Multimodal semantic learning for early fault diagnosis in warp knitting machines via masked fault modeling
Wei Gao, Han Shi, Dazhou Li, Yang Liu · 2026
Read Multimodal semantic learning for early fault diagnosis in warp knitting machines via masked fault modeling by Wei Gao, Han Shi, Dazhou Li, Yang Liu (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/PMC13538714.txt.
Description
Wei Gao and colleagues build a multimodal learning system for early fault warning in warp knitting machines in a 2026 study. Vision checks spot defects only once fabric damage shows, too late for prevention. The framework fuses sensor streams and fabric images into one shared code space, learns process patterns by rebuilding hidden states, and fabricates extra examples of rare faults to fix class imbalance.
On ten thousand hours of real factory data, the system beat rival baselines across metrics with a high combined score and detection in about a tenth of a second. Faults were flagged before visible defects emerged. The authors offer the design as a practical route to smart maintenance in high-speed textile production.
Catalog record
| CREATOR | Wei Gao, Han Shi, Dazhou Li, Yang Liu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 114724 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |