Understanding PET Hydrolysis via Reactive Molecular Dynamics Simulation and Experimental Investigation

Abstract

Polyethylene terephthalate (PET), a widely used polymer in packaging applications, has posed significant environmental challenges due to its resistance to environmental degradation. Chemical recycling via hydrolysis offers a circular solution by breaking PET down into its monomers, terephthalic acid and ethylene glycol, which can then be repolymerized into new PET. Despite its promise, the detailed pathways of PET hydrolysis─particularly the interplay between hydrolysis and thermal degradation─remain a topic of scientific debate. We combine reactive molecular dynamics (MD) simulations with experimental studies to elucidate key reaction pathways, intermediate species, and the temperature-dependent evolution of degradation products. Molecular dynamics simulations offer detailed insights into molecular motions and interactions that are often elusive in experimental setups, thus enhancing our understanding of the complex dynamics at play during PET decomposition. By systematically examining bond dissociation, intermediate species, and product formation at various temperatures, this study elucidates how hydrolysis and thermal degradation pathways evolve and interact. Furthermore, a severity index approach is employed to directly compare TPA yields from simulations with corresponding experimental data.

1

Illustration of the procedure to build the simulated PET-water system: (a) Building a long PET chain (i.e., 100 monomers as shown) with water molecules, and the molecule is placed in a large periodic domain. (b) The system was first compressed by a simulation under the NPT ensemble (300 K and 1 atm). (c) Simulation under the NVT ensemble at the targeted temperature.

2

Arrhenius plot for MD-simulated PET neutral hydrolysis (kinetic constants k represent the PET conversion) and the extrapolated results from MD simulation (i.e., black dashed line) and experimental data.

3

(a) Carbon number of the average longest PET chain during hydrolysis at various temperatures from simulation (data points plotted every 25 ps for clarity) with power-law fit. (b) Temporal variation of the yield of undissolved solids with power-law fit (inclusive of unconverted PET and oligomers). Data in Figure b is adopted from Pereira et al. (Royal Society of Chemistry (CC BY-NC 3.0)).

4

Time evolution of water-derived ionic and radical species during PET hydrolysis in MD simulations at 1800 K: (a) water molecules, (b) Populations of key radical species (H^•, H₃O^•, HO^•, and H₂O–H₃O^•) and (c) ions (H⁺, OH^–, and H₃O⁺) over the course of the reaction.

5

Time evolution of molecular species during PET hydrolysis observed in MD simulations at 1800 K. (a) Distribution of chain lengths over time, indicating progressive chain scission. Formation of carbon-chain fragments of (b) C6–C10 and (c) C1–C5. Formation of (d) various aromatic compounds, including terephthalic acid (TPA), (e) degradation products such as glyoxal and ethylene glycol (EG), and (f) various light gas compounds.

6

Time evolution of molecular species during PET hydrolysis observed in MD simulations at 1800 K: (a) benzoic acid and (b) BHET (bis­(2-hydroxyethyl) terephthalate). The blue line represents the average observed number of five independent runs with the error bar in gray.

7

Schematic diagram of key reactions observed from atomistic MD simulations. Radical species and related reactions are marked red, and the ending nodes are marked green. (–ph– represents a phenyl moiety). The network is a unified map derived by pooling elementary events that appeared in any of the four isothermal ensembles (1400 K, 1600 K, 1800 K, 2000 K).

8

Comparison between MD simulation at 1400 and 1600 K, and experimental data points to (a) TPA yield and (b) PET yield from PET neutral hydrolysis in relation to severity index (SI).