Analysis of effects of oil additive into friction coefficient variations on journal bearing using artificial neural network

Abstract

PurposeThe purpose of this paper is to investigate the effect of a lubricant with a polytetrafluoroethylene (PTFE)‐based additive on the friction behaviour in a steadily loaded journal bearing using an experimental and artificial neural network approach.Design/methodology/approachThe collected experimental data, such as pressure variations, are employed as training and testing data for artificial neural networks (ANNs). A feed forward back propagation algorithm is used to update the weight of the network during the training.FindingsAn artificial neural network predictor has superior performance for modelling journal bearing systems under different lubricant conditions.Research limitations/implicationsA feed forward back propagation algorithm is used as a training algorithm for the proposed neural networks. Various training algorithms can be used to train the proposed network. Various lubricants and concentration ratio of the different additives can be investigated.Practical implicationsThe simulation results suggest that the artificial neural predictor would be used as a predictor for possible experimental applications, especially different lubrication conditions on the modelling journal bearing system.Originality/valueThe paper discusses a new modelling scheme known as ANNs. A neural network predictor has been employed to analyze the effects of a lubricant with a PTFE‐based additive on the friction behaviour in a steadily loaded journal bearing under different operating conditions.