سال انتشار:
2020
عنوان انگلیسی مقاله:
Design of control framework based on deep reinforcement learning and Monte-Carlo sampling in downstream separation
ترجمه فارسی عنوان مقاله:
طراحی چارچوب کنترل مبتنی بر یادگیری تقویت عمیق و نمونه برداری از مونت-کارلو در جداسازی پایین دست
منبع:
Sciencedirect - Elsevier - Computers and Chemical Engineering, 140 (2020) 106910. doi:10.1016/j.compchemeng.2020.106910
نویسنده:
Soonho Hwangbo ∗, Gürkan Sin
چکیده انگلیسی:
This paper proposes a systematic framework to develop deep reinforcement learning (RL)-based algo- rithms for control system of downstream separation in biopharmaceutical process as follows. First, a sim- ulation model as a digital twin is built and Monte-Carlo sampling generates substantial amounts of sam- ples considering disturbances. Second, the deep RL-based control system is designed and the optimization subject to sample datasets is conducted. The methodology is implemented in a prototype software and relevant codes are shared by Mendeley Data. The proposed model is successfully applied to control the liquid-liquid extraction column for the recovery of fusidic acid as part of downstream processing. The resulting deep RL algorithm provides an operation performance with a better API recovery yield (32 % higher than open loop operation) and lower deviations (23 % lower than open loop operation) against disturbances.
Keywords: Liquid-liquid extraction column | Deep reinforcement learning | Monte-Carlo sampling | Control system | API production | Biopharmaceuticals
قیمت: رایگان
توضیحات اضافی:
تعداد نظرات : 0