Surface Modification of AH36 Steel Using ENi-P-nano TiO₂ Composite Coatings Through ANN-Based Modelling and Prediction

Abstract

This study aims to analyse and forecast the significance of input process parameters to obtain a better ENi-P-TiO₂ coated surface using artificial neural networks (ANN). By varying the four process parameters with the Taguchi L9 design, forty-five numbers of AH36 steel specimens are coated with ENi-P-TiO₂ composites, and their microhardness values are determined. The ANN model was formulated using the input and output data obtained from the 45 specimens. The optimal design was developed based on mean squared error (MSE) and R ² values. The experimentally measured values were compared with their predicted values to determine the ANN model’s predictability. The efficiency of the ANN model is evaluated with an R ² value of 0.959 and an MSE value of 34.563 4. The authors have concluded that the developed model is suitable for designing and predicting ENi-P-TiO₂ composite coatings to avoid extensive experimentation with economic production. Scanning Electron Microscope (SEM) and X-ray diffraction analysis (XRD) are also utilised to compare the base metal and optimal coated surface.

Keywords

AH36 steel / ENi-P-nanoTiO₂ composite coatings / Artificial neural networks / Taguchi DOE / Microhardness / Mean squared error