Modelling of tribological behaviours of composite PEEK-CF30 using BP neural networks

作者：Liujie X; Cardoso R; Davim J P^*

来源：Materials Science (Poland), 2008, 26(3): 495-504.

• BP neural network
• friction and wear
• advanced composite (PEEK-CF30)

A high performance of advanced composite PEEK-CF30 enables it to be utilized in many of the most critical areas in general industry such as automotive, electronics, medical and aerospace. In the present paper, a back propagation (BP) neural network was used to study the effects of the pv factor and sliding distance on the friction and wear behaviour of 30 wt.% carbon fibre reinforced poly( ether)-ether-ketone advanced composite (PEEK-CF30) at the contact temperature of 120 C. An experimental plan was performed on a pin-on-disc machine for obtained experimental results under unlubricated conditions. By the use of BP neural network, nonlinear relationship models of the friction coefficient (mu) and weight loss (W) of PEEK-CF30 vs. the pv factor and sliding distance (S) were built based on the experimental data. The test results show that the well-trained BP neural network models can precisely predict the friction coefficient and wear weight loss according to the pv factor and sliding distance. A new method of predicting wear behaviours of composite PEEK-CF30 has been provided by the authors.

• 出版日期2008
• 单位河南大学