基于响应面法的 PEMFC 引射器多参数耦合优化^*

In order to address the inefficiency and high time cost of using only Computational Fluid Dynam⁃ ics（CFD）for optimizing hydrogen ejectors in proton exchange membrane fuel cell （PEMFC）engine systems，this study employs response surface methodology （RSM）combined with a genetic algorithm （GA）to optimize ejector structural parameters and operating pressure. This paper constructs a response surface model using the throat diame⁃ ter，secondary flow pressure，and outlet pressure as optimization parameters，with the hydrogen recirculation ratio as the response indicator. The analysis of variance shows that the model has significance and good fitting accuracy， and on this basis，it is found that it has excellent adaptability through genetic algorithm optimization. The main con⁃ clusions are as follows：（1）The RSM reveals the influence of pressure and throat diameter on the ejection perfor⁃ mance. Increasing the secondary flow inlet pressure and outlet pressure can increase the hydrogen recirculation ra⁃ tio，while the throat diameter and ejection performance show a nonlinear relationship of“M”.（2）Sensitivity analy⁃ sis shows that the secondary inlet pressure is the dominant factor affecting the performance of the ejector，with a sen⁃ sitivity of 80.57%. （3）The GA-optimized ejector achieves a 19.42% improvement in hydrogen recirculation ratio from its baseline of 1.77，validating the effectiveness of the coupled algorithm. This conclusion shows the influence of ejector pressure and throat diameter on the hydrogen return ratio in PEMFC engine system，as well as the working mechanism of secondary flow inlet pressure as the dominant factor，which provides an important theoretical basis and practical guidance for optimizing the structure and working parameters of the propeller and improving its fluid regulation performance and hydrogen utilization rate in PEMFC engine system.