The static DC and PR are two typical operation conditions of converter transformer outlet

moreover

the electrical parameters of RIP

transformer oil and OIP have nonlinear relationship with E-field stress and temperature. Under a temperature gradient

the electrical parameters will modify the static DC and PR E-field distribution of composite insulation. In order to simulate the static DC and PR electric field of the composite insulation structure

we established a full model of the converter transformer outlet. Then

the structure parameters of the converter transformer outlet were optimized using combined RBF neural network and NSGA-II algorithm. Moreover

the electric field verification calculation were carried out under AC and PR conditions. The results show that

under uniform temperature condition

the E-field strength is more significant than that under isothermal condition

and the overshoot coefficient of the bushing end and barrier reaches 65% and 45%

respectively. The study can provide a reference for the design of outlet structure of the converter transformer.