Microwave Assisted Pyrolysis of Biomass and Waste Plastics: Experiments and Modeling Using Machine Learning

Abstract

Thermochemical processes offer a promising avenue for valorizing resources from biomass and plastic waste by converting them into valuable products such as fuels, chemicals, and materials through high-temperature reactions. These methods mitigate environmental pollution by diverting waste from landfills and contribute to sustainable resource utilization and energy production. Pyrolysis is a highly efficient thermochemical technology that produces fuels and chemical intermediates. It can be carried out using conventional, solar, or microwave-controlled heating. Microwave-assisted pyrolysis offers several advantages over conventional pyrolysis methods. The distribution of temperature, rates of mass transfer, and heat transfer rates all depend on the specific operation mode and process parameters. Optimizing the pyrolysis process is essential for scaling up production. Utilizing computer-assisted modeling and simulation techniques is beneficial in developing effective configurations and experimental methods to improve efficiency. Through modeling, one can determine the optimal operating parameters and better understand the transportation mechanisms involved in pyrolysis. Machine learning (ML) is particularly advantageous when dealing with complex and nonlinear physical, chemical, and thermal processes. It also presents an opportunity to tackle data-driven challenges, extract information from large datasets, and unveil the underlying thermochemical conversion methods. ML models are constructed to accurately predict the yields of solid and liquid products obtained from the pyrolysis of biomass and plastic waste. A support vector regression model was developed to predict pyro-product yields from microwave-assisted co-pyrolysis of biomass and waste plastics. Hence, the present study aims to evaluate the microwave-assisted catalytic pyrolysis of torrefied biomass waste to produce biochar, biogas, and bio-oil. The next study investigates the microwave-assisted catalytic co-pyrolysis of torrefied sawdust (TSD) and polystyrene (PS) to obtain biochar, biogas, bio-oil, and value-added products. The design of experiments (DOE) was used to analyze the impact of torrefied sawdust and catalyst KOH loading on pyrolysis process conditions. The role of torrefaction in co-pyrolysis of (TSD: PS) was analyzed to understand the product yields, synergy, and energy consumption. The pyrolysis and co-pyrolysis product yields, average heating rate, microwave conversion efficiency, susceptor thermal efficiency, mass loss, conversion, and pyrolysis temperature will be analyzed using the ML technique. The predicted values will be compared with the experimental ones for the optimal parameters of all variables. The pyrolysis product yields were analyzed using SEM, BET, XRD, FTIR, ICP-OES, and Raman spectroscopy.