026
Read TIG welding defect detection using ResNet and Random Forest by Vu Quang Huy, Vu Minh Thuan, Hoang Van Huong, Tran Minh The Uyen, Van-Thuc Nguyen, Pham Son Minh (2026) 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/plos-pone-0353276.txt.
Description
Vu Quang Huy led a team of six authors on this 2026 study of automatic weld inspection in precision manufacturing. Orbital TIG welds must be checked for flaws, but human review of weld images is slow and defects vary in shape and size. The team trained a system on more than three thousand weld photos sorted into normal welds and three fault types.
A deep network first extracted visual features, then a random forest classifier made the final call, reaching high accuracy across repeated testing. The pairing beat plain neural networks and older machine learning. Huy offers it for factory quality lines.
Catalog record
| CREATOR | Vu Quang Huy, Vu Minh Thuan, Hoang Van Huong, Tran Minh The Uyen, Van-Thuc Nguyen, Pham Son Minh |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 24899 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |