Detecting Gas Vapor Leaks Using Uncalibrated Sensors

TL;DR

This paper presents a method for detecting gas vapor leaks using uncalibrated sensors and deep neural networks, comparing energy-efficient AddNet, GAN-enhanced, and conventional CNN approaches on time-series sensor data.

Contribution

It introduces the use of uncalibrated sensors with deep neural networks, including AddNet and GAN-based models, for improved leak detection without sensor calibration.

Findings

AddNet offers energy-efficient detection.

GAN improves classifier generalization.

CNN serves as a baseline for comparison.

Abstract

Chemical and infra-red sensors generate distinct responses under similar conditions because of sensor drift, noise or resolution errors. In this work, we use different time-series data sets obtained by infra-red and E-nose sensors in order to detect Volatile Organic Compounds (VOCs) and Ammonia vapor leaks. We process time-series sensor signals using deep neural networks (DNN). Three neural network algorithms are utilized for this purpose. Additive neural networks (termed AddNet) are based on a multiplication-devoid operator and consequently exhibit energy-efficiency compared to regular neural networks. The second algorithm uses generative adversarial neural networks so as to expose the classifying neural network to more realistic data points in order to help the classifier network to deliver improved generalization. Finally, we use conventional convolutional neural networks as a baseline method and compare their performance with the two aforementioned deep neural network algorithms in order to evaluate their effectiveness empirically.