Erosion Studies of Short Glass Fiber-reinforced Thermoplastic Composites and Prediction of Erosion Rate Using ANNs

Abstract

Erosion behavior of polyetherketone (PEK) reinforced by short glass fibers with varying fiber content (0—30 wt%) has been studied. Steady-state erosion rates have been evaluated at different impact angles (15°—90°) and impact velocities (25—66 m/s) using silica sand particles as an erodent. PEK and its composites exhibited maximum erosion rate at 30° impact angle indicating ductile erosion behavior. The erosion rates of PEK composites increased with increase in amount of glass fiber. Also, artificial neural networks technique has been used to predict the erosion rate based on the experimentally measured database of PEK composites. The effect of various learning algorithms on the training performance of the neural networks was investigated. The results show that the predicted erosion rates agreed well when compared with the experimentally measured values. It shows that a well-trained neural network will help to analyze the dependency of erosive wear on material composition and testing conditions making use of relatively small experimental databases.