Multimodal deep learning and genetic algorithms for adaptive optimization of injection stretch blow molding with nonconformal temperature control
Nahyun Kim, Yongjae Jeon, Pil-Ho Lee, Sang Won Lee · 2026
Read Multimodal deep learning and genetic algorithms for adaptive optimization of injection stretch blow molding with nonconformal temperature control by Nahyun Kim, Yongjae Jeon, Pil-Ho Lee, Sang Won Lee (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/pmc-13578238.txt.
Description
Nahyun Kim, Yongjae Jeon, Pil-Ho Lee, and Sang Won Lee teach a factory process to retune itself as room conditions drift. Their study from twenty twenty-six covers injection stretch blow moulding. Lamp heating shapes bottle preforms before blowing. When ambient heat shifts, quality drifts despite fixed settings.
Thermal images, lamp settings, and room variables feed one model. The network predicts the preform's temperature pattern after heating. A genetic algorithm then searches for corrected lamp settings. Cross-validation showed temperature predictions within a couple of degrees. Weighted losses emphasise the quality-sensitive regions of the preform. In-situ adjustment replaces slow offline trial and error. Smart factories gain a self-correcting heating loop.
Catalog record
| CREATOR | Nahyun Kim, Yongjae Jeon, Pil-Ho Lee, Sang Won Lee |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 54 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |