Title
Investigation of machining behaviour of flax reinforced epoxy composites using the ANN approach
Authors
MANIKANDAPRABU NALLASIVAM, SHETTAHALLI MANTAIAH VINU KUMAR, CHANDRASEKARAN SASIKUMAR and RISHI JAYAPRAKASH

Received April 29, 2025
Published Volume 60 Issue 3-4 March-April
Keywords flax-epoxy composites, milling, ANN, surface roughness, cutting force, FESEM

Abstract
In this study, flax fiber reinforced epoxy (FFRE) composites were fabricated using the hand layup method. The effects of spindle speed (900, 1800, 2700 rpm), feed rate (70, 90, 110 mm/min), and end mill cutters (6, 8, 10 mm) on milling behavior were analyzed. Milling tests were conducted on a vertical CNC machine for a 2 mm constant depth of cut. Experimental details followed Taguchi’s L27 orthogonal array, where cutting force and surface roughness (Ra) were evaluated as output responses. The investigation revealed that cutting force increased with the increase in the feed rate, but decreased as spindle speed was increased. Better surface quality of the milled surface in terms lower cutting force and surface roughness value was achieved at the optimal input conditions. Artificial neural network (ANN) models with different architectures were implemented to predict the cutting force and surface roughness. The analysis showed that predicted values were in close agreement with the experimental results and exhibited a maximum error deviation of ±5%, particularly when 3-5-4-1, and 3-5-4-2 ANN models (Purelin-Purelin-Purelin Transfer function) were employed for single and dual output respectively. The accuracy of the aforesaid models was measured in terms of highest R2 value and lowest mean absolute percentage error (MAPE). Field emission scanning electron microscopy (FESEM) images of the machined surface exposed matrix damage, cavity formation, fiber pull-out, and micro-tear.