A Study on Tribological Behavior of Linz-Donawitz Slag Filled Polypropylene Composites Using Experimental Design and Neural Networks

Short fiber-reinforced polymer composites are used in numerous tribological applications. In the present work, an attempt has been made to improve the wear resistance of short glass fiber (SGF) reinforced polypropylene composites by incorporation of micro-sized Linz-Donawitz slag (LDS) particles. Composites with different LDS content (0, 7.5, 15 and 22.5 wt%) in a polypropylene matrix base with 20 wt% SGF reinforcement are prepared by injection molding technique. Solid particle erosion trials, as per ASTM G76 test standards, are conducted on the composite samples following a well-planned experimental schedule based on Taguchi design-of-experiments. Significant process parameters predominantly influencing the rate of erosion are identified. The study reveals that the LDS content and impact velocity are the most significant among various factors influencing the wear rate of these composites. Further, a prediction model based on artificial neural network (ANN) is proposed to predict the erosion performance of the composites under a wide range of erosive wear conditions. This work shows that an ANN model is quite helpful in saving time and resources that are required for a large number of experimental trials and thus, successfully predicts the erosion rate of composites both within and beyond the experimental domain.