Ship-Based Carbon Capture (SBCC) technology presents a promising approach to reduce greenhouse gas emissions in the marine transportation. Solvent-based carbon capture has emerged as a leading technology for SBCC, primarily due to its low retrofit costs and effectiveness in treating flue gas with low carbon content. However, challenges remain in optimizing system operation efficiency under the variable conditions of ship main engine loads and in understanding the mechanisms by which process parameters influence key evaluation factors. Consequently, this study established a pilot-scale experimental platform for solvent-based SBCC and developed a carbon capture model based on it. The influence of process parameters, such as main engine exhaust flow rate and liquid/gas ratio (L/G), on the evaluation factors was thoroughly explored. With the utilization of Shapley Additive Explanations (SHAP) analysis to quantify the influence of process parameters on the evaluation factors, a multi-objective optimization equation is proposed. The combination of machine learning and optimization algorithms offers an efficient approach for determining the optimal process of the SBCC system under different main engine loads. The research results show that the main engine exhaust flow rate is the most important process parameter affecting the carbon capture rate (CR), with an influence ratio as high as 64.33%. As the main engine exhaust flow rate increases, the maximum CR decreases from 97.84% to 61.13%. Although the extreme value of the regeneration energy consumption (REC) also decreases from 6.66 to 4.42 GJ/t CO2, the solvent flow rate's influence on REC is also significant, with influence ratios of 38.49% and 35.53%, respectively. A data-driven approach examined the optimal operating conditions at eight main engine loads, achieving a carbon capture rate prediction error of only 1.42% and a maximum REC error of only 0.55 GJ/t CO2. This study provides essential guidance for assessing the suitability of SBCC systems.
Read full abstract