Predictive modeling of pulse-electrodeposited Cu-Zn alloy and dealloying for porous electrode fabrication.

Porous metals (PMs) have attracted significant attention in recent years due to their unique structural and functional properties, holding potential for a wide range of applications in catalysis, sensing, energy storage, and filtration. Among these, porous copper (PC), which is produced by dealloying copper-zinc (Cu-Zn) alloys has evolved as a particularly valuable material. In this study, a Cu-Zn alloy is electrochemically deposited onto a Cu wire in a sulphate-based electrolyte containing tri-sodium citrate as a complexing agent. To produce PC, the alloy has been subjected to chemical dealloying to dissolve the less noble element. We have implemented machine learning algorithms such as adaptive neuro-fuzzy inference systems (ANFIS), artificial neural networks (ANN), and response surface methodology (RSM) to model the interaction of process parameters and responses. Statistical modeling has been carried out to investigate the influence of operating parameters, including precursor reagent quantities (0.002-0.2 M), electrodeposition time (15-45 min), and dealloying time (16-24 h), on Zn content, dealloyed weight, and change in grain size. The test results confirm that both models fit the experimental data well, with the ANN model achieving high accuracy ( = 0.98, 0.96, and 0.96 for Zn content, dealloyed weight, and grain size change, respectively); however, the ANFIS model demonstrates superior performance with the highest value (0.99) and the lowest MAPE (0.003, 0.002, and 0.001 for the respective responses). The RSM-BBD model is best suited for analyzing parameter interactions on responses, as it systematically evaluates the combined effects of multiple variables. By using potentiodynamic polarization curves to compare the corrosion resistance of Cu-Zn electrodes to bare Cu and PC electrodes, it was found that Cu-Zn electrodes have better corrosion resistance. Additionally, dealloying has resulted in a transition from a hydrophobic (110 ± 1°) to a hydrophilic (59 ± 0.5°) surface.