Enhancing biofuel production with Co-pyrolysis of distiller's grains and waste polypropylene: synergistic effects and activation energy optimization with hybrid FLO-ENN approach

Abstract

Biofuel production from renewable feedstocks is gaining significant attention due to the growing demand for sustainable energy solutions. This study proposes enhancing biofuel production through the co-pyrolysis of distiller's grains (DG) and waste polypropylene plastic (PP) using a hybrid FLO-ENN approach. The proposed approach is the joint execution of both the Frilled lizard Optimization (FLO) and Epistemic Neural Network (ENN). The main goal of this research is to improve the quality of biofuel production. The FLO algorithm is used to optimize the operational parameters to enhance the co-pyrolysis of DG and waste PP, while the ENN is employed to predict the quality of the biofuel. The proposed method is simulated using MATLAB to evaluate its performances and is compared with existing methods. The FLO-ENN approach achieves lower error as well as higher efficiency compared to existing techniques such as Particle Swarm Optimization (PSO), Progressive Depth Swarm-Evolution (PDSE) and Artificial Neural Network-Genetic Algorithm (ANN-GA). Also, the co-pyrolisis of DG and PP yields low activation energy of 44.82 kJ mol-1. This improvement demonstrates that the proposed framework has significant potential to optimize the pyrolysis of polymeric wastes and biomass feedstocks more effectively, providing more accurate results than previous optimization techniques.