using Metal Oxide Sensors in a Turbulent Environment Achim J. Lilienthal*, Tom Duckett*, Hiroshi Ishida**, Felix Werner*** * Örebro University – Dept. of Technology, AASS – Örebro (Sweden) ** Tokyo Univ. of Agriculture & Technology – Dept. of Mech. Systems Eng. – Tokyo (Japan) ** University of Tübingen - Wilhelm-Schickard Institute - Tübingen (Germany) • We address the problem of estimating the distance to a gas source using concentration measurements. • The difficulty in a real-world environment is that the gas distribution is turbulent, i.e. the concentration field does not have smooth gradients. • Previous experiments showed that gas sensor readings recorded during a rotation maneouvre can be discriminated according to the distance from the gas source using machine learning techniques. • We investigate possible indicators of gas source proximity in the learned models. A correlation analysis showed that the response variance was a better indicator than the average response.
We address the problem of estimating the distance to a gas source using concentration measurements.
Feb 25, 2016
- PowerPoint PPT Presentation
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Indicators of Gas Source Proximity using Metal Oxide Sensors in a Turbulent Environment
Achim J. Lilienthal*, Tom Duckett*, Hiroshi Ishida**, Felix Werner*** * Örebro University – Dept. of Technology, AASS – Örebro (Sweden)
** Tokyo Univ. of Agriculture & Technology – Dept. of Mech. Systems Eng. – Tokyo (Japan)** University of Tübingen - Wilhelm-Schickard Institute - Tübingen (Germany)
• We address the problem of estimating the distance to a gas source using concentration measurements.
• The difficulty in a real-world environment is that the gas distribution is turbulent, i.e. the concentration field does not have smooth gradients.
• Previous experiments showed that gas sensor readings recorded during a rotation maneouvre can be discriminated according to the distance from the gas source using machine learning techniques.
• We investigate possible indicators of gas source proximity in the learned models. A correlation analysis showed that the response variance was a better indicator than the average response.
Related Documents
