Discrete wavelet transform optimal parameters estimation for arc fault detection in low-voltage residential power networks

AC series arc is dangerous and can cause serious electric fire hazards and property damage. This article proposed a convolutional neural network -based arc detection model named ArcNet. The database of this research is collected from eight different types of loads according to IEC62606 standard. The two most common types of arcs, including arcs from a loose connection of cables and those caused by the failure of the insulation, are generated in testing and included in the database. Using the database of raw current, experimental results indicate ArcNet can achieve a maximum of 99.47% arc detection accuracy at 10 kHz sampling rate. The model is also implemented in Raspberry Pi 3B for classification accuracy. A tradeoff study between the arc detection accuracy and model runtime has been conducted. The proposed ArcNet obtained an average runtime of 31 ms/sample of 1 cycle at 10 kHz sampling rate, which proves the feasibility of practical hardware deployment for real-time processing.

ArcNet: Series AC Arc Fault Detection Based on Raw Current and Convolutional Neural Network

AC series arc is dangerous and can cause serious electric fire hazards and property damage. This article proposed a convolutional neural network -based arc detection model named ArcNet. The database of this research is collected from eight different types of loads according to IEC62606 standard. The two most common types of arcs, including arcs from a loose connection of cables and those caused by the failure of the insulation, are generated in testing and included in the database. Using the database of raw current, experimental results indicate ArcNet can achieve a maximum of 99.47% arc detection accuracy at 10 kHz sampling rate. The model is also implemented in Raspberry Pi 3B for classification accuracy. A tradeoff study between the arc detection accuracy and model runtime has been conducted. The proposed ArcNet obtained an average runtime of 31 ms/sample of 1 cycle at 10 kHz sampling rate, which proves the feasibility of practical hardware deployment for real-time processing. 

Transmission line faults are detrimental to a power system but are inevitable. They disrupt power supply and can result in calamitous situations such as blackouts. With the advent of modern technology, protective systems use computer based digital relays. The operation of relays can be made more reliable, accurate and fast by the use of better techniques which are immune to factors such as fault distance, fault inception angle and fault impedance. This paper presents one such unique and powerful digital relaying technique using wavelet multi-resolution analysis (MRA) for a parallel transmission line. Daubechies 4 (db — 4) wavelet is used as mother wavelet. The summation of the 6th level detail co-efficients obtained from the wavelet MRA filter bank are used for fault detection and classification. This paper explicates the need for this type of algorithm and its advantages. The reliability of this algorithm has been tested using a MATLAB/Simulink model of a parallel transmission line for a variety of faults, fault distances and fault inception angles and this validates the proposed digital relaying technique.

A wavelet based novel technique for detection and classification of parallel transmission line faults

Robust functional analysis for fault detection in power transmission lines

Transmission lines faults are an inevitable part of any power system. They cause a disruption in the power supply, which is undesirable. With an ever-increasing demand for better performance and minimal interruptions, accurate fault analysis is necessary to restore a system to its normal operation by detecting and clearing the transmission line fault. This paper presents a comprehensive review of the techniques employed in fault analysis which have evolved over the last decade. This review paper mainly focuses on the implementation of discrete wavelet transform (WT), multi-resolution analysis (MRA) artificial neural networks (ANN) and fuzzy logic for fault analysis.

G Abilash

Papers

Wavelet based transmission line fault analysis: A literature survey