Advances in artificial intelligence (AI) make it possible to reduce analysis times, costs and improve industrial processes. This work integrates a literature review and an experimental approach to the application of AI in the electrodeposition of zinc in low carbon steels. The review, carried out on the Web of Science database, revealed
studies that are still incipient, indicating room for research that explores machine learning (ML) in the optimisation of the galvanising process. Experimentally, predictive models for coating thickness, essential for corrosion resistance according to standard NBR 10476 (ABNT,2016), were developed using multivariate regression, random forest and xgboost. The xgboost model stood out, with an R2 of 0.95 and an MSE of 0.815, proving effective in predicting results. AI models make it possible to optimise process parameters (process time, ZnO/NaOH concentrations, anode material, and additives), improving quality and reducing costs. It is concluded that AI offers a promising way forward for galvanising low carbon steels.