Thermal Analysis And Prediction Of Temperature Rise In Oil-air Lubricated Angular Contact Ball Bearings

Angular contact ball bearings are widely used in supporting parts of many high-speed rotating systems due to high stiffness,small starting friction and good reliability.Nevertheless,as bearing rotating speed increases,the temperature rise caused by frictional loss has still been the dominant limiting factor for improving the performance and service life of many highspeed ball bearing applications.Moreover,with the advantages of high cooling,high lubricating efficiency,precise oil quantity control,and environmental benefits,the oil-air lubrication has been successfully used in high-speed angular contact ball bearings.Therefore,it has important research significance and practical value to study the thermal characteristics of angular contact ball bearings and the dynamic prediction of angular contact ball bearings.Based on the CFD method,the fluid area model of 7006 C angular contact ball bearing is established,and the transient thermal analysis of the fluid field of bearing chamber is realized.The relation between speed and temperature rise of bearing is obtained.And by comparing the simulation data and experimental data of the bearing chamber's temperature,the validity of the simulation is proved.The results show that the simulation values are in good agreement with the experimental values,and it is found that the temperature field in the bearing chamber is unevenly distributed.In the bearing chamber,the temperature rises closer to the oil-air pipe inlet is lower,the temperature rises far from the oil-air pipe inlet is higher.Based on artificial neural network and genetic algorithm,a new prediction methodology for bearings temperature rise is proposed which capitalizes on the notion that the temperature rise of oil-air lubricated angular contact ball bearing is generally nonlinear and coupling.The influence factors of temperature rise in high-speed angular contact ball bearings are analyzed through grey relational analysis,and the key influence factors are determined.Combined with genetic algorithm,the artificial neural network model based on these key influence factors is built up;two groups of experimental data were chosen to input the ANN model for training and predicting.Results show that,compared with the ANN model,the ANN-GA model has shorter training time,higher accuracy and better stability;the output of ANN-GA model shows a good agreement with the experimental data,above 90% of bearing temperature rise under varying conditions can be predicted.It provides a reference method for the dynamic prediction of the angular contact ball bearing temperature rise.