This paper investigates the pressure variations on the steel shafts on the journal bearing system with low temperature and variable speed. This paper mainly consist of two parts, experimental and simulation. In the experimental work, journal bearing system is tested with different shafts speed and temperature conditions. The temperature of the system's working conditions was under minus. The collected experimental data such as pressure variations are employed as training and testing data for an artificial neural network. The neural network is a feed forward three layered network. Quick propagation algorithm is used to update the weight of the network during the training. Finally, neural network predictor has superior performance for modelling journal bearing systems with load disturbances.