This study investigates the seismic fragility of nuclear power plant (NPP) auxiliary structures by incorporating material aging deterioration into machine learning–based response prediction models. An artificial neural network (ANN) was developed using 17 seismic and material parameters, achieving high predictive accuracy (R2 = 0.96) while significantly reducing computational demands compared with conventional finite element analyses. By combining the ANN with Monte Carlo simulations, fragility curves for Motor Control Center (MCC) cabinet anchors were derived at resonance frequencies of 10 Hz and 15 Hz. Results indicate that equipment with higher resonance frequency (15 Hz) exhibits lower seismic vulnerability due to reduced sensitivity to dominant low-frequency seismic components. When material deterioration was introduced, fragility curves shifted toward lower ground motion intensities, reflecting increased failure probabilities and approximately 20% reduction in median seismic capacity. These findings highlight the necessity of considering aging effects in probabilistic seismic risk assessments and demonstrate the efficiency of ML-based surrogate models for quantifying long-term safety margins of NPP structures.