.png){kind=icon}
.png){kind=icon}
Return
Integral Conservation Physics-Informed Neural Networks with different network architectures for patient-specific aortic flow simulations
.png){kind=icon}
PRE
AI
Y
L
Y
J
W
W
魏
DOI：10.1016/j.ijheatfluidflow.2025.110011.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• ICPINNs framework is extended from steady-state to transient aortic flow problems. • Mesh-free ICPINNs require small training data and adapt easily to diverse aortic geometries. • Flexible integration of velocity measurements data improves modeling of complex aortas. • ICPINNs with FCNN achieves optimal efficiency, while DGM excels in modeling pathological cases.
Keywords:
ICPINNs
transient aortic flow
mesh-free
velocity measurements
deep learning
Journal
I
IF:
5.1
Papers:
3.3K
Citations:
5.7K
Organization
Cited Papers