Real-Time Monitoring of Unmanned Substation Based on Audio Recognition

DOI

10.2991/icmmita-15.2015.272How to use a DOI?

Keywords

Audio recognition; real-time monitoring; failure recognition; unmanned substation.

Abstract

To make the unmanned power substation perform independently and efficiently, the theory and structure of a real-time monitoring system based on audio recognition is introduced in this paper. It focuses on the monitoring and identification process of audio data. Firstly the audio signal of substation is acquired by system using sensors. Then multi-audio data is transmitted to monitoring host. After spectrum analysis and process, MFCC feature parameters are extracted as signal features. Feature parameters are inputted into sinusoidal neural network for identification which can identify the operating status and type of failure efficiently and precisely. Numerical results illustrate that this method improves the traditional manual monitoring method and significantly increases the efficiency of device detection.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Wenming Cao
AU  - Erqian Tang
AU  - Guanzheng Tan
PY  - 2015/11
DA  - 2015/11
TI  - Real-Time Monitoring of Unmanned Substation Based on Audio Recognition
BT  - Proceedings of the 2015 3rd International Conference on Machinery, Materials and Information Technology Applications
PB  - Atlantis Press
SP  - 1475
EP  - 1483
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmmita-15.2015.272
DO  - 10.2991/icmmita-15.2015.272
ID  - Cao2015/11
ER  -