Support Vector Machine Parameters Optimization for 500 kV Long OHTL Fault Diagnosis

Faults can seriously damage high-voltage (HV) power systems, particularly if they occur on the long overhead transmission line (OHTL) that connects nuclear plant (NPP) to electrical grid. Finding OHTL problems quickly and accurately is essential for economy, safety, dependability of HV systems. It pinpoint problematic phase avoid unneeded outages. Thus, one most crucial research challenges now how identify, classify, locate faults. In this study, transient current with high frequency oscillations arise immediately after a defect at sending end investigated in single-circuit, single-side fed Egyptian 500-kV OHTL. Asymmetric symmetric faults locations are also represented Alternative Transients Program-Electro Magnetic Program (ATP/EMTP) simulation model under varying fault resistance inception angles. The proposed solution paper an Optimized Support Vector Machine (OSVM), whose characteristics optimized via mutant particle swarm optimization (MPSO) method detect 500 kV localizer built practical applications, including system noise contaminating signals. findings prove suggested approach locates 0.012 seconds from start event, 0.0098 percent average percentage error, without being impacted by differences distance, resistance, noise, or angle. Additionally, optimised classifier reaches 99.85% accuracy rate, enhancing advancing development.