In order to verify the feasibility of the random forest algorithm in predicting the tribological properties the modified water-lubricated bearing,the algorithm was written by Python,and the simulation modeling was established based on the known data.The accuracy of the algorithm was verified by the known data,and the average value of the receiver operating characteristic(ROC)curve is 0.85,which proved that the accuracy of the model was high.The prediction model was verified by experiments under different temperature and load conditions.The error between the experimental results and the prediction results is about 5%,indicating that the random forest model can be used to predict the tribological performance of modified water lubricated bearings.The results show that the temperature has a great influence on the average friction coefficient of the modified water lubricated bearing,while the load has a small influence on the average friction coefficient,but has a great influence on the running stability of the bearings.