Low-temperature pressure drop experiments take a long time, in this study, computational fluid dynamics (CFD) and a general regression neural network (GRNN) are used to predict the pressure drop in a wind power lubrication system to serve as an alternative to experiments. The simulation results show a clear increase in the yield stress as the temperature decreases, especially under -35℃. The factors that affect the pressure of lubricating grease transport are as follows in decreasing order of importance: temperature, high-pressure pipe diameter, and flow rate. The general regression neural network can be used to effectively predict the pressure of lubricating grease transport under different conditions with a mean relative error of 8.1%.