Chemical Discrimination in Turbulent Gas Mixtures with MOX Sensors Validated by Gas Chromatography-Mass Spectrometry

Abstract

Chemical detection systems based on chemo-resistive sensors usually include a gas chamber to control the sample air flow and to minimize turbulence. However, such a kind of experimental setup does not reproduce the gas concentration fluctuations observed in natural environments and destroys the spatio-temporal information contained in gas plumes. Aiming at reproducing more realistic environments, we utilize a wind tunnel with two independent gas sources that get naturally mixed along a turbulent flow. For the first time, chemo-resistive gas sensors are exposed to dynamic gas mixtures generated with several concentration levels at the sources. Moreover, the ground truth of gas concentrations at the sensor location was estimated by means of gas chromatography-mass spectrometry. We used a support vector machine as a tool to show that chemo-resistive transduction can be utilized to reliably identify chemical components in dynamic turbulent mixtures, as long as sufficient gas concentration coverage is used. We show that in open sampling systems, training the classifiers only on high concentrations of gases produces less effective classification and that it is important to calibrate the classification method with data at low gas concentrations to achieve optimal performance.

Exploiting plume structure to decode gas source distance using metal-oxide gas sensors

“…Only small numbers of bouts were detected on the three outermost boards on either side (no. 1, 2, 3 and 7, 8,9). This observation indicates that the region of plume dispersal was mainly limited to a region central to the wind tunnel (see also [7]).…”

“…S6A), although the measure is very sensitive to noise in when the total bout count is low, e.g. close to the walls of the wind tunnel (boards 1, 2, 3 and 7, 8,9). Likewise, the standard deviation of bout counts over trials can be replaced by the standard deviation of inter-bout intervals in a trial, which is minimal near the centreline of the plume (Fig.…”

Reservoir computing compensates slow response of chemosensor arrays exposed to fast varying gas concentrations in continuous monitoring

“…Therefore, algorithms based on RC are better suited for open sampling systems, in which the sensors are exposed directly to gas plumes in a turbulent environment, or continuous monitoring and alarm applications, in which large number of volatiles are expected to fluctuate irregularly [47,48]. Previous experimental protocols in open sampling systems also assume control of the gas onset, which happens at specific times from the beginning of the measurement [49,50]. A calibration model based on RC would be sensitive to changes in the sample composition at all times and to turbulence.…”

Online decorrelation of humidity and temperature in chemical sensors for continuous monitoring

“…Additionally, humidity sensors are extremely appealing due to a high correlation between humidity levels and human perception of air quality [45,46]. Thus, when combined with other techniques [18,35,47,27,48,49], our model is likely to significantly enhance the performance of chemical detection systems, as for instance of home monitoring tasks. Our contribution thus emphasizes the importance of simultaneous recordings of humidity and temperature, and that their use is computationally amenable in sensor boards using low-energy micro-controllers.…”