Random gas mixtures for efficient gas sensor calibration
<p>Applications like air quality, fire detection and detection of explosives require selective and quantitative measurements in an ever-changing background of interfering gases. One main issue hindering the successful implementation of gas sensors in real-world applications is the lack of appr...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Copernicus Publications
2020-11-01
|
Series: | Journal of Sensors and Sensor Systems |
Online Access: | https://jsss.copernicus.org/articles/9/411/2020/jsss-9-411-2020.pdf |
id |
doaj-251197449b8e4fb1aa9a2a95b0ad1719 |
---|---|
record_format |
Article |
spelling |
doaj-251197449b8e4fb1aa9a2a95b0ad17192020-12-07T08:10:33ZengCopernicus PublicationsJournal of Sensors and Sensor Systems2194-87712194-878X2020-11-01941142410.5194/jsss-9-411-2020Random gas mixtures for efficient gas sensor calibrationT. Baur0M. Bastuck1C. Schultealbert2T. Sauerwald3T. Sauerwald4A. Schütze5Lab for Measurement Technology, Saarland University, 66123 Saarbrücken, GermanyLab for Measurement Technology, Saarland University, 66123 Saarbrücken, GermanyLab for Measurement Technology, Saarland University, 66123 Saarbrücken, GermanyLab for Measurement Technology, Saarland University, 66123 Saarbrücken, Germanycurrently at: Fraunhofer Institute for Process Engineering and Packaging IVV, 85354 Freising, GermanyLab for Measurement Technology, Saarland University, 66123 Saarbrücken, Germany<p>Applications like air quality, fire detection and detection of explosives require selective and quantitative measurements in an ever-changing background of interfering gases. One main issue hindering the successful implementation of gas sensors in real-world applications is the lack of appropriate calibration procedures for advanced gas sensor systems. This article presents a calibration scheme for gas sensors based on statistically distributed gas profiles with unique randomized gas mixtures. This enables a more realistic gas sensor calibration including masking effects and other gas interactions which are not considered in classical sequential calibration. The calibration scheme is tested with two different metal oxide semiconductor sensors in temperature-cycled operation using indoor air quality as an example use case. The results are compared to a classical calibration strategy with sequentially increasing gas concentrations. While a model trained with data from the sequential calibration performs poorly on the more realistic mixtures, our randomized calibration achieves significantly better results for the prediction of both sequential and randomized measurements for, for example, acetone, benzene and hydrogen. Its statistical nature makes it robust against overfitting and well suited for machine learning algorithms. Our novel method is a promising approach for the successful transfer of gas sensor systems from the laboratory into the field. Due to the generic approach using concentration distributions the resulting performance tests are versatile for various applications.</p>https://jsss.copernicus.org/articles/9/411/2020/jsss-9-411-2020.pdf |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
T. Baur M. Bastuck C. Schultealbert T. Sauerwald T. Sauerwald A. Schütze |
spellingShingle |
T. Baur M. Bastuck C. Schultealbert T. Sauerwald T. Sauerwald A. Schütze Random gas mixtures for efficient gas sensor calibration Journal of Sensors and Sensor Systems |
author_facet |
T. Baur M. Bastuck C. Schultealbert T. Sauerwald T. Sauerwald A. Schütze |
author_sort |
T. Baur |
title |
Random gas mixtures for efficient gas sensor calibration |
title_short |
Random gas mixtures for efficient gas sensor calibration |
title_full |
Random gas mixtures for efficient gas sensor calibration |
title_fullStr |
Random gas mixtures for efficient gas sensor calibration |
title_full_unstemmed |
Random gas mixtures for efficient gas sensor calibration |
title_sort |
random gas mixtures for efficient gas sensor calibration |
publisher |
Copernicus Publications |
series |
Journal of Sensors and Sensor Systems |
issn |
2194-8771 2194-878X |
publishDate |
2020-11-01 |
description |
<p>Applications like air quality, fire detection and
detection of explosives require selective and quantitative measurements in
an ever-changing background of interfering gases. One main issue hindering
the successful implementation of gas sensors in real-world applications is
the lack of appropriate calibration procedures for advanced gas sensor
systems. This article presents a calibration scheme for gas sensors based on
statistically distributed gas profiles with unique randomized gas mixtures.
This enables a more realistic gas sensor calibration including masking
effects and other gas interactions which are not considered in classical
sequential calibration. The calibration scheme is tested with two different
metal oxide semiconductor sensors in temperature-cycled operation using
indoor air quality as an example use case. The results are compared to a
classical calibration strategy with sequentially increasing gas
concentrations. While a model trained with data from the sequential
calibration performs poorly on the more realistic mixtures, our randomized
calibration achieves significantly better results for the prediction of both
sequential and randomized measurements for, for example, acetone, benzene and
hydrogen. Its statistical nature makes it robust against overfitting and
well suited for machine learning algorithms. Our novel method is a promising
approach for the successful transfer of gas sensor systems from the
laboratory into the field. Due to the generic approach using concentration
distributions the resulting performance tests are versatile for various
applications.</p> |
url |
https://jsss.copernicus.org/articles/9/411/2020/jsss-9-411-2020.pdf |
work_keys_str_mv |
AT tbaur randomgasmixturesforefficientgassensorcalibration AT mbastuck randomgasmixturesforefficientgassensorcalibration AT cschultealbert randomgasmixturesforefficientgassensorcalibration AT tsauerwald randomgasmixturesforefficientgassensorcalibration AT tsauerwald randomgasmixturesforefficientgassensorcalibration AT aschutze randomgasmixturesforefficientgassensorcalibration |
_version_ |
1724397802969104384 |