Grease in the normal operation of the rotate vector (RV) reducer has a role that cannot be ignored, for the variable working conditions of the RV reducer, the performance of the lubricant changes directly affect its reliable operation. Therefore, the study of the rheological properties of the grease has become the focus of the study of RV reducer performance. Here, SK‐1A grease is taken as the research object, and its rheological characteristics under wide temperature range working conditions (−20–40°C) are investigated through rheological experiments to analyze the potential influence of the performance of RV reducer. However, the ordinary way of research is too complicated to better research the rheological properties of grease for a variety of working conditions. The Elman neural network (ENN) model was used to predict the rheological properties, and the results were compared with those of back propagation (BP) and radial basis function (RBF) neural networks. The results demonstrate that the ENN model demonstrates high prediction accuracy for grease rheological property prediction by comparing three types of predictions. This method can provide a theoretical reference for the accurate prediction of the rheological properties of lubricating grease affected by complex multifactors.