Using evolutionary machine learning to characterize and optimize co-pyrolysis of biomass feedstocks and polymeric wastes

Co-pyrolysis of biomass feedstocks with polymeric wastes is a promising strategy for improving the quantity and quality parameters of the resulting liquid fuel. Numerous experimental measurements are typically conducted to find the optimal operating conditions. However, performing co-pyrolysis experiments is highly challenging due to the need for costly and lengthy procedures. Machine learning (ML) provides capabilities to cope with such issues by leveraging on existing data. This work aims to introduce an evolutionary ML approach to quantify the (by)products of the biomass-polymer co-pyrolysis process. Multi-objective optimization is done to maximize pyrolysis oil production and minimize char/syngas formation simultaneously. A comprehensive dataset covering various biomass-polymer mixtures under a broad range of process conditions is compiled from the qualified literature. The database was subjected to statistical analysis and mechanistic discussion. The input features are constructed using an innovative approach to reflect the physics of the process. The constructed features are subjected to principal component analysis to reduce their dimensionality. The obtained scores are introduced into six ML models. Gaussian process regression model tuned by particle swarm optimization algorithm presents better prediction performance (R2 > 0.9, MAE < 0.03, and RMSE < 0.06) than other developed models. The multi-objective particle swarm optimization algorithm successfully finds optimal independent parameters. Under optimal conditions, pyrolysis oil, char, and syngas yields are in the range of 70.9-75.3%, 7.23-21.5%, and 5.68-18.6%, respectively. The results demonstrate how ML can be employed to obviate the need for chemical-demanding, cost-intensive, and time-consuming co-pyrolysis experimental measurements.

Automated summary

Machine learning is utilized to predict the products of biomass-polymer co-pyrolysis by analyzing a comprehensive dataset. The model is constructed using an innovative approach and optimized to maximize pyrolysis oil production while minimizing char and syngas formation. The results showcase the potential of ML in replacing costly and time-consuming experimental measurements.