Over the last few years, the ability of a conventional bearing has gradually declined to survive in the era of modern advanced engines, as they are not able to cope-up with high speed requirements, high operating temperature range, etc. In some turbine engines, bearing temperatures are expected to exceed the capabilities of conventional liquid lubricant completely. This has lead to the development of new concepts in bearing technology, resulting in developmental efforts related to other bearings like Spiral Journal Bearings. This paper portrays the determination of amplitude, velocity and acceleration as the response parameters for vibration analysis of a rotating rotor-bearing assembly. The successive points in a long time history of the rotor-bearing motion during a transient vibration period have been identified. The calculation of the vibrations and the forces acting is not straightforward because these equations of motion of the system contain non-linear terms. Initially, the most influential parameters are identified. A supervised multilayer neural network model is then trained and tested with the input and output data using the back-propagation algorithm. The response characteristics are derived as the outputs of the Neural Network for different conditions of bearing parameters. The experimental and the simulated results are then compared.