Air-discharge Decomposition Gases Detected by Sensor Array with Contrast Learning

  • Jiakun Wang
  • , Feng Jing
  • , Zhengyang Yuan
  • , Bingjie Li
  • , Jie Yang
  • , Jianbin Pan
  • , Jifeng Chu
  • , Aijun Yang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

Before the insulation failure of the air switch cabinet, its partial discharge will decompose the air and form characteristic decomposition products including carbon monoxide (CO) and nitrogen dioxide (NO2). Because of its cross sensitivity, a single semiconductor gas sensor can hardly selectively distinguish these characteristic gases. Sensor array can effectively identify the gas composition, but to reduce the cost and sensor volume, the array needs to be optimized to reduce the number of sensors. In this paper, In this paper, an unsupervised algorithm based on contrast learning is employed to optimize semiconductor gas sensor array, to maintaining gas recognition accuracy while reducing the number of sensors.

Original languageEnglish
Title of host publicationProceedings - 2023 8th Asia Conference on Power and Electrical Engineering, ACPEE 2023
EditorsTek-Tjing Lie, Wenpeng Luan, Youbo Liu
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1596-1600
Number of pages5
ISBN (Electronic)9798350345520
DOIs
StatePublished - 2023
Event8th Asia Conference on Power and Electrical Engineering, ACPEE 2023 - Tianjin, China
Duration: 14 Apr 202316 Apr 2023

Publication series

NameProceedings - 2023 8th Asia Conference on Power and Electrical Engineering, ACPEE 2023

Conference

Conference8th Asia Conference on Power and Electrical Engineering, ACPEE 2023
Country/TerritoryChina
CityTianjin
Period14/04/2316/04/23

Keywords

  • array optimization
  • contrast learning
  • gas mixtures
  • semiconductor gas sensor

Fingerprint

Dive into the research topics of 'Air-discharge Decomposition Gases Detected by Sensor Array with Contrast Learning'. Together they form a unique fingerprint.

Cite this