TY  - JOUR
A1  - Iannello, Stefano
A1  - Friso, Andrea
A1  - Galvanin, Federico
A1  - Materazzi, Massimiliano
JF  - Energy & Fuels
SN  - 0887-0624
UR  - https://doi.org/10.1021/acs.energyfuels.4c05870
N1  - This publication is licensed under

CC-BY 4.0 .
cc licence
by licence
Copyright © 2025 The Authors. Published by American Chemical Society
IS  - 9
VL  - 39
SP  - 4549
KW  - Science & Technology
KW  -  Technology
KW  -  Energy & Fuels
KW  -  Engineering
KW  -  Chemical
KW  -  Engineering
KW  -  FUEL-PARTICLES
KW  -  WOOD PARTICLES
KW  -  DEVOLATILIZATION
KW  -  SEGREGATION
KW  -  GASIFICATION
KW  -  CONVERSION
KW  -  VELOCITY
KW  -  SYSTEMS
KW  -  SOLIDS
KW  -  WASTE
PB  - AMER CHEMICAL SOC
ID  - discovery10205793
N2  - The axial mixing/segregation behavior of single plastic particles in a bubbling fluidized bed reactor has been investigated by noninvasive X-ray imaging techniques in the temperature range of 500-650 °C and under pyrolysis conditions. Experimental results showed that the extent of mixing between the plastic particle and the fluidized bed increases as both the temperature and fluidization velocity increase. Three modeling approaches were proposed to describe the axial mixing/segregation behavior of the plastic particle, i.e., a purely mechanistic model, a physics-informed neural network (PINN), and an augmented PINN (augPINN). The former model is based on the second law of motion. The second model is a standard PINN, built by simply embedding the second law of motion in the loss function. The third approach involves the introduction of a new interphase distribution parameter, P, into the model. This parameter represents the relative importance of the effects of the emulsion and bubble phases on the plastic particle. This parameter was obtained by training the neural network using the X-ray axial displacement data. The augPINN has been shown to outperform both the mechanistic and the standard PINN models in describing the axial mixing/segregation of polypropylene particles. Moreover, the obtained parameter P was found to be physically interpretable. The main novelty of this work is to show how different frameworks based on the concept of physics-informed machine learning can be successfully applied to complex and real-world hydrodynamic data sets.
EP  - 4564
AV  - public
Y1  - 2025/01/01/
TI  - A Hybrid Physics-Machine Learning Approach for Modeling Plastic-Bed Interactions during Fluidized Bed Pyrolysis
ER  -