Triboperformance Analysis of Coatings of LD Slag Premixed with TiO2 Using Experimental Design and ANN

This article reports on the analysis of triboperformance in regard to the erosion wear of a new class of coatings by an integrated implementation of Taguchi's experimental design and artificial neural networks (ANNs). Plasma-sprayed coatings of LD slag premixed with TiO₂ in different weight proportions are deposited on metal substrates at various input power levels of the plasma torch. Solid particle erosion trials, as per ASTM G 76 test standards, are conducted on the coating samples following a well-planned experimental schedule based on Taguchi's design of experiments. An air jet–type erosion test rig capable of creating reproducible erosive wear situations is used. Significant process parameters predominantly influencing the rate of erosion are identified. The study reveals that the impact velocity is the most significant among various factors influencing the wear rate of these coatings. A prediction model based on an ANN is proposed to predict the erosion performance of these coatings 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. This work shows that an ANN model helps to save time and resources that are required for a large number of experimental trials and successfully predicts the erosion wear rate of the coatings both within and beyond the experimental domain.