Designing of High Voltage Cable Bonding with Intelligence Algorithms to Avoid Cable Insulation Faults and Electroshock in High Voltage Lines

  • BAHADIR AKBAL Selçuk University


There are different layers in the high voltage cable, and the most important layer is the insulation layer. The

      insulation layer of cable is protected by metal sheath in high voltage cable, but harmonic current and the metal sheath

      voltage (MV) occurs on the metal sheath of cable due to the line current, and harmonic current and MV are major factors

      for the insulation fault in the cable. Metal sheath is grounded by the bonding methods to avoid insulation fault in the

      literature. However, these bonding methods are not adequate to avoid insulation faults. Sectional solid bonding with

      different grounding resistance (SSBr) method is developed to avoid insulation fault that is based on harmonic current and

  1. MV of high voltage cable should be known to use SSBr. However, if SSBr is used for a new line, MV of high voltage

      cable is not known for designing of SSBr. Thus, three groups the prediction methods are used to determine MV. These

      groups are neural networks, hybrid neural networks and regression methods. The most suitable prediction methods are

    selected from each group according to minimum training error, and hybrid neural network with inertia weighted particle

     swarm optimization (H-iPSO), linear regression and feedforward backpropagation neural network are selected from their

      groups. After the prediction methods are determined, SSBr is optimized for minimization of harmonic current and MV

     value. Inertia weighted particle swarm optimization, particle swarm optimization, genetic algorithm and differential

      evolution algorithm are used for optimization of SSBr. When H-iPSO is used as prediction method in particle swarm

      optimization for optimization of SSBr, minimum harmonic current distortion and MV values are obtained. Namely, when

     H-iPSO and particle swarm optimization is used together in SSBr, both insulation fault and electroshock are avoided by

     the optimized SSBr.

Electrical Engineering