Dual-Level XAI-Guided Digital Twin Framework for Prescriptive Decision Making in Sensor-Driven Manufacturing
Joonyong Park · 2026
Read Dual-Level XAI-Guided Digital Twin Framework for Prescriptive Decision Making in Sensor-Driven Manufacturing by Joonyong Park (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-13611365.txt.
Description
Joonyong Park presents a digital twin framework for precision lens molding that not only predicts defects but prescribes fixes, in a 2026 study. Optical lens production tolerates only tiny deviations in lens power, a quarter diopter either way. The system watches streams of sensor data, such as melt temperature and injection pressure, from the molding machines.
A transformer model trained on 175,089 sensor logs acts as the twin, predicting lens power with an accuracy score of 0.97 in standard tests. A stricter test that holds out whole machines still scored 0.88, which supports use on new equipment. Explanations run at two levels, checking both the model's internal attention and a global stand-in model, so engineers can audit why it recommends a change.
Catalog record
| CREATOR | Joonyong Park |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 47 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |