.png){kind=icon}
.png){kind=icon}
Return
Application of data-driven surrogate-assisted evolutionary algorithm for optimization and heat transfer analysis of helical groove tubes
.png){kind=icon}
PRE
AI
S
L
H
G
Y
S
Y
M
DOI：10.1016/j.ijthermalsci.2026.111191.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Field synergy and secondary flow analyses identify the semi-elliptical groove as optimal for heat transfer. A GAN–SVM data augmentation strategy generates high-fidelity datasets for heat-transfer optimization. An improved MPGA–BPNN–MPGA model delivers superior accuracy in nonlinear parameter–performance mapping.
Keywords:
Helical groove tube
Enhanced heat transfer
Field synergy theory
Generative adversarial network
Support vector machine
Multi-population genetic algorithm–backpropagation neural network
Journal
IF:
5
Papers:
8.5K
Citations:
2.5W
Organization
Cited Papers