Detecting gas leaks using unmanned aerial vehicles

Patent metadata

Field	Value
Publication number	US-10677771-B2
Application number	US-201715800116-A
Country	US
Kind code	B2
Filing date	Nov 1, 2017
Priority date	Apr 5, 2017
Publication date	Jun 9, 2020
Grant date	Jun 9, 2020

Abstract

Methods, systems and computer program products for detecting gas leaks using a drone are provided. Aspects include capturing a first set of data regarding a presence of a gas in the geographic area while flying along the initial flight path. Aspects also include creating secondary flight paths through regions in the geographic area in which the presence of the gas exceeds a threshold amount and capturing a second set of data regarding a concentration of the gas in the one or more regions while flying along the secondary flight paths. Aspects further include capturing wind data while flying along the initial and second flight paths and creating a three-dimensional gas plume model for gas leaks identified in the geographic area based on the first set of data, the second set of data and the wind data, wherein the three-dimensional gas plume model identifies a source of the gas leaks.

First claim

What is claimed is:

1. A computer-implemented method for detecting gas leaks using a drone, the method comprising:
creating, by the drone, an initial flight path based on a three-dimensional model of a geographic area;
capturing, by the drone, a first set of data regarding a presence of a gas in the geographic area while flying along the initial flight path through the geographic area;
creating one or more secondary flight paths through one or more regions in the geographic area in which the presence of the gas exceeds a threshold amount;
capturing, by the drone, a second set of data regarding a concentration of the gas in the one or more regions while flying along the one or more secondary flight paths;
capturing, by the drone, wind data in the geographic area while flying along the initial flight path and the one or more secondary flight paths; and
creating a three-dimensional gas plume model for gas leaks identified in the geographic area based on the first set of data, the second set of data, and the wind data, wherein the three-dimensional gas plume model identifies a location of a source of the gas leaks,
wherein the first set of data is captured at a first sampling rate using a sensor, and the second set of data is captured at a second sampling rate using the sensor, the second sampling rate being greater than the first sampling rate.

2. The computer-implemented method of claim 1 , wherein the three-dimensional model of the geographic area is created based on a plurality of global positioning system (GPS) tagged images and measurements of objects in the geographic area captured by the drone.

3. The computer-implemented method of claim 2 , wherein the initial flight path includes a grid pattern through an entirety of the geographic area, wherein the grid pattern is created based on the three-dimensional model of the geographic area to avoid impact with objects in the geographic area.

4. The computer-implemented method of claim 2 , wherein the one or more secondary flight paths includes a spiral pattern through each of the one or more regions.

5. The computer-implemented method of claim 4 , wherein the spiral pattern is created based on the three-dimensional model of the geographic area to avoid impact with objects in the one or more regions.

6. The computer-implemented method of claim 1 , wherein the second set of data regarding the concentration of the gas in the geographic area includes a plurality of gas concentrations captured by a volatile organic compound (VOC) sensor disposed on the drone.

7. The computer-implemented method of claim 1 , wherein the first set of data regarding the presence of the gas in the geographic area includes a plurality of infrared images of the geographic area captured by the drone.

8. The computer-implemented method of claim 1 , wherein the initial flight path includes a grid pattern through an entirety of the geographic area, wherein the grid pattern is configured to avoid obstructions based on the three-dimensional model of the geographic area.

Assignees

• IBM

Inventors

• Dittberner Matthias
• Klein Levente
• Renwick Jason D

Classifications

• G08G5/0021

  Physics · mapped topic

• G08G5/0086

  Physics · mapped topic

• G01N33/0047 Primary

  Organic compounds · CPC title

• B64C2201/024

  Operations & Transport · mapped topic

• G08G5/0069

  Physics · mapped topic