Application of artificial neural network for lubrication performance evaluation of rough elliptic bore journal bearing

Abstract In this study, rough elliptic bore journal bearing performance is predicted using an artificial neural network (ANN) technique. The effects of non-circularity and roughness are quantified to isotropic in macro micro scale, respectively. numerically estimated parameters like load, friction, flow-in at different eccentricities [0.3 (low), 0.5 (medium), 0.8 (high)], non-circularities [0.5 1.0 2.0 factors [0.1 0.2 0.3 0.4 (high)] used train build the ANN model. training continued until maximum mean square error achieved, best-fitting plot generated. With a confidence level 99.75% or R-value 0.99757, results found be satisfactory.