Application of deep learning in quantitative analysis of the infrared spectrum of logging gas

RIS ID

143461

Publication Details

L. Song, H. Wu, Y. Yang, Q. Guo & J. Li, "Application of deep learning in quantitative analysis of the infrared spectrum of logging gas," Applied Optics, vol. 59, (17) pp. E9-E16, 2020.

Abstract

Infrared spectrum analysis technology can perform fast and nondestructive detection of gas and has been widely used in many fields. This work studies the quantitative analysis technology of the infrared spectrum based on deep learning. The experimental results show that the quantitative analysis model of logging gas established here can reach 100% recognition accuracy for elemental gas; further, the accuracy rate of spectral of mixed gas recognition reached 98%, indicating that the infrared spectrum logging gas detection model based on deep learning can quickly and accurately perform quantitative analysis of logging gas.

Please refer to publisher version or contact your library.

Share

COinS
 

Link to publisher version (DOI)

http://dx.doi.org/10.1364/AO.386639