IP Library Granted Patent US 12,631,513
Granted Patent B2
US 12,631,513 · App. 17/738,533 · Granted May 19, 2026

Technologies for improved visualization of gas leak detection data

Inventors: Ajay Nahata (San Jose, CA); J. Brian Leen (Sunnyvale, CA)
Assignee: ABB Schweiz AG
G01M3/16
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,631,513
App. No.
17/738,533
Granted
May 19, 2026
Kind
B2
Abstract

A visualization system for visualizing gas leak detection data including a processor in communication with at least one memory device is provided herein. The processor is configured to receive, from one or more sensors, gas measurement data for a plurality of measurement locations within a survey area; receive, from the at least one memory device, a geographic representation of the survey area; determine, based upon the gas measurement data, estimated gas source locations of the plurality of measurement locations; and apply a smoothing algorithm to the estimated gas source locations to create a multi-dimensional density plot.

Claims (38)

1 . A visualization system for visualizing gas leak detection data including a processor in communication with at least one memory device, wherein the processor is configured to:

receive, from the at least one memory device, a geographic representation of a survey area;

receive, from one or more sensors that comprise one or more gas concentration sensors, gas measurement data for a plurality of measurement locations within the survey area, wherein the gas measurement data includes gas concentration data measured by the one or more gas concentration sensors;

determine, based upon the gas measurement data and the geographic representation, estimated gas source locations of the plurality of measurement locations, wherein the estimated gas source locations include one or more measurement locations of the plurality of measurement locations where the gas concentration data is at or above a threshold; and

utilize, by a smoothing algorithm, point density data of the estimated gas source locations to create a multi-dimensional density plot.

2 . The visualization system of claim 1 , wherein the processor is further configured to generate a graphic comprising the multi-dimensional density plot superimposed on the geographic representation of the survey area.

3 . The visualization system of claim 1 , wherein the one or more sensors are moved through the survey area, and wherein the one or more sensors perform gas measurements at the plurality of measurement locations as the one or more sensors are moved within the survey area.

4 . The visualization system of claim 1 , wherein the gas measurement data further includes at least one of global positioning system (GPS) data associated with the gas concentration data and wind velocity data associated with the gas concentration data.

5 . The visualization system of claim 1 , wherein the smoothing algorithm comprises a kernel density estimation (KDE) algorithm having a kernel function and a bandwidth.

6 . The visualization system of claim 5 , wherein the kernel function is a two-dimensional Gaussian function.

7 . The visualization system of claim 5 , wherein the processor is further configured to:

adjust the kernel function based on a local density of the estimated gas source locations; and/or

adjust the kernel function based on an uncertainty value associated with the estimated gas source locations.

8 . The visualization system of claim 7 , wherein the uncertainty value represents a variability of wind measurements associated with the estimated gas source locations.

9 . The visualization system of claim 5 , wherein the bandwidth is a fixed bandwidth.

10 . The visualization system of claim 5 , wherein the bandwidth differs between an x dimension and a y dimension.

11 . The visualization system of claim 5 , wherein the bandwidth is varied spatially to minimize an error value associated with a cost function, and wherein the cost function is a mean integrated squared error.

12 . The visualization system of claim 1 , wherein the processor is further configured to:

weight each estimated gas source location prior to applying the smoothing algorithm to the respective estimated gas source locations.

13 . The visualization system of claim 12 , wherein the weighting of each estimated gas source location is a function of the gas measurement data associated with each estimated gas source location.

14 . The visualization system of claim 1 , wherein the processor is further configured to:

detect sampling bias by applying k-fold validation to the estimated gas source locations.

15 . The visualization system of claim 14 , wherein the processor is further configured to:

remove the sampling bias by calculating a likelihood that a kernel location was over-sampled and normalizing for calculated sample density.

16 . The visualization system of claim 1 , wherein the geographic representation comprises at least one of a satellite image and a street map.

17 . The visualization system of claim 1 , wherein the multi-dimensional density plot includes at least one of a plurality of colors and a plurality of patterns indicating different likelihoods of a presence of a gas source, and wherein transparent regions of the multi-dimensional density plot indicate the lowest likelihood of the presence of a gas source.

18 . A computer-implemented method for visualizing gas leak detection data, the computer-implemented method performed by a visualization system including a processor in communication with at least one memory device, the computer-implemented method comprising:

receiving, from the at least one memory device, a geographic representation of a survey area;

receiving, from one or more sensors that comprise one or more gas concentration sensors, gas measurement data for a plurality of measurement locations within the survey area, wherein the gas measurement data includes gas concentration data measured by the one or more gas concentration sensors;

determining, based upon the gas measurement data and the geographic representation, estimated gas source locations of the plurality of measurement locations, wherein the estimated gas source locations include one or more measurement locations of the plurality of measurement locations where the gas concentration data is at or above a threshold; and

utilizing, by a smoothing algorithm, point density data of the estimated gas source locations to create a multi-dimensional density plot.

19 . The computer-implemented method of claim 18 further comprising:

generating a graphic comprising the multi-dimensional density plot superimposed on the geographic representation of the survey area.

20 . A non-transitory computer-readable media having computer-executable instructions embodied thereon, wherein when executed by a visualization system including a processor in communication with at least one memory device, the computer-executable instructions cause the processor to:

receive, from the at least one memory device, a geographic representation of a survey area;

receive, from one or more sensors that comprise one or more gas concentration sensors, gas measurement data for a plurality of measurement locations within the survey area, wherein the gas measurement data includes gas concentration data measured by the one or more gas concentration sensors;

determine, based upon the gas measurement data and the geographic representation, estimated gas source locations of the plurality of measurement locations, wherein the estimated gas source locations include one or more measurement locations of the plurality of measurement locations where the gas concentration data is at or above a threshold; and

utilize, by a smoothing algorithm, point density data of the estimated gas source locations to create a multi-dimensional density plot.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 12, 2023
From: NAHATA, AJAY
To: ABB SCHWEIZ AG
Reel/Frame 064221/0601 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 12, 2023
From: LEEN, J. BRIAN
To: ABB SCHWEIZ AG
Reel/Frame 064221/0765 →
Continuity (2)
Provisional Application 63185344 · May 6, 2021
Related Publication 20220357231A1 · Nov 10, 2022
References Cited (13)
US 7082370B2 · Ardo et al. · 2006 [cited by applicant]
US 7385681B2 · Ninomiya et al. · 2008 [cited by applicant]
US 10634575B2 · Miranda · 2020 [cited by examiner]
US 10928268B2 · Mcneil · 2021 [cited by applicant]
US 20200116583A1 · Hedberg · 2020 [cited by applicant]
US 20210140934A1 · Smith · 2021 [cited by examiner]
CN 107917341A · 2018 [cited by applicant]
WO 2020206008A1 · 2020 [cited by applicant]
Anthony Schenck et al (hereinafter Schenck) “ArileakSlam: Detection of Pressurized Air Leaks Using Passive Ultrasonic Sensors”, IEEE, (Oct. 27, 2019), doi: 10.1109/43011.2019.8956631, pp. 1-4, XP033685497. (Year: 2019). [cited by examiner]
Eckert-Gallup et al. (hereinafter “Eckert-Gallup”) “Kernel density estimation (KDE) with adaptive bandwidth selection for environmental contours of extreme sea states”, Oceans 2016 Monterey, IEEE, (Sep. 19, 2016), doi: … [cited by examiner]
Eckert-Gallup et al., “Kernel density estimation (KDE) with adaptive bandwidth selection for environmental contours of extreme sea states”, Oceans 2016 MTS/IEEE Monterey, IEEE, (Sep. 19, 2016), doi:10.1109/OCEANS.2016.7… [cited by applicant]
Extended European Search Report issued in European Patent Application No. 22172066.7, dated Oct. 10, 2022, 11 pages. [cited by applicant]
Schenck et al., “AirleakSlam: Detection of Pressurized Air Leaks Using Passive Ultrasonic Sensors”, 2019 IEEE Sensors, IEEE, (Oct. 27, 2019), doi:10.1109/SENSORS43011.2019.8956631, pp. 1-4, XP033685497. [cited by applicant]