文献类型：期刊文献

英文题名：Multi-objective optimization of oxygen transfer and hydrodynamic shear in dual-impeller stirred tanks via integrated computational fluid dynamics and machine learning framework

作者：Gu, Qingfeng[1];Ji, Shuoyan[1];Liu, Yongqiang[1];Wang, Yongbo[1];Yu, Junxiong[1];Wang, Zejian[1];Zhuang, Yingping[1];Li, Chao[1,2]

机构：[1]East China Univ Sci & Technol, State Key Lab Bioreactor Engn, 130 Meilong Rd, Shanghai 200237, Peoples R China;[2]Suzhou Womei Biol Co Ltd, Suzhou 215614, Peoples R China

年份：2026

卷号：446

外文期刊名：BIORESOURCE TECHNOLOGY

收录：;EI(收录号：20261420416653);WOS:【SCI-EXPANDED(收录号:WOS:001691587500001)】；

基金：This work was supported by the National Natural Science Foundation of China [No. 22208099] , Shanghai Key Technology R & D Program "Synthetic Biology" Project [No. 25HC2820600] , and the Yangtze River Delta Community of Sci-Tech Innovation Joint R & D Projects [No. 2024CSJGG01800] .

语种：英文

外文关键词：Stirred-tank bioreactor; Oxygen mass transfer; Shear strain rate; Blakesleatrispora; beta-carotene

摘要：Optimizing the structure of stirred bioreactors is crucial to improve the efficiency of biomanufacturing. This study proposes an intelligent design framework integrating computational fluid dynamics (CFD), machine learning (ML), and the non-dominated sorting genetic algorithm II (NSGA-II) to co-optimize the oxygenation and shear performance of a dual-impeller stirred tank. Initially, a parameterized CFD model was employed to systematically investigate the impacts of impeller inclination angles, dimensions, and blade numbers on the volumetric oxygen transfer coefficient (k(L)a) and shear strain rate. Subsequently, six ML algorithms were evaluated using a dataset of 837 CFD-generated samples, where the artificial neural network (ANN) demonstrated superior predictive accuracy (R-2 > 0.97) and was selected as the surrogate model. Utilizing the NSGA-II algorithm coupled with the ideal point decision-making method, an optimal asymmetric impeller configuration was identified from the Pareto-optimal frontier. The results reveal that the optimized design enhanced k(L)a by 98.4% (reaching 312.5 h(-1)) while maintaining a shear intensity comparable to the baseline. Finally, fermentation experiments with Blakeslea trispora confirmed that the optimized configuration led to a 30.9% increase in beta-carotene yield (attaining 3193 mg/L). This work provides a robust and efficient methodology for the rational design of bioreactors and offers a new pathway for the intensification of shear-sensitive bioprocesses.