This paper presents an investigation into the classical problem using an experimental apparatus and applying an artificial neural network (NN) optimisation approach for determining the pressure distribution in a journal bearing at elasto-hydrodynamic state of lubrication. The experimental system is employed at different working speeds with different surface roughness of shafts for getting pressure distribution. A NN is employed to predict the real data of the system as an optimisation technique. The NN is a radial basis function back propagation network. The NN has a superior performance to follow the desired results of the system and is employed to analyse such systems parameters in practical applications.