Prediction and Optimization of Biomass and Coal Co-Pyrolysis Based on NSGA-II Genetic Algorithm and Random Forest Model

With the growth of global energy demand and the pursuit of renewable energy, biomass and coal co-pyrolysis has attracted much attention as a potential energy conversion technology. In this paper, based on the NSGA - II genetic algorithm and random forest biomass with coal pyrolysis prediction optimization are studied. Firstly, we propose an optimization method for the co-pyrolysis mixing ratio based on the NSGA-II genetic algorithm. Then, we propose a Random Forest-based method for predicting the yield of co-pyrolysis products, and use the coefficient of determination, the average absolute error and the average deviation error as the model evaluation indexes. The experimental results show that the prediction model proposed in this paper has strong fitting effect, high prediction accuracy, and good robustness and practicability.