Prediction on tribological behaviour of composite PEEK-CF30 using artificial neural networks

In the present article artificial neural networks (ANN) were used to study the effects of pv factor and contact temperature on the dry sliding tribological behaviour of 30 wt.% carbon-fibre-reinforced polyetheretherketone composite (PEEK-CF30). An experimental plan was performed on a pin-on-disc machine for obtained experimental results. By the use of back propagation (BP) network, the non-linear relationship models of friction coefficient and weight loss of PEEK-CF30 versus pv factor and contact temperature were built. The test results show that the well-trained BP neural network models can precisely predict friction coefficient and wear weight loss according to pv factor and contact temperature. The obtained results show that friction coefficient was mainly influenced by the pv factor (mechanical factor), and the weight loss was mainly influenced by the contact temperature (thermal factor). (c) 2007 Elsevier B.V. All rights reserved.