Quantitative Natural Gas Discrimination For Pipeline Leak Detection Through Time-Series Analysis of an MOS Sensor Response
Loading...
Date
May-18
Authors
Barriault, Matthew
Montazeri, Mahyar Mohaghegh
O'Brien, Allen
Najjaran, Homayoun
Hoorfar, Mina
Journal Title
Journal ISSN
Volume Title
Publisher
CSME-SCGM
Abstract
In order to detect natural gas pipeline leaks, ethane in the natural gas must be discriminated from background methane emissions. Our gas detection apparatus is well-suited for this application due to its flexibility and low cost. We present a comparison of machine learning models for quantitative estimation of concentrations of both methane and ethane in a target gas sample, using a response over time from a single sensor in our apparatus. We also demonstrate that the use of synthetic data is very effective for training a model to discriminate between methane and ethane.
Description
Paper presented at 2018 Canadian Society of Mechanical Engineers International Congress, 27-30 May 2018.
Keywords
Microtechnology and Nanotechnology, Machine learning, Gas detection, Microfluidic, Diffusion simulation, Pipeline leak detection