Combined Mixed Potential Electrochemical Sensors and Artificial Neural Networks for the Quantificationand Identification of Methane in Natural Gas Emissions Monitoring. Issue 9 (16th September 2021)

• Record Type: Journal Article
• Authors: Halley, Sleight; Tsui, Lok-kun; Garzon, Fernando
• Is Part Of: Journal of the Electrochemical Society. Volume 168:Issue 9(2021)
• Publication Date: 2021-09-16
• Subjects: Electrochemistry -- Periodicals; 541.3705
• DOI: 10.1149/1945-7111/ac2465
• Languages: English
• ISSNs: 0013-4651

Abstract

Abstract : Sensors capable of quantifying methane concentration and discriminating between possible sources are needed for natural gas leak detection where multiple spatially overlapping sources including wetlands and agriculture may be present. We report on the fabrication by an additive manufacturing process of a four electrode La0.87 Sr0.13 CrO3, Indium Tin Oxide (In2 O3 90 wt%, SnO2 10 wt%), Au, Pt mixed potential electrochemical sensor using yttria-stabilized zirconia (YSZ) as a solid electrolyte to natural gas detection. Artificial neural networks (ANNs) are used to automatically decode the possible source and concentration of methane. The ANNs trained on sensor data are capable of correctly discriminating between three sources of methane emissions from simulated mixtures of emissions from cattle, wetlands, or natural gas with >98% accuracy. Quantification error for methane in mixtures of CH4 in air, CH4 + NH3 in air, and simulated natural gas is less than 1.5% ppm when a two-temperature dataset is employed.