ON THE MODELING OF FRICTIONAL PHENOMENA USING NEURAL NETWORKS

In this work, an effort is made to model the friction coefficient of sliding surfaces under a variety of temperature, stress and sliding velocity conditions using an artificial neural network (ANN) methodology. First, friction coefficient measurements were obtained for unlubricated similar metal couples of the most commonly used titanium alloy Ti6A14V, for interface temperatures of 20 degrees C up to 900 degrees C, normal stress conditions up to 30 MPa and rubbing velocity between the specimens of 178 mm/s up to 700 mm/s. Next, these measured firiction coefficients along with the relevant measured conditions were used to train, in an efficient way, appropriate neural network architecture and further tests were also conducted in order to validate the artificial neural network performance.