Abstract:
In modern days, material engineers are constantly striving to develop new composite materials due to its lightweight, high specific strength and high specific modulus are being considered as some remarkable properties that can be facilitated with their applications in various automobile and engineering sectors. Alkaline treated banana fiber is gaining popularity due to its comparison to conventional glass fiber. In this study machinability of alkaline treated banana fiber, reinforced polymer has been compared with traditional glass fiber. Among various machining environments, which have been evolved to cut fiber-reinforced polymer, compressed air cooling environment has been found very effective in machining FRPs when surface roughness and cutting force are taken into consideration.
In this research work, turning operation of alkaline treated banana fiber reinforced epoxy was performed under both dry and compressed air cooling condition. Experimental Investigation was carried upon to compare the performances of two machining environments. Cutting speed, feed rate and depth of cut have been considered as input cutting parameters whereas resultant outputs are surface roughness and cutting force. A predictive model of surface roughness was developed using artificial neural network (ANN) which has been validated against the experimentally found results.Furthermore, Response Surface Methodology (RSM) was used to develop a quadratic equation to compare it with the experimental value. Using desirability function analysis, optimum cutting condition has been found while machining BFRP composite under compressed air cooling condition, the optimum cutting parameters which yielded the desired output responses (surface roughness and cutting force) ; Ra =2.511 µm, Pz = 15.457 N are follows: 0.403 mm of t, 55 m/min of Vc and 0.116 mm/rev. For ANN developed model, regression value is found to be 0.99518 for banana fiber reinforced epoxy composite under compressed air cooling condition which is very close to 1, thus justifying the efficacy of the developed model.
