Abstract
This study presents an artificial intelligence (AI)-based approach for predicting the thickness of electrodeposited zinc coatings on low carbon steel. The thickness of the coating is directly related to the corrosion resistance of the steel, according to the ABNT NBR 10476. The study investigates the influence of process time, ZnO/NaOH concentrations, anode material, and additives on coating thickness measured by X-ray fluorescence, employing the Hull cell method and a fractional factorial design. Statistical analysis and supervised machine learning algorithms, including multivariate regression, random forest, and extreme gradient boosting (XGBoost), were employed to develop prediction models. Among these models, XGBoost demonstrated superior performance with a coefficient of determination (R2) of 0.95 and a mean squared error (MSE) of 0.815, highlighting the effectiveness of AI in comparison to traditional regression methods. The AI models developed provide a valuable tool for the electroplating industry. They allow for the optimization of input parameters to achieve desired coating thicknesses and improve corrosion resistance. This ultimately reduces costs and improves product quality.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call