Process optimization for improving anti-oxidation performance of silver-coated copper powders by response surface methodology and artificial neural network

The use of silver-coated copper powders (SCCPs) is a promising approach to reduce costs in the photovoltaic industry. However, the anti-oxidation performance of SCCPs directly determines their reliability in practical applications. This study aims to design an efficient approach for optimizing process parameters to enhance anti-oxidation performance of SCCPs. An innovative co-optimization strategy integrating response surface methodology (RSM) and artificial neural network (ANN) is proposed to optimize process parameters. The effects of interactions between process parameters on the anti-oxidation performance of SCCPs were investigated using RSM. The optimal parameter combination (ascorbic acid concentration: 0.05 mol/L, pH: 7, and feeding rate: 15 mL/min) was determined, and the results were predicted using ANN. The strategy achieves superior optimization efficiency and predictive accuracy compared to individual methods by reducing experimental requirements, lowering error functions, and enhancing fitting precision. Experimental results demonstrated that the co-optimization strategy reduced the oxidation weight gain of SCCPs by 60 % under dynamic heating conditions in an atmospheric environment, with a prediction error of 2.45 %. The co-optimization strategy successfully enhanced both the antioxidant properties and powder quality of SCCPs. This work offers an innovative design approach for enhancing the properties of silver-coated copper powders.