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