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.

In order to enhance the heat transfer efficiency of direct contact heat exchangers, numerical simulation methods have been employed to investigate three different thicknesses of SV hybrid elements. An experimental platform for direct contact heat transfer was established, utilizing THERMINOL62 synthetic heat transfer oil and R141b refrigerant as the working fluids. The maximum relative error between the experimental heat transfer results and numerical simulation results was within 3%, indicating the accuracy of the numerical simulation in reflecting the direct contact heat transfer process. The results showed that the heat transfer effectiveness of the heat exchanger with a thickness of 3 mm (a heat exchanger equipped with SV hybrid elements with a thickness value of 3 mm) was superior, manifested by a higher outlet temperature of the gaseous working fluid. Compared to heat exchangers with thicknesses of 2 mm and 4 mm, the separation intensity decreased to 0.03, representing reductions of 62.5% and 25% respectively. Turbulence intensity values were relatively high, with some exceeding 10%, reaching a peak of 19.57%. Compared to heat exchangers with thicknesses of 2 mm and 4 mm, the volumetric heat transfer coefficients increased by 8.9% and 3.7% respectively. The maximum pressure drop of heat exchangers with a thickness of 3 mm and 4 mm increased by 2.91% and 3.0% compared to those with a thickness of 2 mm. This work shows that appropriately increasing the thickness of SV hybrid elements (3 mm) can afford better heat transfer efficiency without causing excessive pressure drop.