Repercussion of Cenosphere Filler Size on Mechanical and Dry Sliding Wear Peculiarity of Glass Fiber-Reinforced Polyester Composites Using Taguchi Analysis and Neural Network

Abstract

Abstract Filler plays a significant role in determining the properties and behavior of particulate composites. In this experimental study, mechanical and tribological behaviors of sub-micron size cenospheres filled glass-polyester composites are investigated. Cenospheres and glass fiber-reinforced polyester composites are prepared by hand lay-up technique. Composites are fabricated by filling 10 wt.% and 20 wt.% of 800 nm and 200 nm size of cenosphere filler particulate respectively along with 40 wt.% of glass fiber. Glass polyester composite without filler is also prepared for proportional analysis. A series of dry sliding wear test are conducted on a pin-on-disc machine with three sliding velocities of 1.57, 2.62 and 3.66 m/s under three different normal loading of 20, 25 and 40 N for three sliding distances of 1000, 2500 and 4000 m respectively. A statistics-based design of experiments approach is used by using Taguchi's orthogonal arrays. Results reveal that mechanical properties and wear resistance of the composites increase with a decrease in the particle size. Artificial neural network (ANN) approach is also applied to the friction and wear data for subsequent validation. Finally, optimal factor settings are determined using genetic algorithm (GA).