NOx Measurements in Vehicle Exhaust Using Advanced Deep ELM Networks

Considering that vehicle exhaust contributes to the majority of nitrogen oxides (NOx), which is harmful to environment and climate, it is important to measure NOx concentrations in sustainable developments. This article proposes to apply spectroscopic gas sensing methods and an innovative deep learn...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on instrumentation and measurement 2021, Vol.70, p.1-10
Main Authors: Ouyang, Tinghui, Wang, Chongwu, Yu, Zhangjun, Stach, Robert, Mizaikoff, Boris, Huang, Guang-Bin, Wang, Qi-Jie
Format: Article
Language:English
Subjects:
Algorithms
Analytical models
Artificial neural networks
Deep learning
Exhaust emission
Exhaust gases
Extreme learning machine (ELM)
Feature extraction
Gas mixtures
gas sensing
Gas sensors
Infrared detectors
Infrared spectra
Machine learning
Mathematical model
midinfrared sensors
Nitrogen oxides
Predictive models
Principal component analysis
Sensors
substrate-integrated hollow waveguides (iHWGs)
Substrates
vehicle exhaust
Waveguides
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Considering that vehicle exhaust contributes to the majority of nitrogen oxides (NOx), which is harmful to environment and climate, it is important to measure NOx concentrations in sustainable developments. This article proposes to apply spectroscopic gas sensing methods and an innovative deep learning network algorithm for obtaining high-precision NOx data. The adopted mid-infrared sensor technology is based on mid-infrared spectroscopy combined with an advanced substrate-integrated hollow waveguide (iHWG) sensing interface. Using extreme learning machine (ELM) algorithms with an exceptionally fast learning speed when dealing with big data problems next to excellent generalization abilities, a deep learning network for regressing NOx concentrations was implemented. Moreover, to further improve the regression performance the proposed deep ELM was provided with features derived from supervised learning improving its ability to address target constituents. Finally, experiments with gas mixtures containing three species relevant in exhaust emission monitoring have confirmed the utility of the developed approach.
ISSN:0018-9456
1557-9662
DOI:10.1109/TIM.2020.3013129