Prediction of friction coefficient on workpiece/fixture contact surface using artificial neural networks

Abstract

The friction coefficient at the interface between a fixture tip and the workpiece plays an important role in work-holding applications. The present paper investigates the application of neural network schemes and architectures to predict the friction coefficient on the contact face between the workpiece and fixture tip taking into account factors such as surface roughness, applied normal load, workpiece material, and fixture element roughness. The model presented can be used to develop a virtual friction tester to overcome the difficulties associated with experimental determination of the friction coefficient and to facilitate testing of different fixturing scenarios in a virtual environment by providing a smart database for the friction coefficient values. The predicted results are compared with experiments and show reasonable agreement.