A Novel Non-intrusive Arc Fault Detection Method for Low-Voltage Customers

2014 ◽

Vol 889-890 ◽

pp. 741-744 ◽

Cited By ~ 1

Author(s):

Kai Yang ◽

Ren Cheng Zhang ◽

Jian Hong Yang ◽

Xiao Mei Wu

Keyword(s):

Fault Detection ◽

Fourth Order ◽

Detection Method ◽

Low Voltage ◽

Normal Load ◽

Higher Order ◽

Higher Order Cumulants ◽

Low Voltage Circuits

Arc faults are one of the main reasons of electrical fires. For the difficulty of series arc fault detection, very few of techniques have successfully protected loads from arc faults in low-voltage circuits, especially in China. When series arc faults occur, shoulders will appear in load currents. The shoulder widths of non-arc faults such as normal load arcs are stable, while those of arc faults are variable because the appearance of arc faults is erratic. Therefore, a novel detection method based on shoulder characteristics was proposed. To better capture shoulder widths, original currents were firstly converted into pulses. Then, the pulse widths were used to detect arcs and the fourth-order cumulants of their differential were used to distinguish arc faults from normal operations. Finally, an arc fault detection device (AFDD) prototype was developed for test. The results show this prototype can discriminate arc faults effectively from normal operations.

Download Full-text

Low voltage AC series arc fault detection method based on parallel deep convolutional neural network

IOP Conference Series Materials Science and Engineering ◽

10.1088/1757-899x/490/7/072020 ◽

2019 ◽

Vol 490 ◽

pp. 072020

Author(s):

Qiongfang Yu ◽

Gaolu Huang ◽

Yi Yang

Keyword(s):

Neural Network ◽

Fault Detection ◽

Convolutional Neural Network ◽

Detection Method ◽

Low Voltage ◽

Deep Convolutional Neural Network

Download Full-text

Research on Arc Fault Detection Method of Low Voltage Shutdown Controller

2020 International Conference on Urban Engineering and Management Science (ICUEMS) ◽

10.1109/icuems50872.2020.00066 ◽

2020 ◽

Author(s):

He Ninghui ◽

Li Xiuguang ◽

Zhou Xiu ◽

Tian Lu

Keyword(s):

Fault Detection ◽

Detection Method ◽

Low Voltage

Download Full-text

A Fault Detection Approach Based on Sound Signal Analysis for Equipment Monitoring

International Journal of Scientific Research in Science Engineering and Technology ◽

10.32628/ijsrset207430 ◽

2020 ◽

pp. 129-139

Author(s):

Weihai Sun ◽

Lemei Han

Keyword(s):

Fault Detection ◽

Signal Analysis ◽

Energy Analysis ◽

Detection Method ◽

Sound Signal ◽

Practical Significance ◽

Time Frequency ◽

Detection Approach ◽

Machine Fault ◽

Learning Data

Machine fault detection has great practical significance. Compared with the detection method that requires external sensors, the detection of machine fault by sound signal does not need to destroy its structure. The current popular audio-based fault detection often needs a lot of learning data and complex learning process, and needs the support of known fault database. The fault detection method based on audio proposed in this paper only needs to ensure that the machine works normally in the first second. Through the correlation coefficient calculation, energy analysis, EMD and other methods to carry out time-frequency analysis of the subsequent collected sound signals, we can detect whether the machine has fault.

Download Full-text