Nano-PCM Intelligence Classification Dataset for Energy Storage and Heat Transfer Analysis using Deep Neural Networks

Big data images for free convection flow and heat transfer of nano-encapsulated phase change (NePCM) suspensions.
The dataset contains 3290 images of temperature fields for natural convection of nano-encapsulated phase change material suspensions in an enclosure. The provides codes try to classify the model parameters using the available images of temperature field. The codes have been provided in Phyton and Matlab languages.

A sample of the dataset has one normalized temperature image between 0 and 1 as input and four output parameters consisting of Fi, TTF, Ra, and Ste. It has 3290 samples of data. This dataset is derived from the following dataset and article:
Edalatifar, Mohammad; Ghalambaz, Mohammad; Tavakoli, Mohammad Bagher; Setoudeh, Farbod (2023), “Deep Learning Approach to Natural Convection Heat Transfer in a Cavity: A Simulation Dataset for Nano-Encapsulated Phase Change Material Suspensions”, Mendeley Data, V1, doi: 10.17632/j5f6r56jnb.1

M. Edalatifar, M. B. Tavakoli and F. Setoudeh, "A Deep Learning Approach to Predict the Flow Field and Thermal ‎Patterns of Nonencapsulated Phase Change Materials ‎Suspensions in an Enclosure‎", Journal of Applied and Computational Mechanics 2022, Vol. 8, Issue 4, Pages 1270-1278, DOI: 10.22055/jacm.2021.37805.3092.
https://jacm.scu.ac.ir/article_16903.html

The related paper of this dataset has been published as:
Mohammad Ghalambaz, Mohammad Edalatifar, Sara Moradi Maryamnegari, and Mikhail Sheremet, An intelligence parameter classification approach for energy storage and natural convection and heat transfer of nano-encapsulated phase change material: Deep neural networks, Neural Computing and Applications, https://doi.org/10.1007/s00521-023-08708-5