Neural Topology Optimization Via Active Learning for Efficient Channel Design in Turbulent Mass Transfer
Source abstract
Abstract
Abstract The design of fluid channel structures of reactors or separators of chemical processes is a key to enhancing the mass transfer processes inside the devices. However, systematically designing channel topological structures remains challenging for complex turbulent flows. Here, this challenge is addressed by developing a machine learning framework to efficiently perform topology optimization of channel structures for turbulent mass transfer. A topological structure is represented using a neural network (referred to as “neural topology”), which is optimized by employing pre‐trained neural operators combined with a fine‐tuning strategy with active data augmentation. The optimization is performed targeting two objectives: maximization of mass transfer efficiency and minimization of energy consumption, for the possible considerations of compromise between the two in real‐world designs. The developed neural operator with active learning is data efficient in network training and demonstrates superior computational efficiency compared with traditional methods in obtaining optimal structures across a large design space. The optimization results are experimentally validated, proving that the optimized channel improves concentration uniformity by 37% compared to the original channel. The variation of the optimal structures with changes in inlet velocity conditions is also demonstrated, offering insights for designing turbulent mass transfer devices under various operating conditions.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Model Reduction and Neural Networks · Heat Transfer and Optimization · Heat Transfer and Boiling Studies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Chemical Engineering and Technology, State Key Laboratory of Chemical Engineering Tianjin University Tianjin 300072 China
College of Chemistry & Chemical Engineering Yantai University Yantai 264005 China
Department of Statistics and Data Science Yale University New Haven CT 06511 USA
Department of Chemical Engineering University College London London WC1E 7JE UK
Funding
National Natural Science Foundation of China
References (53)
Show source-provided references
1. Sánchez J. · AIChE J. · 2014 · 60 · 3089
2. 10.1016/j.ces.2012.03.00210.1016/j.ces.2012.03.002 ↗
3. 10.1016/j.cej.2007.10.00810.1016/j.cej.2007.10.008 ↗
4. Sundararajan V. · Nat. Phys. · 2009 · 5 · 1026
5. 10.1016/j.ces.2018.12.06410.1016/j.ces.2018.12.064 ↗
6. Kumar R. · Chem. Eng. J. · 2014 · 243 · 206
7. Tao L. · Chem. Eng. Sci. · 2017 · 153 · 109
8. Hassan M. Y. · AIChE J. · 2020 · 66 · 3101
9. 10.1016/j.est.2024.11230310.1016/j.est.2024.112303 ↗
10. 10.1016/j.ijheatmasstransfer.2007.09.02410.1016/j.ijheatmasstransfer.2007.09.024 ↗
11. 10.1016/j.energy.2010.04.05310.1016/j.energy.2010.04.053 ↗
12. 10.1016/j.jpowsour.2016.05.11010.1016/j.jpowsour.2016.05.110 ↗
13. 10.1016/j.fuel.2022.12440110.1016/j.fuel.2022.124401 ↗
14. 10.1016/S0017-9310(99)00311-710.1016/S0017-9310(99)00311-7 ↗
15. Bendsoe M. P. · 2013
16. 10.1016/j.mtphys.2022.10075410.1016/j.mtphys.2022.100754 ↗
17. 10.1364/OL.55938410.1364/OL.559384 ↗
18. 10.1016/j.ces.2020.11626510.1016/j.ces.2020.116265 ↗
19. 10.1016/j.compchemeng.2019.10670710.1016/j.compchemeng.2019.106707 ↗
20. 10.1016/j.ces.2017.05.04010.1016/j.ces.2017.05.040 ↗
21. 10.1016/j.cej.2010.05.06810.1016/j.cej.2010.05.068 ↗
22. 10.1038/nmat116410.1038/nmat1164 ↗
23. 10.1016/j.ces.2024.11975210.1016/j.ces.2024.119752 ↗
24. 10.1038/s42254-021-00314-510.1038/s42254-021-00314-5 ↗
25. 10.1126/science.aaw474110.1126/science.aaw4741 ↗
26. 10.1016/j.ynexs.2024.10001610.1016/j.ynexs.2024.100016 ↗
27. 10.1002/smtd.20240062010.1002/smtd.202400620 ↗
28. 10.1038/s42256-021-00302-510.1038/s42256-021-00302-5 ↗
29. 10.1137/22M147775110.1137/22M1477751 ↗
30. 10.1016/j.cma.2022.11477810.1016/j.cma.2022.114778 ↗
31. A.Jiao H.He R.Ranade J.Pathak L.Lu arXiv preprint arXiv:2104.055122021.
32. A.Jiao Q.Yan J.Harlim L.Lu arXiv preprint arXiv:2407.054772024.
33. 10.1016/j.cma.2023.11606410.1016/j.cma.2023.116064 ↗
34. 10.1038/s41467-025-56122-310.1038/s41467-025-56122-3 ↗
35. 10.1038/s44286-024-00099-110.1038/s44286-024-00099-1 ↗
36. Y.Yang R.Li Y.Zhang H.Chen inAIAA SCITECH 2024 Forum 2024 1227.
37. 10.2514/1.J06457610.2514/1.J064576 ↗
38. 10.1126/sciadv.adq237510.1126/sciadv.adq2375 ↗
39. 10.1103/PhysRevResearch.4.02321010.1103/PhysRevResearch.4.023210 ↗
40. 10.1137/21M139790810.1137/21M1397908 ↗
41. Z.Hao C.Ying H.Su J.Zhu J.Song Z.Cheng arXiv preprint arXiv:2209.070752022.
42. 10.1016/j.cma.2023.11630010.1016/j.cma.2023.116300 ↗
43. 10.1016/j.ress.2024.11039210.1016/j.ress.2024.110392 ↗
44. Lee J. E. · Eng. Appl. Comput. Fluid Mech. · 2024 · 18
45. 10.2528/PIER2401220110.2528/PIER24012201 ↗
46. 10.1016/j.ces.2021.11730610.1016/j.ces.2021.117306 ↗
47. Batchelor G. K. · 1967
48. Launder B. E. · 1983
49. 10.1007/978-3-642-53911-410.1007/978-3-642-53911-4 ↗
50. 10.1016/j.ces.2021.11714810.1016/j.ces.2021.117148 ↗
51. Z.Li N.Kovachki K.Azizzadenesheli B.Liu K.Bhattacharya A.Stuart A.Anandkumar arXiv preprint arXiv:2010.088952020.
52. 10.1016/j.advwatres.2022.10418010.1016/j.advwatres.2022.104180 ↗
53. 10.1137/19M127406710.1137/19M1274067 ↗