Electric field estimation around an overhead power transmission line using neural network model

This paper presents the use of artificial neural networks (ANN) to estimate electric fields around an overhead power transmission line. Although there exist many efficient numerical methods, e.g. finite difference method (FDM), finite element method (FEM), boundary element method (BEM), etc, to estimate electric field distribution caused by live conductors, it typically consumes substantial execution time when high accuracy of obtained solutions is required or especially when time-varying field is involved. Therefore, to estimate the electric field strength using ANN employing feedforword network with backpropagation learning can be an alternative. To evaluate its use, an overhead single-phase power line of 100 m(2) test area was simulated with 22 kV standard distribution level of Thailand. The results obtained from the ANN are compared with those obtained by the analytical method, the FDM and the FEM.