TY - CHAP
T1 - Heat Transfer Modelling with Physics-Informed Neural Network (PINN)
AU - Dhamirah Mohamad, Najwa Zawani
AU - Yousif, Akram
AU - Shaari, Nasiha Athira Binti
AU - Mustafa, Hasreq Iskandar
AU - Abdul Karim, Samsul Ariffin
AU - Shafie, Afza
AU - Izzatullah, Muhammad
N1 - KAUST Repository Item: Exported on 2022-11-03
PY - 2022/10/13
Y1 - 2022/10/13
N2 - The numerical simulations of partial differential equations aid us in studying the nanofluid flow in the porous media, the analysis of the dispersion of pollutants, and many other physical phenomena. However, to simulate such phenomena requires tremendous computational power, and it increases with the number of parameters. In this chapter, we will explore the application of the Physics-Informed Neural Network (PINN) in solving heat equation with distinct types of materials. To leverage the GPU performance and cloud computing, we perform the simulations on the Google Cloud Platform.
AB - The numerical simulations of partial differential equations aid us in studying the nanofluid flow in the porous media, the analysis of the dispersion of pollutants, and many other physical phenomena. However, to simulate such phenomena requires tremendous computational power, and it increases with the number of parameters. In this chapter, we will explore the application of the Physics-Informed Neural Network (PINN) in solving heat equation with distinct types of materials. To leverage the GPU performance and cloud computing, we perform the simulations on the Google Cloud Platform.
UR - http://hdl.handle.net/10754/685381
UR - https://link.springer.com/10.1007/978-3-031-04028-3_3
UR - http://www.scopus.com/inward/record.url?scp=85140231783&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-04028-3_3
DO - 10.1007/978-3-031-04028-3_3
M3 - Chapter
SN - 9783031040276
SP - 25
EP - 35
BT - Studies in Systems, Decision and Control
PB - Springer International Publishing
ER -