Neural network analysis of leakage oil quantity in the design of partially hydrostatic slipper bearings

This paper presents an investigation for analyzing the efficiency of axial piston pumps in a variety conditions using a proposed neural network. Since slippers affect the performance of the system considerably, the effects of surface roughness on lubrication have been studied in slippers with varying hydrostatic bearing areas and surface roughness. The neural network structure is very suitable for this kind of system. The network is capable of predicting the leakage oil quantity of the experimental system. The network has parallel structure and fast learning capacity. It is also easy to see from the experimental results that the leakage oil quantity was caused by surface roughness, orifice diameter and the size of hydrostatic bearing area, loading pressure and the number of rotations. It can be outlined from the results for both approaches, neural network could be modeled slipper bearing systems in real time applications.