Gas differentiating sensor suite

12216,103

17/735451

May 03, 2022

A gas leak detection system that combines sensor units having an array of sensors that detect natural gas and the volatile organic compounds and variable atmospheric conditions that confound existing gas leak detection methods, a specially designed sensor housing that limits the variability of those atmospheric conditions, and a machine learning-enabled process that uses the wide array of sensor data to differentiate between natural gas leaks and other confounding factors. Multiple low-cost sensor units can be used to monitor gas concentrations at multiple locations across a site (e.g., a well pad or other oil or natural gas facility), enabling the gas leak detection system to model gas leak emission rates in two- or three-dimensional space to reveal the most likely origin of the gas leak.

Earthview Corporation (Longmont, CO, US)

Earthview Corporation (Dallas, TX, US)

1. A gas leak detection system, comprising: a sensor suite for sampling an air sample at a site and outputting observed sensor data, the sensor suite comprising: one or more environmental condition sensors for measuring the temperature and humidity of the air sample; and an array of metal oxide sensors, each of the metal oxide sensors having different sensitivities to methane and different sensitivities to volatile organic compounds; non-transitory computer readable storage media that stores a gas leak detection model, generated by a machine learning algorithm trained by exposing each of the metal oxide sensors to known concentrations of methane and volatile organic compounds having measured temperatures and measured humidity; and a processing unit that: models a relationship between measured temperature and humidity and sensor data output by each of the metal oxide sensors; identifies the temperature and humidity of the air sample; identifies a background methane concentration calculated based on a wind direction at the site; uses the gas leak detection model to generate predicted sensor data for a baseline air sample having only the background methane concentration at the temperature and humidity of the air sample; compares the observed sensor data output by each of the metal oxide sensors to the predicted sensor data for the baseline air sample having only the background methane concentration; and uses the gas leak detection model to calculate a methane concentration of the air sample based on the comparison of the sensor data output by each of the metal oxide sensors to the predicted sensor data for the baseline air sample having only the background methane concentration.

2. The system of claim 1 , further comprising: a sensor chamber enclosing the sensor suite; an intake tube and an intake pump for introducing the air sample into the sensor chamber; and an exhaust tube for evacuating the chamber, wherein the metal oxide sensors heat the air sample inside the sensor chamber.

3. The system of claim 2 , wherein: the metal oxide sensors each include a heating plate for heating the metal oxide sensor; the sensor suite includes a sensor housing temperature sensor that measures an external temperature of at least one of the metal oxide sensors; and the observed sensor data includes the external temperature of the at least one metal oxide sensor.

4. The system of claim 3 , further comprising: a heater circuit that provides a voltage to the heating plate of the at least one metal oxide sensor; and a controller that outputs sensor control signals to the sensor heater circuit to heat and cool the at least one metal oxide sensor, wherein the observed sensor data includes data indicative of the output of the at least one metal oxide sensor at a plurality of external temperatures.

5. The system of claim 1 , wherein the one or more environmental condition sensors comprise two or more temperature and humidity sensors, each of the temperature and humidity sensors having different sensitivities and different response times.

6. The system of claim 1 , wherein the array of metal oxide sensors comprises a methane-sensitive metal oxide sensor, a volatile organic compound-sensitive metal oxide sensor, and a volatile organic compound-filtered metal oxide sensor.

7. The system of claim 6 , wherein the metal oxide sensors are n-type metal oxide sensors.

8. The system of claim 1 , wherein the array of metal oxide sensors comprises a p-type metal oxide sensor.

9. The system of claim 1 , wherein the sensor suite further comprises a particulate counter or a carbon monoxide sensor.

10. The system of claim 1 , comprising: a plurality of sensor units, each including the sensor suite, deployed at a site; an anemometer that senses wind speed and wind direction at the site; and a remote server that receives measured methane concentrations from the plurality of sensor units and uses a gas transport model to estimate methane emissions rates at each of a plurality of location at the site most likely to cause the measured methane concentrations at each of the sensor units.

11. The system of claim 1 , wherein the processing unit: measures the methane concentration of the air sample based on the comparison of the sensor data output by each of the metal oxide sensors to the predicted sensor data; and measures a concentration of one or more volatile organic compounds based on the comparison of the sensor data output by each of the metal oxide sensors to the predicted sensor data for the baseline air sample having only the background methane concentration.

12. A gas leak detection method, comprising: observing sensor data at a site, by a sensor suite for sampling an air sample comprising one or more environmental condition sensors for measuring the temperature and humidity of the air sample and an array of metal oxide sensors, each of the metal oxide sensors having different sensitivities to methane and different sensitivities to volatile organic compounds; storing a gas leak detection model, generated by a machine learning algorithm trained by exposing each of the metal oxide sensors and each of the one or more environmental condition sensors to known concentrations of methane and volatile organic compounds having measured temperatures and measured humidity; modeling a relationship between measured temperature and humidity and sensor data output by each of the metal oxide sensors; identifying the temperature and humidity of the air sample; identifying a background methane concentration calculated based on a wind direction at the site; using the gas leak detection model to generate predicted sensor data for a baseline air sample having only the background methane concentration at the temperature and humidity of the air sample; comparing the observed sensor data output by each of the metal oxide sensors to the predicted sensor data for the baseline air sample having only the background methane concentration; and using the gas leak detection model to calculate a methane concentration of the air sample based on the comparison of the sensor data output by each of the metal oxide sensors to the predicted sensor data for the baseline air sample having only the background methane concentration.

13. The method of claim 12 , wherein the sensor suite is enclosed in a sensor chamber and the metal oxide sensors heat the air sample inside the sensor chamber.

14. The method of claim 13 , wherein: the metal oxide sensors each include a heating plate for heating the metal oxide sensor; the sensor suite includes a sensor housing temperature sensor that measures an external temperature of at least one of the metal oxide sensors; and the observed sensor data includes the external temperature of the at least one metal oxide sensor.

15. The method of claim 14 , further comprising: providing, by a heater circuit, a voltage to the heating plate of the at least one metal oxide sensor; and outputting sensor control signals to the sensor heater circuit to heat and cool the at least one metal oxide sensor, wherein the observed sensor data includes data indicative of the output of the at least one metal oxide sensor at a plurality of external temperatures.

16. The method of claim 12 , wherein the one or more environmental condition sensors comprise two or more temperature and humidity sensors, each of the temperature and humidity sensors having different sensitivities and different response times.

17. The method of claim 12 , wherein the array of metal oxide sensors comprises a methane-sensitive metal oxide sensor, a volatile organic compound-sensitive metal oxide sensor, and a volatile organic compound-filtered metal oxide sensor.

18. The method of claim 17 , wherein the metal oxide sensors are n-type metal oxide sensors.

19. The method of claim 12 , wherein the array of metal oxide sensors comprises a p-type metal oxide sensor.

20. The method of claim 12 , wherein the sensor suite further comprises a particulate counter or a carbon monoxide sensor.

21. The method of claim 12 , further comprising: observing methane concentrations by a plurality of sensor units, each including the sensor suite, deployed at a site; sensing, by an anemometer, wind speed and wind direction at the site; and using a gas transport model to estimate methane emissions rates at each of a plurality of location at the site most likely to cause the measured methane concentrations at each of the sensor units.

10031040 July 2018 Smith
10168276 January 2019 Stambaugh
10386258 August 2019 Steele
10948471 March 2021 MacMullin
10962437 March 2021 Nottrott
2004/0215402 October 2004 Hsiung
2014/0032129 January 2014 Rella
2017/0026722 January 2017 Schwartz
2018/0156766 June 2018 Zeng
2018/0225426 August 2018 Murthy
2018/0321208 November 2018 Bai
2019/0285504 September 2019 Muralidhar
2020/0019168 January 2020 Guzman
2020/0232959 July 2020 Armitage
2020/0333307 October 2020 Armitage
2021/0102925 April 2021 Gogoana
2021/0109049 April 2021 Potyrailo
2022/0366108 November 2022 Filippov

Wolfrum et al., “Metal oxide sensor arrays for the detection, differentiation, and quantification of volatile organic compounds at sub-parts-per-million concentration levels”, Sensors and Actuators B, vol. 115, Nov. 2, 2005, pp. 322-329. cited by applicant
Bicelli et al., “Model and Experimental Characterization of the Dynamic Behavior of Low-Power Carbon Monoxide MOX Sensors Operated with Pulsed Temperature Profiles”, IEEE Transactions on Instrumentation and Measurements. vol. 58, No. 5, May 2009, pp. 1324-1332. cited by applicant
Zhu et al., “An ultra-low power switch array of temperature and humidity sensors with direct digital output”, Transducers, Jun. 16, 2013, pp. 108-111. cited by applicant
International Search Report and Written Opinion; International Application No. PCT/US2022/027487; International Filing Date: May 3, 2022; 29 pages. cited by applicant
Hirst et al., Locating and quantifying gas emission sources using remotely obtained concentration data, Atmospheric Environment 74, 2013, pp. 141-158, www.elsevier.com/locate/atmosenv. cited by applicant
Bennetts et al., Creating true gas concentration maps in presence of multiple heterogeneous gas sources, IEEE Sensors, 2012. cited by applicant
Allen et al., Improving pollutant source characterization by better estimating wind direction with a genetic algorithm, Atmospheric Environment 41, 2007, pp. 2283-2289, www.elsevier.com/locate/atmosenv. cited by applicant
Bennetts et al., Robot Assisted Gas Tomography—Localizing Methane Leaks in Outdoor Environments, IEEE ICRA, 2014, pp. 6362-6367. cited by applicant
Haupt et al., Validation of a Receptor-Dispersion Model Coupled with Genetic Algorithm Using Synthetic Data, American Meteorological Society, vol. 45, 2006, pp. 476-490. cited by applicant
Long et al., Assessing sensitivity of source term estimation, Atmospheric Environment 44, 2010, pp. 1558-1567, www.elsevier.com/locate/atmosenv. cited by applicant

edspgr.12216103