Magnetorheological grease (MRG) is a new type of field-response intelligent material with controllable performance and excellent settlement stability, which is feasible to replace traditional materials. The heating phenomenon of magnetorheological (MR) devices is more common during operation, while the MRG as a medium has more significant thermal rheological characteristics in the heating process. In the process of MRG modeling, a model is established to study the effect of thermal-magnetic coupling on its performance and to save experimental time and reduce costs. Hence, an improved and reliable artificial neural network (ANN) prediction model is established to characterize and predict the relationship among temperature, aging time, magnetic field strength and thermal-rheological properties of MRG. The training data of neural network were obtained from the experiments under the condition of thermomagnetic coupling with rotational rheometer. After the neural network was trained and substituted into the test set data, the predicted results were compared with the experimental results, the correlation coefficient R reached and exceeded 0.95. The results show that the model has excellent prediction accuracy and can provide theoretical reference for the thermal aging behavior of MRG.