![Sample our Physical Sciences journals, sign in here to start your FREE access for 14 days]({"type":"image" , "src" : "/sda/110819/TOC-Subject-Sample-2021-Physical-Sciences.jpg"})
Abstract
The target of this experimental study is to investigate the solid particle erosion behavior of a new composite material formed by adding blast furnace slag (BFS) particles at different amounts of 0, 10, 20, 30 wt% to short glass fiber (SGF)-reinforced epoxy resin. The resulting hybrid composites are subjected to solid particle erosion using an air jet–type erosion test rig. Erosion tests are carried out by following a well-designed experimental schedule based on Taguchi's orthogonal array. BFS content, impact velocity, and impingement angle are identified as the significant factors affecting the erosion rate of the composites. A prediction model based on an artificial neural network (ANN) is proposed to predict the erosion performance of these composites under a wide range of erosive wear conditions. This model is based on the database obtained from the experiments and involves training, testing, and prediction protocols. The work shows that an ANN model helps in saving time and resources that are required for a large number of experimental trials and successfully predicts the erosion rate of composites both within and beyond the experimental domain.