Battery temperature is a primary factor affecting the battery performance. Suitable battery temperature control, in particular internal temperature control can not only guarantee the battery operation safety but also improve its efficiency. This is however challenging as existing controller designs for battery charging rarely have a mechanism to incorporate such information. This paper proposes a novel battery charging control strategy which applies the constrained generalized predictive control (GPC) to charge a LiFePO4 battery based on a newly developed coupled thermoelectric model. The control target primarily aims to maintain the battery internal temperature within a desirable range while delivering fast charging. To achieve this, the coupled thermoelectric model is firstly introduced to capture the battery behaviours in particular SOC and internal temperature which are not directly measurable. Then a controlled auto-regressive integrated moving average (CARIMA) model, whose structure is optimized by a fast recursive algorithm and the parameters are identified by the recursive least squares algorithm, is developed as an online self-tuning predictive model for a GPC controller. Then the constrained generalized predictive controller is developed to manipulate the charging current. Experiment results confirm the effectiveness of the proposed control strategy. Further, the best region of the heat dissipation rate and proper internal temperature set-points are investigated and analysed.