At present, the pivotal challenges hindering the commercialization of the Solid Oxide Fuel Cell (SOFC) lie in system design and matching, thermal management safety, and performance optimization. To address these issues, a SOFC system-level model for the optimal control is proposed, integrating a two-stage preheater design, the electrochemical reaction mechanisms, and the influence of thermoelectric coupling effects on electrode temperature distributions. Furthermore, a comprehensive multi-criteria sensitivity analysis is conducted, incorporating thermodynamic, economic, and environmental indicators. The research demonstrates that there exist distinct mechanisms underlying the impact of varying trends in fuel utilization ratio and excess air ratio on the performance indicators of the SOFC system. Then, a detailed sensitivity analysis is undertaken, exploring the response trends of performance indicators under varying parameters. To validate the dynamic behavior of the objective functions, an intelligent learning approach based on the Artificial Neural Network is proposed. Additionally, a Multi-Objective Grey Wolf Optimization process is introduced, aimed at enhancing the comprehensive performance of the SOFC system. The results of this study demonstrate that the proposed multi-objective optimization strategy achieves a reduction of 12.12% in maximum temperature gradient, 28.00% in Levelized Cost of Energy, and 4.76% in Mass Specific Emission at the optimal operating point. This underscores the effectiveness of the approach in balancing and optimizing the trade-offs between thermal stability, economic feasibility, and environmental impact of the SOFC system.
