Solid oxide fuel cells (SOFCs) are an efficient, reliable and clean source of energy. Predictive modeling and analysis of their performance is becoming increasingly important, especially with the growing emphasis on sustainable development’s requirements. However, mathematical modeling is difficult due to the complexity of its internal structure. In this study, the system’s electricity generating performance and operational characteristics were analyzed using recent on-site monitoring data first. Then, based on Pearson’s correlation coefficient, some of the variables were selected to build two prediction models: an artificial neural network (ANN) model and a multiple linear regression (MLR) model. The models were evaluated on the basis of the normalized mean square error (NRMSE), which was 1.89% for the MLR model and 0.66% for the ANN model, with no overall bias. They were also compared with other existing models, and it was found that the two models used in this study have the advantage of high accuracy and low difficulty. Therefore, the models developed in this study can more accurately and effectively assess the SOFC system’s state and can better support work to improve the thermoelectric performance of SOFC systems.

The prediction of stack output power in solid oxide fuel cell (SOFC) systems is a key technology that urgently needs improvement, which will promote SOFC systems towards high-power multi-stack applications. The accuracy of power prediction directly determines the control effect and working condition recognition accuracy of the SOFC system controller. In order to achieve this goal, a genetic algorithm back propagation (GA-BP) neural network is constructed to predict output power in the SOFC system. By testing 40 sets of sample data collected from the experimental platform, it is found that the GA-BP method overcomes the limitation of the traditional back propagation (BP) method—falling into local optima. Further analysis shows that the average relative error of GA-BP has decreased to 1%. The reduction of the relative error improves the accuracy of the prediction results and the average prediction accuracy. Compared with the long short-term memory (LSTM) and BP algorithm, the GA-BP prediction model significantly reduces the relative error of power output prediction, which provides a solid foundation for multi-stack SOFC systems.