Akbal, Bahadir2020-03-262020-03-2620171300-70092147-5881https://dx.doi.org/10.5505/pajes.2016.84669https://hdl.handle.net/20.500.12395/35135The sheath current causes cable faults and electroshock risk in high voltage underground cable lines. Also the sheath current increases cable temperature and it reduces cable ampacity. Hence, cable performance decreases due to the sheath current. Different precautions can be taken to reduce the sheath current effects in high voltage underground cable line. However, primarily the sheath current must be detected at the project phase of high voltage underground cable line. In literature, artificial neural networks are used for forecasting studies. In this study, artificial neural network (ANN) is used with particle swarm optimization, particle swarm optimization with inertia weight and genetic algorithm to generate hybrid ANN methods for forecasting of the sheath current. High voltage underground cable line is modeled in PSCAD/EMTDC to measure the sheath current of different high voltage underground lines, and the obtained data from PSCAD/EMTDC are used to train artificial neural network based hybrid methods to forecast the sheath current of any high voltage underground cable line. When particle swarm optimization with inertia weight is used with artificial neural network, hybrid ANN-iPSO method is developed. The results of ANN-iPSO are better than the results of ANN-GA and ANN-PSO. If ANN-iPSO is used to determine the sheath current, the sheath current of high voltage underground cable line can be determined at the project phase of high voltage underground cable line. Hence, the most suitable precautions can be implemented, and cable faults and electroshock risk can be prevented, also cable performance is increased in high voltage underground cable line.tr10.5505/pajes.2016.84669info:eu-repo/semantics/openAccessHigh voltage underground cableArtificial neural networkOptimization methodsThe sheath currentHybrid methodsArticle232119125#YOKWOS:000443167700004N/A