An efficient data-driven approach for modeling and optimization of reactivity-controlled compression ignition engine fueled with polyoxymethylene dimethyl ethers and hydrogen

This paper presents an efficient data-driven approach for optimizing the utilization of PODE_n and hydrogen in reactivity-controlled compression ignition (RCCI) engines. A novel high dimensional model representation (HDMR) technique is adopted to construct a highly accurate surrogate model for the RCCI engine based on the dataset generated by a detailed CFD model that has been calibrated against experimental data. The HDMR model is then coupled with Non-dominated Sorting Genetic Algorithm III (NSGA III), a multi-objective genetic algorithm, to search for the optimal operating conditions where the RCCI engine fueled by PODE_n and H₂ achieves the highest combustion performance. Results suggest that the constructed HDMR model is highly accurate, being able to predict the engine performance within milliseconds. The coupled HDMR-NSGA III approach successfully identifies the optimal engine operating condition, which significantly improves the combustion performance and reduces pollutant emissions compared with the base condition.