Inverse input optimization for tuning two-ply yarn processing parameters using feedforward neural network
Habib Amiri Savadroodbari, Mohsen Rezahasani, Mohammad Javad Abghary, Aliasghar Alamdar Yazdi · 2026
Read Inverse input optimization for tuning two-ply yarn processing parameters using feedforward neural network by Habib Amiri Savadroodbari, Mohsen Rezahasani, Mohammad Javad Abghary, Aliasghar Alamdar Yazdi (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/PMC13578441.txt.
Description
Habib Amiri Savadroodbari and colleagues tune a cotton yarn process by running a trained neural network in reverse, in a 2026 study. Factories set twist levels by trial and error to hit a target yarn strength. Their network first learned how settings map to strength from plant data. Then the settings themselves were nudged, step by step, until the network forecast the wanted strength.
Twist direction proved the biggest lever on strength, ahead of twist amounts. The best recipe used matching high twists in each single strand, a slightly lower combined twist, and a Z direction wrap. Strength rose by about a quarter over the starting yarn. A rival genetic search matched the cost score yet needed nearly four times the computing tries.
Catalog record
| CREATOR | Habib Amiri Savadroodbari, Mohsen Rezahasani, Mohammad Javad Abghary, Aliasghar Alamdar Yazdi |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 71269 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |