Prediction of mechanical properties of XLPE cable insulation under thermal aging: neural network approach

Abstract

The widespread use of Cross-linked Polyethylene (XLPE) as insulation in the manufacturing of medium and high voltage cables may be attributed to its outstanding mechanical and electrical properties. However, it is well known that degradation under service conditions is the major problem in the use of XLPE as insulation in cables. In order to reduce the aging experiments time, we have used Artificial Neural Networks (ANN) to predict the insulation properties. The proposed networks are supervised and non supervised neural networks. The supervised neural network was based on Radial Basis Function Gaussian (RBFG) and was trained with two algorithms: Backpropagation (BP) and Random Optimization Method (ROM). The non supervised neural network was based on the use of Kohonen Map. All these neural networks present good quality of prediction.