Error analysis.

An Aquila optimizer-back propagation (AO-BP) neural network was used to establish an approximate model of the relationship between the design variables and the optimization objective to improve elevator block brake capabilities and achieve a lightweight brake design. Subsequently, the constraint conditions and objective functions were determined. Moreover, the multi-objective genetic algorithm optimized the structural block brake design. Finally, the effectiveness of the optimization results was verified using simulation experiments. The results demonstrate that the maximum temperature of the optimized brake wheel during emergency braking was 222.09°C, which is 36.71°C lower than that of 258.8°C before optimization, with a change rate of 14.2%. The maximum equivalent stress after optimization was 246.89 MPa, 28.87 MPa lower than that of 275.66 MPa before optimization, with a change rate of 10.5%. In addition, the brake wheel mass was reduced from 58.85 kg to 52.40 kg, and the thermal fatigue life at the maximum equivalent stress increased from 64 times before optimization to 94 times after optimization.