Machine Learning‐Enabled Smart Gas Sensing Platform for Identification of Industrial Gases
Research output: Contribution to journal › Research article › Contributed › peer-review
Contributors
Abstract
Both ammonia and phosphine are widely used in industrial processes, and yetthey are noxious and exhibit detrimental effects on human health. Despite theremarkable progress on sensors development, there are still some limitations, forinstance, the requirement of high operating temperatures, and that most sensorsare solely dedicated to individual gas monitoring. Herein, an ultrasensitive, highlydiscriminative platform is demonstrated for the detection and identification ofammonia and phosphine at room temperature using a graphene nanosensor.Graphene is exfoliated and successfully functionalized by copper phthalocyaninederivate. In combination with highly efficient machine learning techniques, thedeveloped graphene nanosensor demonstrates an excellent gas identificationperformance even at ultralow concentrations: 100 ppb NH3(accuracy—100.0%,sensitivity—100.0%, specificity—100.0%) and 100 ppb PH3(accuracy—77.8%,sensitivity—75.0%, and specificity—78.6%). Molecular dynamics simulationresults reveal that the copper phthalocyanine derivate molecules attached to thegraphene surface facilitate the adsorption of ammonia molecules owing tohydrogen bonding interactions. The developed smart gas sensing platform pavesa path to design a highly selective, highly sensitive, miniaturized, low-powerconsumption, nondedicated, smart gas sensing system toward a wide spectrumof gases.RESEARCH ARTICLEwww.advintellsyst.comAdv. Intell. Syst.2022,4, 22000162200016 (1 of 11)© 2022 The Authors. Advanced Intelligent Systems published by Wiley-VCH GmbH
Details
Original language | English |
---|---|
Article number | 2200016 |
Number of pages | 11 |
Journal | Advanced Intelligent Systems |
Volume | 4 |
Issue number | 4 |
Publication status | Published - 2022 |
Peer-reviewed | Yes |
External IDs
ORCID | /0000-0002-4349-793X/work/142245520 |
---|---|
ORCID | /0000-0002-3007-8840/work/142247147 |
ORCID | /0000-0002-9899-1409/work/142249226 |