An effective battery thermal management (BTM) strategy is very important for electric vehicles (EVs). In this paper, a robust predictive BTM strategy based on thermoelectric cooler (TEC) is proposed to adjust the battery temperature within an appropriate range and reduce energy consumption. Firstly, a modeling method of TEC based on thermal resistance is presented, which considers the influence of heat sink and fan on modeling effect. Next, a distributed battery thermal model is developed by using the difference method, which takes the tab thermal model as the first kind of boundary condition of the cell core. Then, a thermal management model is developed by combining the TEC model and distributed battery thermal model, and a neural network (NN) observer is proposed to compensate the model uncertainty. Finally, a nonlinear model predictive control (NMPC) method is proposed to optimize the cooling process. Genetic algorithm (GA) optimization is used to solve the nonlinear programming problem in NMPC method. Additional stability analysis shows the convergence of the proposed observer. Experiments and verifications suggest that the proposed method can accurately control the battery working near the target temperatures under four different cycles, and the errors are less than 0.5 °C.