Retrieval of gas concentrations in optical spectroscopy with deep learning

•A basis for further research on the contacts between DL and absorption spectroscopy.•An end-to-end DNN based DAS gas sensing system is established for the first time.•Higher accuracy and faster computation speed compared with WMS.•Robustness to noisy conditions, laser aging and circuit parameters c...

Full description

Saved in:
Bibliographic Details
Published in:Measurement : journal of the International Measurement Confederation 2021-09, Vol.182, p.109739, Article 109739
Main Authors: Tian, Linbo, Sun, Jiachen, Chang, Jun, Xia, Jinbao, Zhang, Zhifeng, Kolomenskii, Alexandre A., Schuessler, Hans A., Zhang, Sasa
Format: Article
Language:English
Subjects:
Absorption spectroscopy
Acetylene
Artificial neural networks
Circuits
Deep Neural Networks
Direct Absorption Spectroscopy
Gas sensors
Gases
Gases Concentration Retrieval
Information retrieval
Machine learning
Multilayers
Natural gas
Neural networks
Retrieval
Robustness (mathematics)
Spectrum analysis
Studies
Transfer learning
Wavelength modulation
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:•A basis for further research on the contacts between DL and absorption spectroscopy.•An end-to-end DNN based DAS gas sensing system is established for the first time.•Higher accuracy and faster computation speed compared with WMS.•Robustness to noisy conditions, laser aging and circuit parameters compared with WMS. A novel direct absorption spectroscopy gas sensing system based on end-to-end deep neural networks was proposed for measurements of gas concentration. One-dimensional convolutional neural network and deep multi-layer perceptron were explored to measure the concentrations of methane and acetylene. The accurate measurement results for both gases demonstrated that deep neural networks based direct absorption spectroscopy technique can be reliably applied to different gas molecules. The developed gas sensing system achieved more precise concentration retrieval compared with that of wavelength modulation spectroscopy, and fast computation speed as well as robustness to noisy conditions, laser aging and circuit parameter variation simultaneously. The combination of deep neural networks and direct absorption spectroscopy provides new ideas for the further research of gas absorption spectroscopy.
ISSN:0263-2241
1873-412X
DOI:10.1016/j.measurement.2021.109739