Transmission line faults pose a significant threat to power system resilience,underscoring the need for accurate and rapid fault identification to facilitate proper resource monitoring,economic loss prevention,and bla...Transmission line faults pose a significant threat to power system resilience,underscoring the need for accurate and rapid fault identification to facilitate proper resource monitoring,economic loss prevention,and blackout avoidance.Extreme learning machine(ELM)offers a compelling solution for rapid classification,achieving network training in a single epoch.Leveraging the Internet of Things(IoT)and the virtual instrumentation capabilities of LabVIEW,ELM can enable the swift and precise identification of transmission line faults.This paper presents a regularized radial basis function(RBF)ELM-based fault detection and classification system for transmission lines,utilizing a LabVIEW based virtual phasor measurement unit(PMU)and IoT sensors.The transmission line fault is identified using the phaselet algorithm applied to the phase current acquired from the virtual PMU.Classification is then performed using the ELM algorithm.The proposed methodology is validated in real-time on a practical transmission line,achieving an accuracy of 99.46%.This has the potential to significantly influence future fault detection strategies incorporating virtual PMUs and machine learning.展开更多
基金supported by the Experimental-Demonstration project PN-IV-P7-7.1-PED-2024-0567(Improving the Fuel Cell Hybrid Electric Vehicle Drivetrain by Implementing a Novel Optimal Real-Time Power Management Strategy),contract no.58PED(N.B.)the APC was funded by S.C.ECAI CONFERENCE S.R.Lsupported by Science and Engineering Research Board,India with grant number ECR/2017/000812.
文摘Transmission line faults pose a significant threat to power system resilience,underscoring the need for accurate and rapid fault identification to facilitate proper resource monitoring,economic loss prevention,and blackout avoidance.Extreme learning machine(ELM)offers a compelling solution for rapid classification,achieving network training in a single epoch.Leveraging the Internet of Things(IoT)and the virtual instrumentation capabilities of LabVIEW,ELM can enable the swift and precise identification of transmission line faults.This paper presents a regularized radial basis function(RBF)ELM-based fault detection and classification system for transmission lines,utilizing a LabVIEW based virtual phasor measurement unit(PMU)and IoT sensors.The transmission line fault is identified using the phaselet algorithm applied to the phase current acquired from the virtual PMU.Classification is then performed using the ELM algorithm.The proposed methodology is validated in real-time on a practical transmission line,achieving an accuracy of 99.46%.This has the potential to significantly influence future fault detection strategies incorporating virtual PMUs and machine learning.
