PID Sensor Reading Calibration for Vigi E-Nose System Using Deep Neural Network

PID Sensor Reading Calibration for Vigi E-Nose System Using Deep Neural Network

The 17th IEEE Conference on Industrial Electronics and Applications (ICIEA 2022)

http://www.ieeeiciea.org/2022/

Susu Yao, Haiyan Shu, Yi Guo

Electrical and Electronic Engineering

19 December 2022

NA

Sensors are widely used to monitor the urban environment and human activities. Due to the nature of chemical sensors, they suffer seriously to the environment. Especially for PID sensors, its sensitivity may degrade over time which results in an unreliable reading. To solve this problem, sensor calibration is adopted. However, regular calibration can only capture the status at the time of calibration, while the sensitivity degradation is not captured in between the period of two calibrations. In this paper, the sensitivity degradation pattern of PID sensor is studied and modeled using deep neural network. The refined base sensitivity is used to re-calibrate the sensor reading to improve the reliability of the gas concentration measurement of the Vigi E-nose system.

Publisher Copyright

This research / project is supported by the Singapore Ministry of National Development / National Research Foundation, Prime Minister’s Office - Land and Liveability National Innovation Challenge (L2 NIC) Research Programme
Grant Reference no. : L2NICTDF1-2017-3

© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

https://oar.a-star.edu.sg/communities-collections/articles/18868

978-1-6654-0983-4

Institute for Infocomm Research