Optimization of coffee shell carbonization parameters based on BP neural network-genetic algorithm

Biochar is a multifunctional material efficiently developed from biomass. It is combined with fertilizers to prepare biochar-based fertilizers，which has excellent slow-release performance and minimal soil burden. The carbonization temperature，carbonization time，and heating rate during biomass carbonization process affect the physical and chemical properties of biochar. The biochar under different carbonization temperatures，carbonization times and heating rates have a significant impact on the slow-release performance of biochar-based fertilizers. In this study，BP neural network coupled with genetic algorithm was used to predict and optimize key process parameters during the carbonization process of coffee shell biochar in order to improve the slow-release performance of biochar-based fertilizers. Results had shown that based on BP neural network-genetic algorithm，rapid prediction and optimization of the slow-release performance of coffee shell biochar-based fertilizer had been achieved through experiments. The optimal process parameters were：carbonization time of 2.8 h，carbonization temperature of 780.7 ℃，and the heating rate of 15.1 ℃/min. The seven-day cumulative nutrient release rate of the biochar-based fertilizer prepared under this process parameter was 45.9%，and the slow-release performance was improved. The study proposed a new method for optimizing the parameters of biochar carbonization process，which provided new ideas for the development of high-performance biochar preparation processes and had certain reference significance for improving the performance of biochar-based fertilizers.