Temperature Rise Prediction of Oil-Air Lubricated Angular Contact Ball Bearings Using Artificial Neural Network

摘要

Background: Angular contact ball bearing is an important component of many high-speedrotating mechanical systems. Oil-air lubrication makes it possible for angular contact ball bearing tooperate at high speed. So the lubrication state of angular contact ball bearing directly affects the performanceof the mechanical systems. However, as bearing rotation speed increases, the temperature riseis still the dominant limiting factor for improving the performance and service life of angular contactball bearings. Therefore, it is very necessary to predict the temperature rise of angular contact ball bearingslubricated with oil-air.Objective: The purpose of this study is to provide an overview of temperature calculation of bearingfrom many studies and patents, and propose a new prediction method for temperature rise of angularcontact ball bearing.Methods: Based on the artificial neural network and genetic algorithm, a new prediction methodologyfor bearings temperature rise was proposed which capitalizes on the notion that the temperature rise ofoil-air lubricated angular contact ball bearing is generally coupling. The influence factors of temperaturerise in high-speed angular contact ball bearings were analyzed through grey relational analysis, andthe key influence factors are determined. Combined with Genetic Algorithm (GA), the Artificial NeuralNetwork (ANN) model based on these key influence factors was built up, two groups of experimentaldata were used to train and validate the ANN model.Results: Compared with the ANN model, the ANN-GA model has shorter training time, higher accuracyand better stability, the output of ANN-GA model shows a good agreement with the experimentaldata, above 92% of bearing temperature rise under varying conditions can be predicted using the ANNGAmodel.Conclusion: A new method was proposed to predict the temperature rise of oil-air lubricated angularcontact ball bearings based on the artificial neural network and genetic algorithm. The results show thatthe prediction model has good accuracy, stability and robustness.