Analysis and prediction of surface roughness of plasma sprayed mild steel

Abstract

In many structural applications plasma spray technique has becomes a popular technique because its capability to produce required surface properties. This paper describes about industrial wastes or low grade ore (Flay-ash+ quartz+ illmenite) as the deposition material which is to be coated on Mild Steel substrates. In many cases it is found that surface roughness parameter become crucial for structural modification. To decrease the surface roughness by optimizing other necessary properties, one of the soft computing method i.e.Artificial Neural Network (ANN) technique used. This technique efficiently describe the approximation complexity of inter-relations in between different parameter of atmospheric plasma spray process and helps in saving time & resources for experimental trials for which it is advantageous than all conventional methods. The aim of this investigation is to find out an appropriate input vector set in ANN model. This methodology can provide clear understanding of various co-relationships across multiple scales of length and time which could be essential for improvement of product performance and process. ANN experimental results indicate that the projection network has good generalization capability to optimize the surface roughness. The aim of this article is to find specific parameter set for required surface roughness.