Design of an artificial neural network predictor for analysis of a hydrodynamic thrust bearing system

Abstract

PurposeSeeks to present a theoretical analysis on the general behaviour of a thrust bearing.Design/methodology/approachThe model programme using a method adaptation of finite differences was developed to solve the Reynolds equation for lubrication. The model in the theoretical analysis uses a single one‐dimensional grid. The altering of total lubrication load obtained as a result of under‐cutting in the thrust bearing has been determined together with the parameters such as oil film thickness and pressure. Parameters such as the pressure and thickness of the oil film were determined. The hydrodynamic behaviour of thrust bearing was analysed by considering different dimensionless system pressure, speed and geometry of the bearing. The effect of the elastic load due to elastic deflection is taken into account as the load‐bearing characteristics are included. Also, a proposed neural network predictor is utilised to analyse the general behaviour of thrust bearing.FindingsThe results of the proposed neural network predictor give superior performance for analysing of the behaviour of a thrust bearing undergoing in elastic deformation.Originality/valueThis continuation of theoretical and practical study evaluation should be of benefit to thrust bearing designers and researchers, who hopefully will make significant progress as a result.