This article describes a concept for the lifetime prediction of fluids used in hydraulic networks that has emerged from sub-project A3 concerned with "ageing behaviour of ecologically compatible precursor materials" within collaborative research centre (SFB) 442 at the RWTH Aachen University, Germany. This concept is focused around a neural network that implicitly contains the ageing properties of the fluid. The complex of loads imposed on the fluid by the hydraulic circuit is processed in such a way that it can be used as the input for the neural network when described by appropriate characteristic values.

Keywords:oil ageing, lifetime prediction, environmentally compatible fluids, neural networks