The operation state of insulators is closely related to the safety and reliability of the power network. Affected by the environment, the insulator strings will gradually age and become low-value or zero-value in insulators. Therefore, it is of great engineering significance to correctly and timely detect whether there are faults in insulators. It has a good engineering application prospect to evaluate the insulation condition of insulators by detecting the surface electric field value of insulators. In this paper, the external axial electric field value of the insulator skirt is obtained through finite element simulation, and the combined neural network model is used. Finally, the effectiveness of the model is verified by the measured data. The experimental results show that this method can effectively identify whether the insulator has deteriorated.