Nonlinear multivariable modeling of solid oxide fuel cells using core vector regression

► This paper presents new steady-state and dynamic models for solid oxide fuel cells using core vector regression (CVR). ► Two CVRs are trained for each operating mode of solid oxide fuel cell, considering important operating parameters. ► In comparison with existing black-box models, the proposed model has little training time and small amount of memory. ► The proposed model has less error and better correlation coefficient in comparison with existing black-box models. ► Because of less support vectors the proposed CVR-based model is faster than existing models for time-consuming studies.