Intelligent optimization of Y2O3-doped AgSnO2 electrical contact materials: a machine learning and finite element analysis approach

In order to clarify the influence of the reinforced phase Y2O3 on the electrical contact properties of AgSnO2, 10,000 electrical contact experiments were completed on AgSnO2Y2O3 prepared by internal oxidation method by an electrical property testing system under DC 28V/40A. The surface morphology of the arc erosion specimens was characterized using scanning electron microscopy, the weight changes before and after the electrical contact tests were determined, and the effects of Y2O3 on the contact resistance, arc ignition time, arc energy, fusion welding force, and material transfer of AgSnO2 were discussed. The results show that the addition of 0.5 wt% of Y2O3 to AgSnO2 can reduce the overall contact resistance while improving its stability, make the overall reduction of the closed arc ignition time and energy while improving the stability, and also reduce the fusion welding force of the contact while reducing the net material loss of the contact pairs, but an increase in the amount of the additive is rather detrimental to the improvement of the electrical contact performance of the contact. Furthermore, a computer-aided data acquisition system was utilized to monitor arc behavior in real-time, and numerical simulations (ANSYS) were integrated to validate experimental trends. This combined approach offers a pathway for intelligent optimization of contact materials.