Analysis And Prediction Of Plasma Sprayed Alumina-Titania Coating Deposition Using Neural Computation

Abstract

Coating deposition by plasma spraying involves a number of process variables, which contribute in a large way to the quality of the coating. During spraying, various operating parameters are determined mostly based on past experience. It therefore does not provide the optimal set of parameters for a particular objective. In order to obtain the best result with regard to any specific coating quality characteristic, accurate identification of significant control parameters is essential. Deposition efficiency of any coating is a characteristic which not only rates the effectiveness of the spraying method but also is a measure of the coatability of the material under study. This work is devoted to analyze the experimentally obtained results on the deposition efficiency of alumina-titania coatings made at different operational conditions. For this purpose, a statistical technique called Taguchi experimental design methd is used. Factors are identified according to their influence on the coating deposition. The most significant parameter is found. A prediction model using artificial neural network (ANN) is presented considering the significant factors. Inspired by the biological nervous system, an artificial neural network (ANN) approach is a fascinating computational tool, which can be used to simulate a wide variety of complex engineering problems such as deposition of ceramic coatings on metal substrates by plasma spraying. Prediction of deposition rate helps in selecting the optimum combination of process parameters and hence is essential in a plasma spray coating activity. This research shows that the use of a neural network model to simulate experiments with parametric design strategy is quite effective for prediction of wear response of materials within and beyond the experimental domain.