TY - JOUR
T1 - Machine learning-aided modeling of the hydrogen storage in zeolite-based porous media
AU - Hai, Tao
AU - Alenizi, Farhan A.
AU - Mohammed, Adil Hussein
AU - Chauhan, Bhupendra Singh
AU - Al-Qargholi, Basim
AU - Metwally, Ahmed Sayed Mohammed
AU - Ullah, Mirzat
N1 - Publisher Copyright:
© 2023 Elsevier Ltd
PY - 2023/6
Y1 - 2023/6
N2 - Zeolites are among the most popular porous solids for hydrogen storage. Hydrogen attaches to the surface and microporous structure of zeolites. The literature mainly inspected the hydrogen adsorption capacity of zeolites (HACZ) experimentally and paid little attention to its modeling. Furthermore, there is no tool to compare/reveal the role of surface and pore characteristics of zeolites in hydrogen storage. This work applies several well-established artificial intelligence techniques to correlate the HACZ to surface and pore characteristics of zeolites, pressure, and temperature. The topology-tuned multi-layer perceptron neural network is the best model to simulate the hydrogen storage of fourteen systems (NH4Y, X, and ZSM-5). This model predicts the HACZ of a vast experimental databank with a regression coefficient of 0.99875 and an absolute average relative deviation of 6.43%. Results approve that the role of the BET surface area of zeolites on the HACZ is more vital than the pore volume.
AB - Zeolites are among the most popular porous solids for hydrogen storage. Hydrogen attaches to the surface and microporous structure of zeolites. The literature mainly inspected the hydrogen adsorption capacity of zeolites (HACZ) experimentally and paid little attention to its modeling. Furthermore, there is no tool to compare/reveal the role of surface and pore characteristics of zeolites in hydrogen storage. This work applies several well-established artificial intelligence techniques to correlate the HACZ to surface and pore characteristics of zeolites, pressure, and temperature. The topology-tuned multi-layer perceptron neural network is the best model to simulate the hydrogen storage of fourteen systems (NH4Y, X, and ZSM-5). This model predicts the HACZ of a vast experimental databank with a regression coefficient of 0.99875 and an absolute average relative deviation of 6.43%. Results approve that the role of the BET surface area of zeolites on the HACZ is more vital than the pore volume.
KW - Artificial intelligence techniques
KW - Artificial neural networks
KW - Hydrogen storage
KW - Surface and pore characteristics
KW - Zeolite
UR - http://www.scopus.com/inward/record.url?scp=85159763849&partnerID=8YFLogxK
U2 - 10.1016/j.icheatmasstransfer.2023.106848
DO - 10.1016/j.icheatmasstransfer.2023.106848
M3 - Article
AN - SCOPUS:85159763849
SN - 0735-1933
VL - 145
JO - International Communications in Heat and Mass Transfer
JF - International Communications in Heat and Mass Transfer
M1 - 106848
ER -
