A sensor for nuisance sewer gas monitoring

Montazeri, Mahyar Mohaghegh; Vries, Niels de; Mehrabi, Pouria; Kim, Eujin; O’Brien, Allen; Najjaran, Homayoun; Hoorfar, Mina; Kadota, Paul

doi:10.1109/icsens.2017.8234327

Cited by 5 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is made easier by the fact that Figaro manufactures sensors with similar dimensions, but for a variety of target gases. Parallel work in our lab has demonstrated the suitability of this apparatus for nuisance sewer gas detection [2], wine identification [3], and breath analysis. Its small size enables it to be used for both stationary and mobile applications, which is extremely beneficial in the context of pipeline leak detection, where both types of devices may be needed, depending on the individual situation.…”

Section: Sensing Apparatus and Data Collectionmentioning

confidence: 94%

See 1 more Smart Citation

Quantitative Natural Gas Discrimination For Pipeline Leak Detection Through Time-Series Analysis of an MOS Sensor Response

Barriault¹,

Montazeri²,

O’Brien³

et al. 2018

Progress in Canadian Mechanical Engineering

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Sensing Apparatus and Data Collectionmentioning

confidence: 94%

“…Future work will also include the extension of the algorithms described here to other projects in our lab, as described above [2] [3]. In addition, we will be investigating a variant of the RNN called the long short-term memory (LSTM) network, which tends to learn longer-term dependencies better than regular RNNs [10].…”

Section: Future Workmentioning

confidence: 99%

Quantitative Natural Gas Discrimination For Pipeline Leak Detection Through Time-Series Analysis of an MOS Sensor Response

Barriault¹,

Montazeri²,

O’Brien³

et al. 2018

Progress in Canadian Mechanical Engineering

Self Cite

View full text Add to dashboard Cite

show abstract

“…Hydrogen is a light and odorless gas; it is challenging to determine the concentration in the mixture of HENG in real time using commercial sensors [ 35 ]. The use of a microfluidic channel for the detection of gases based on adsorption/desorption phenomena provides the apparatus with enough delay in the diffusion time and, consequently, in the response time to differentiate between various gases [ 15 , 28 , 36 ]. The schematic diagram of the experimental sensing apparatus is illustrated in Figure 2 .…”

Section: Experimental Verificationmentioning

confidence: 99%

“…Based on a previous study to maximize the selectivity between VOCs, the channel length was set to 30 mm, with a width of 3 mm and a height of 1 mm. As reported in previous and parallel works done by our research group, these microchannel-MOS gas detectors can provide specific patterns for various gases and are used in several gas detection applications, such as wine identification, natural gas detection, hydrogen sulfide monitoring in sewer systems, and differentiating between VOCs [ 15 , 28 , 36 , 38 ].…”

Section: Experimental Verificationmentioning

confidence: 99%

Investigation of a Sparse Autoencoder-Based Feature Transfer Learning Framework for Hydrogen Monitoring Using Microfluidic Olfaction Detectors

Mirzaei

Ramezankhani

Earl

et al. 2022

Sensors

View full text Add to dashboard Cite

Alternative fuel sources, such as hydrogen-enriched natural gas (HENG), are highly sought after by governments globally for lowering carbon emissions. Consequently, the recognition of hydrogen as a valuable zero-emission energy carrier has increased, resulting in many countries attempting to enrich natural gas with hydrogen; however, there are rising concerns over the safe use, storage, and transport of H2 due to its characteristics such as flammability, combustion, and explosivity at low concentrations (4 vol%), requiring highly sensitive and selective sensors for safety monitoring. Microfluidic-based metal–oxide–semiconducting (MOS) gas sensors are strong tools for detecting lower levels of natural gas elements; however, their working mechanism results in a lack of real-time analysis techniques to identify the exact concentration of the present gases. Current advanced machine learning models, such as deep learning, require large datasets for training. Moreover, such models perform poorly in data distribution shifts such as instrumental variation. To address this problem, we proposed a Sparse Autoencoder-based Transfer Learning (SAE-TL) framework for estimating the hydrogen gas concentration in HENG mixtures using limited datasets from a 3D printed microfluidic detector coupled with two commercial MOS sensors. Our framework detects concentrations of simulated HENG based on time-series data collected from a cost-effective microfluidic-based detector. This modular gas detector houses metal–oxide–semiconducting (MOS) gas sensors in a microchannel with coated walls, which provides selectivity based on the diffusion pace of different gases. We achieve a dominant performance with the SAE-TL framework compared to typical ML models (94% R-squared). The framework is implementable in real-world applications for fast adaptation of the predictive models to new types of MOS sensor responses.

show abstract

“…calibration), portability, sensitivity, and selectivity. There has been recent development of microfluidic-based gas detectors with the goal of overcoming these constraints; these detectors have shown promise output in a number of applications, such as the monitoring of nuisance sewage gases [9] and the detection of tetrahydrocannabinol [10] in exhaled air. The following sources demonstrate that microfluidic-based gas detectors prove to be advantageous and are able to overcome the aforementioned limitations: Hossein-Babaei et al demonstrated a gas analyser which was a superior alternative to GC and MS that was robust, inexpensive, portable, and adaptable in its use case selection [11].…”

Section: Introductionmentioning

confidence: 99%

Emerging trends in microfluidic-assisted nanomaterial synthesis for their high-resolution gas sensing applications

et al. 2023

View full text Add to dashboard Cite

The proliferation of point-of-use (PoU) or point-of-care (PoC) detecting technologies has resulted in a significant expansion of miniaturized sensors that were indispensable in the battle against pollution, arising contaminants, and pandemics. These sensors enable immediate identification of gases and airborne pathogens. Notwithstanding, the economical fabrication of miniature gas sensors, while maintaining their selectivity, sensitivity, and response time, presents a significant challenge. To address the aforementioned constraints, microfluidic technology has been utilized as a potential solution, rendering it a highly favorable option for PoU or PoC applications. Microfluidic-based gas sensors, while showing promising results, are still in their infancy. This review focuses on emerging trends in the synthesis of novel materials and their application is microfluidic gas sensors. Further, the challenges pertaining to this sensing and future perspective with the possible solution have been discussed.

show abstract

A sensor for nuisance sewer gas monitoring

Cited by 5 publications

References 7 publications

Quantitative Natural Gas Discrimination For Pipeline Leak Detection Through Time-Series Analysis of an MOS Sensor Response

Quantitative Natural Gas Discrimination For Pipeline Leak Detection Through Time-Series Analysis of an MOS Sensor Response

Investigation of a Sparse Autoencoder-Based Feature Transfer Learning Framework for Hydrogen Monitoring Using Microfluidic Olfaction Detectors

Emerging trends in microfluidic-assisted nanomaterial synthesis for their high-resolution gas sensing applications

Contact Info

Product

Resources

About