Shape optimization of a cap and pin insulator in pollution condition using particle swarm and neural network

The objective in this paper is the introduction of a new method in the design of high voltage insulators by exploiting a meta-heuristic optimization. Indeed, a neural network is used for the prediction of the value of the tangential electric field at the high voltage pin (the area where the value of the electric field is maximum), which will then serve as an objective function to be minimized by the particle swarms optimization method (PSO). Constraints are assigned to the model in order to reduce the creepage distance of the insulator and consequently reduce its weight.