Heuristic based analytics for gas leak source identification

1. A method for identifying a location of a gas leak source, comprising the steps of:

obtaining gas sensor data and wind data synchronously from a gas leak detection system having a network of interconnected motes comprising gas sensors and wind sensors, with the gas sensors arranged around possible gas leak sources in a given area of interest;

identifying the location of the gas leak source using the gas sensor data and wind data; and

determining a magnitude of gas leak from the gas leak source using the location of the gas leak source and a distance d between the location of the gas leak source and a select one of the gas sensors from which the gas sensor data was obtained, wherein the method further comprises the steps of:

accumulating the gas sensor data and the wind data over a given time interval;

determining an average wind direction over the time interval using the accumulated wind data;

ranking the gas sensors using the accumulated gas sensor data based on a number of peaks the gas sensors received during the time interval; and

identifying the location of the gas leak source using back propagation along the average wind direction from a given one of the gas sensors receiving a greatest number of peaks during the time interval.

2. The method of claim 1 , further comprising the steps of:

a) obtaining peak sensor data from at least a first one of the gas sensors synchronously with the wind data from the wind sensors indicating a first wind direction at a first time t 1 ;

b) determining a direct line path along the first wind direction through the first gas sensor;

c) obtaining peak sensor data from at least a second one of the gas sensors synchronously with the wind data from the wind sensors indicating a second wind direction at a second time t 2 ;

d) determining a direct line path along the second wind direction through the second gas sensor;

e) determining an intersection point between the direct line path along the first wind direction and the direct line path along the second wind direction; and

f) identifying the location of the gas leak source using the intersection point.

3. The method of claim 2 , further comprising the steps of:

repeating the steps a-e to determine multiple intersection points; and

accumulating the intersection points to form a point cloud.

4. The method of claim 3 , further comprising the step of:

determining a centroid of the point cloud to identify the location of the gas leak source.

5. The method of claim 4 , further comprising the step of:

clustering the intersection points in the point cloud into at least one cluster.

6. The method of claim 5 , further comprising the step of:

eliminating the intersection points that lie outside of the at least one cluster.

7. The method of claim 5 , wherein the intersection points in the point cloud are clustered into multiple clusters, the method further comprising the step of:

separating the clusters based on a stability of the atmospheric conditions at different time periods.

8. The method of claim 3 , further comprising the steps of:

creating boundaries around possible gas leak source locations; and

eliminating the intersection points that lie outside of the boundaries.

9. The method of claim 3 , further comprising the steps of:

creating a heat map visually depicting a density of the intersection points; and

using the heat map to identify the location of the gas leak source based on the density of the intersection points.

10. The method of claim 1 , wherein the gas sensors are arranged in a perimeter around the possible gas leak sources, and wherein at least one of the wind sensors is located within the perimeter of the gas sensors.

11. The method of claim 10 , wherein at least one of the wind sensors is located outside of the perimeter of the gas sensors.

12. The method of claim 1 , wherein the gas sensors are selected from the group consisting of: methane gas sensors, carbon dioxide gas sensors, carbon monoxide gas sensors, and combinations thereof.

13. The method of claim 1 , wherein each of the motes comprising gas sensors has multiple gas sensors.

14. The method of claim 1 , wherein at least one of the motes is mobile.

15. A gas leak detection system, comprising:

a network of interconnected motes having gas sensors and wind sensors, with the gas sensors arranged around possible gas leak sources in a given area of interest; and

at least one processor device, coupled to a memory, the processor device being implementable to:

obtain gas sensor data and wind data synchronously from the gas sensors and wind sensors;

identify a location of a gas leak source using the gas sensor data and wind data; and

determine a magnitude of gas leak from the gas leak source using the location of the gas leak source and a distance d between the location of the gas leak source and a select one of the gas sensors from which the gas sensor data was obtained, wherein the processor device is further implementable to:

accumulate the gas sensor data and the wind data over a given time interval;

determine an average wind direction over the time interval using, the accumulated wind data;

rank the gas sensors using the accumulated gas sensor data based on a number of peaks the gas sensors received during the time interval; and

identify the location of the gas leak source using back propagation along the average wind direction from a given one of the gas sensors receiving a greatest number of peaks during the time interval.

16. The gas leak detection system of claim 15 , wherein the processor device is further implementable to:

a) obtain peak sensor data from at least a first one of the gas sensors synchronously with the wind data from the wind sensors indicating a first wind direction at a first time t 1 ;

b) determine a direct line path along the first wind direction through the first gas sensor;

c) obtain peak sensor data from at least a second one of the gas sensors synchronously with the wind data from the wind sensors indicating a second wind direction at a second time t 2 ;

d) determine a direct line path along the second wind direction through the second gas sensor;

e) determine an intersection point between the direct line path along the first wind direction and the direct line path along the second wind direction; and

f) identify the location of the gas leak source using the intersection point.

17. The gas leak detection system of claim 16 , wherein the processor device is further implementable to:

repeat the steps a-e to determine multiple intersection points; and

accumulate the intersection points to form a point cloud.

18. A non-transitory computer program product for identifying a location of a gas leak source, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to:

obtain gas sensor data and wind data synchronously from a gas leak detection system having a network of interconnected motes comprising gas sensors and wind sensors, with the gas sensors arranged around possible gas leak sources in a given area of interest;

identify the location of the gas leak source using the gas sensor data and wind data; and

determine a magnitude of gas leak from the gas leak source using the location of the gas leak source and a distance d between the location of the gas leak source and a select one of the gas sensors from which the gas sensor data was obtained, wherein the program instructions further cause the computer to:

accumulate the gas sensor data and the wind data over a given time interval;

determine an average wind direction over the time interval using the accumulated wind data;

rank the gas sensors using the accumulated gas sensor data based on a number of peaks the gas sensors received during the time interval; and

identify the location of the gas leak source using back propagation along the average wind direction from a given one of the gas sensors receiving a greatest number of peaks during the time interval.