Application of Artificial Neural Network Modelling in Machining of Epoxy/TiC and Epoxy/MWCNTs Nanocomposites | ||||
| Engineering Research Journal (Shoubra) | ||||
| Volume 47, Issue 1, January 2021, Page 90-95 PDF (801.1 K) | ||||
| Document Type: Research articles | ||||
| DOI: 10.21608/erjsh.2021.405292 | ||||
 View on SCiNiTO | ||||
| Authors | ||||
| Aneesah A. Q. AlSubaiei; S. S. Mohammed | ||||
| Mechanical Engineering Department, Faculty of Engineering at Shoubra, Benha University, Cairo, Egypt | ||||
| Abstract | ||||
| In the present investigation, two different nanofillers were dispersed in epoxy matrix, namely, multi-wall carbon nanotubes (MWCNTs) and titanium carbide nanoparticles (TiC). Several epoxy/MWCNTs and epoxy/TiC nanocomposites containing different volume fractions of the nanofillers. The epoxy/MWCNTs and epoxy/TiC nanocomposites were machined using conventional center lathe using different cutting speeds, feed rates and depth-of-cuts to study the influence of these parameters on the surface roughness and roundness error. Based on the experimental data collected from the machining of the nanocomposites, artificial neural network (ANN) models were developed to predict the surface roughness and the roundness error as function of the volume fraction of the nanofiller, cutting speed, feed rate and depth-of-cut. The predicted results using ANN indicate good agreement between the experimental values and predicted values. For epoxy/MWCNTs nanocomposites, the developed ANN model for predicting the surface roughness and roundness error exhibited mean relative errors of 7.8% and 10.67%, respectively. While for epoxy/TiC nanocomposites, the developed ANN model exhibited mean relative errors of 6.86% and 8.39% for predicting the surface roughness and roundness error, respectively | ||||
| Keywords | ||||
| Machining; Turning; Epoxy; Artificial Neural Networks; Nanocomposites; Surface roughness; Roundness error | ||||
|
Statistics Article View: 64 PDF Download: 28 |
||||
