Two-Terminal Fault Location Method of Distribution Network Based on Adaptive Convolution Neural Network

Liang, Jiefeng; Jing, Tianjun; Huanna, Niu; Wang, Jiangbo

doi:10.1109/access.2020.2980573

Cited by 117 publications

(40 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, in [11], the high-frequency components, extracted using Empirical Mode Decomposition, are used to obtain the faulty section of an HVDC transmission line. Another study [12] proposes an Adaptative Convolutional Neural Networks (ACNN) to infer the fault type in a transmission line using measurements from two Phasor Measurement Units (PMUs). It is stated that ACNN, in comparison to CNN, are trained faster and have a slightly better accuracy.…”

Section: Introductionmentioning

confidence: 99%

Fast Fault Location Method for a Distribution System with High Penetration of PV

Jiménez-Aparicio

Grijalva

Reno

2021

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

Distribution systems with high levels of solar PV may experience notable changes due to external conditions, such as temperature or solar irradiation. Fault detection methods must be developed in order to support these changes of conditions. This paper develops a method for fast detection, location, and classification of faults in a system with a high level of solar PV. The method uses the Continuous Wavelet Transform (CWT) technique to detect the traveling waves produced by fault events. The CWT coefficients of the current waveform at the traveling wave arrival time provide a fingerprint that is characteristic of each fault type and location. Two Convolutional Neural Networks are trained to classify any new fault event. The method relays of several protection devices and doesn't require communication between them. The results show that for multiple fault scenarios and solar PV conditions, high accuracy for both location and type classification can be obtained.

show abstract

Section: Introductionmentioning

confidence: 99%

Fast Fault Location Method for a Distribution System with High Penetration of PV

Jiménez-Aparicio

Grijalva

Reno

2021

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

show abstract

“…Feature extraction processes may rely upon on the Wavelet Transform, as presented in [20], the Discrete Fourier Transform, as in [21], and/or the energy of the signal [22]. The choice of the most suitable artificial intelligence algorithm may consider Artificial Neural Networks, as described in [22], [23], Support Vector Machines, as in [24], Fuzzy Logic, as in [25], and Petri Nets, as in [26].…”

Section: Introductionmentioning

confidence: 99%

Fault Location in Overhead Transmission Lines Based on Magnetic Signatures and on the Extended Kalman Filter

Neto¹,

Sartori

Manassero

2021

IEEE Access

View full text Add to dashboard Cite

This paper proposes a non-contact method for fault location in transmission lines, which is based on magnetic fields produced by current signals measured using magnetoresistive sensors installed only at transmission line terminals, under the phase conductors of the first transmission tower at both terminals or at the substations portals. The proposed method uses the Extended Kalman filter to process these measurements and is based on a travelling wave approach in order to perform the fault localization. This paper also describes the implementation and testing of the method, firstly introducing its overview, followed by an analysis of the magnetic fields produced by the current signals, as well as considerations on their measurement; secondly, detailing the Extended Kalman filter and the travelling wave approach; and, finally, presenting the results of the method with regards to simulations built using EMTP/ATP to evaluate its robustness under different conditions varying the fault resistance, fault inception angle, phases involved and fault location. The results indicate that the proposed method is robust and accurate.

show abstract

“…Traveling methods are categorized as single-or double-terminal faultlocation methods [14][15][16], and the development of inexpensive communications and accurate satellite-time services has led to double-terminal fault-location methods becoming common. Machine learning methods, such as convolution neural networks, are also used in fault location, and are greatly effective in some situations [17]. However, although the theory of many fault location methods has been researched, few have been tested in practice.…”

Section: Introductionmentioning

confidence: 99%

A Double-Terminal Traveling-Wave-Based Method Using Novel Noncontact Sensors for Fault Location in Transmission Cable Lines

et al. 2021

View full text Add to dashboard Cite

The burgeoning demand for enhanced power-system safety means that there is increased attention on technologies for the detection and location of cable faults. The double-terminal fault location method, which senses a fault current using a current transformer (CT), is the most effective and widely applied method in industrial practice. However, CT sensors may suffer from magnetic saturation when exposed to a high fault current, resulting in significant location errors, and their sensitivity cannot be adjusted. To address this problem, this paper describes an improved method for the acquisition of fault signal and the identification of fault-wave arrival time in power cables. First, a novel noncontact sensor (NCS) is developed for the detection of electric fields, and its sensitivity-adjustment curves are obtained by theoretical calculation and simulation. Then, based on feedback variational mode decomposition (FVMD) and the Wigner-Ville distribution (WVD), an improved method (the FVMS + WVD method) for the identification of fault-wave arrival time is devised, and its efficacy and accuracy are verified by simulations in Power Systems Computer-Aided Design/Electromagnetic Transients including DC (PSCAD/EMTDC) software. Finally, the fault-wave arrival-time detection performance of the NCS is examined in a series of on-site DC and AC experiments based on damped AC technology. The results show that the NCS exhibits feasible and effective performance, and that its response can be appropriately tuned based on its sensitivityadjustment curves. The FVMD + WVD method is more accurate than several other current methods, as its error is only 0.48%, and thus this method enables the practical location of cable faults. In sum, these findings demonstrate that the NCS and the FVMD + WVD method comprise an improved system for the detection and location of cable faults, which will enhance cable safety in power systems.INDEX TERMS fault detection and location, double-terminal, electric field sensors, feedback variational mode decomposition, Wigner-Ville distribution.

show abstract

Two-Terminal Fault Location Method of Distribution Network Based on Adaptive Convolution Neural Network

Cited by 117 publications

References 8 publications

Fast Fault Location Method for a Distribution System with High Penetration of PV

Fast Fault Location Method for a Distribution System with High Penetration of PV

Fault Location in Overhead Transmission Lines Based on Magnetic Signatures and on the Extended Kalman Filter

A Double-Terminal Traveling-Wave-Based Method Using Novel Noncontact Sensors for Fault Location in Transmission Cable Lines

Contact Info

Product

Resources

About