Skip to content
Licensed Unlicensed Requires Authentication Published by De Gruyter Oldenbourg 2018

6. Analysis and optimization of hole quality parameters in cenosphere-multiwall carbon nanotube hybrid composites drilling using artificial neural network and gravitational search technique

V. N. Gaitonde, Shashikant, Anand Lakkundi, S. R. Karnik, A. S. Deshpande and J. Paulo Davim


Analysis and optimization of hole quality parameters in drilling of cenosphere- multiwall carbon nanotubes (MWCNTs) - epoxy composite materials have been presented in this chapter. The hybrid composite material is being prepared with 40% by weight of cenosphere with varying 0.2%, 0.3% and 0.4% of MWCNT as a filler and epoxy as matrix. The full factorial design (FFD) was planned to reduce the drilling experiments. The influence of four factors: explicit cutting speed, feed, % weight of MWCNT and drill diameter of hole quality parameters such as circularity error, drilled hole surface roughness and delamination factor have been studied. The artificial neural network (ANN)-based modeling analysis indicates that an addition of MWCNT reinforced with cenosphere-epoxy resin decreases the circularity error and surface roughness, whereas delamination is found to be minimal for 0.2% of MWCNT reinforcement drilling. To reduce the circularity error, 0.3% MWCNT reinforcement is desirable for drill diameters in the range 8-16 mm. For a particular drill size and MWCNT combination, the concurrent increase in cutting speed with feed has visible consequence for reducing the surface roughness. With 0.4% MWCNT reinforcement drilling, more delamination is observed for all the specified speed-feed combinations. ANN models were later used for gravitational search (GS) technique to decide the best combinations of cutting conditions for a particular drill diameter and % MWCNT for minimal circularity error, surface roughness and delamination factor.

© 2018 Walter de Gruyter GmbH, Berlin/Munich/Boston