Series arc fault detection of complex branch based on CNN_LSTM model

Qiongfang Yu; Jing Xu; Yi Yang

doi:10.1117/12.2635185

25 April 2022 Series arc fault detection of complex branch based on CNN_LSTM model

Qiongfang Yu, Jing Xu, Yi Yang

Proceedings Volume 12244, 2nd International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2022); 122444B (2022) https://doi.org/10.1117/12.2635185
Event: 2nd International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2022), 2022, Guilin, China

Abstract

When the simulation series arc fault occurs in the actual circuit, we find that the more complex the type and quantity of the load connected to the circuit end, the more difficult it is to detect. The collected trunk current signal has the characteristics of timing, periodicity and non-stationarity. To solve this problem, a series arc-fault detection method combining convolutional neural network (CNN) and long and short time memory network (LSTM) is proposed. Al l kinds of collected current data are directly fed into the improved CNN_LSTM model for fault data detection. The test results show that this method can quickly and accurately identify arc fault, and the accuracy rate is more than 99.04%. Moreover, It can accurately detect which kind of load branch occurs arc fault, and the accuracy rate is 97.90%. This method provides a reference for the research of the arc-fault detection under complex branches.

Citation Download Citation

Qiongfang Yu, Jing Xu, and Yi Yang "Series arc fault detection of complex branch based on CNN_LSTM model", Proc. SPIE 12244, 2nd International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2022), 122444B (25 April 2022); https://doi.org/10.1117/12.2635185

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
9 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Convolution

Data modeling

Neural networks

Neurons

Feature extraction

Performance modeling

Power supplies

Show All Keywords

Keywords/Phrases

Search In:

Publication Years