Reinforcement-Learning-Enabled Supervisory Control of a Full-Scale Anaerobic Digestion Facility Using a Calibrated Digital Twin
Ahmed I Yunus, Srinivas Jalla, Joe F Bozeman, Yongsheng Chen · 2026
Read Reinforcement-Learning-Enabled Supervisory Control of a Full-Scale Anaerobic Digestion Facility Using a Calibrated Digital Twin by Ahmed I Yunus, Srinivas Jalla, Joe F Bozeman, Yongsheng Chen (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/PMC13648226.txt.
Description
Ahmed I. Yunus and three colleagues test a reinforcement-learning controller, software that learns actions from rewards, for a full-scale anaerobic digestion plant that turns wastewater solids into biogas. Digesters are usually run cautiously because feedback is slow and upsets can destabilise the biology.
A calibrated digital twin model of the plant was built first, then a learning policy was trained on simulated years of operation to raise gas output while penalising acidity and instability signals. Tested against historical and rule-based control, the policy matched output in simulation and suggested a modest possible gain on real plant data. The authors stress that the benefit carries substantial uncertainty and needs careful interpretation.
Catalog record
| CREATOR | Ahmed I Yunus, Srinivas Jalla, Joe F Bozeman, Yongsheng Chen |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 53 KB |
| LICENSE | This article is licensed under CC-BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |