As computers develops, virtual simulation technology becomes an important means of integrated circuit design. Therefore, based on the demand for virtual simulation of integrated circuits, a simulation method combining affinity propagation and differential evolution algorithm was proposed. By applying the affinity propagation to circuit fault diagnosis and combining it with differential evolution algorithm, circuit parameters optimization was carried out. These experiments confirm that the fusion of affinity propagation and differential evolution algorithm has a precision of 94.26%, recall of 93.41%, mean F1 of 88.59%, convergence speed of 56.77 seconds, and stability of 93.17%. The affinity propagation performs well in clustering. Especially without pre-defining the classes, it can identify the position and number of class centers automatically. The simulation of integrating affinity propagation and differential evolution algorithm has broad application prospects in virtual simulation of integrated circuits. It can improve simulation effectiveness and performance, providing effective support for circuit design and testing.