.png){kind=icon}
.png){kind=icon}
Return
Kinetics and product evolution in polyethylene pyrolysis over γ-Al2O3: A synergistic approach integrating particle swarm optimization, machine learning, and TG-FTIR-GC/MS
.png){kind=icon}
PRE
AI
Y
Y
J
C
H
Z
Y
DOI：10.1016/j.joei.2026.102675.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Integrated PSO, machine learning, and TG-FTIR-GC/MS for PE/γ-Al2O3 pyrolysis. • Optimal γ-Al2O3:PE ratio of 1:1 minimized activation energy to 192.56 kJ/mol. • Reaction mechanism shifted from F3 (chemical) to D1 (diffusion) with catalyst. • LSTM outperformed BPNN in TG prediction (R2=0.9991, RMSE=0.38, MAE=0.21). • C8–C14 olefins reached 89.46% at 550 °C with γ-Al2O3:PE=1:1.
Journal
IF:
6.2
Papers:
2.9K
Citations:
8.1K
Organization
Cited Papers