Method and system for analyzing gas leak based on machine learning
Abstract
Embodiments of the present invention provide a system for estimating a location of a gas leak, based on machine learning from forward gas concentration data provided by an analog or scale model including a gas source. The system improves significantly over previous systems by providing high quality, physically accurate forward modeling data inexpensively. During operation, the system configures an aerosol source at a first location to emit a gaseous aerosol. The system then configures a laser source to illuminate the aerosol with a laser sheet. The system may then obtain an image of a reflection of the laser sheet from the aerosol. The system may then analyze the image to quantify a three-dimensional concentration distribution of the aerosol. The system may then estimate, based on solving an inverse problem and an observed second gas concentration, a second location of a second gas source.
- Inventors:
- Issue Date:
- Research Org.:
- Palo Alto Research Center Incorporated, Palo Alto, CA (United States)
- Sponsoring Org.:
- USDOE Advanced Research Projects Agency - Energy (ARPA-E)
- OSTI Identifier:
- 1464218
- Patent Number(s):
- 10031040
- Application Number:
- 15/472,018
- Assignee:
- Palo Alto Research Center Incorporated (Palo Alto, CA)
- Patent Classifications (CPCs):
-
G - PHYSICS G01 - MEASURING G01M - TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES
G - PHYSICS G01 - MEASURING G01N - INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- DOE Contract Number:
- AR0000542
- Resource Type:
- Patent
- Resource Relation:
- Patent File Date: 2017 Mar 28
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING; 03 NATURAL GAS
Citation Formats
Smith, Clinton J., Saha, Bhaskar, Beck, Victor A., and Schwartz, David E. Method and system for analyzing gas leak based on machine learning. United States: N. p., 2018.
Web.
Smith, Clinton J., Saha, Bhaskar, Beck, Victor A., & Schwartz, David E. Method and system for analyzing gas leak based on machine learning. United States.
Smith, Clinton J., Saha, Bhaskar, Beck, Victor A., and Schwartz, David E. Tue .
"Method and system for analyzing gas leak based on machine learning". United States. https://www.osti.gov/servlets/purl/1464218.
@article{osti_1464218,
title = {Method and system for analyzing gas leak based on machine learning},
author = {Smith, Clinton J. and Saha, Bhaskar and Beck, Victor A. and Schwartz, David E.},
abstractNote = {Embodiments of the present invention provide a system for estimating a location of a gas leak, based on machine learning from forward gas concentration data provided by an analog or scale model including a gas source. The system improves significantly over previous systems by providing high quality, physically accurate forward modeling data inexpensively. During operation, the system configures an aerosol source at a first location to emit a gaseous aerosol. The system then configures a laser source to illuminate the aerosol with a laser sheet. The system may then obtain an image of a reflection of the laser sheet from the aerosol. The system may then analyze the image to quantify a three-dimensional concentration distribution of the aerosol. The system may then estimate, based on solving an inverse problem and an observed second gas concentration, a second location of a second gas source.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Tue Jul 24 00:00:00 EDT 2018},
month = {Tue Jul 24 00:00:00 EDT 2018}
}
Works referenced in this record:
Gas-Mapping 3D Imager Measurement Techniques and Method of Data Processing
patent-application, April 2017
- Thorpe, Michael; Kreitinger, Aaron; Crouch, Stephen
- US Patent Document 15/285787; 20170097274
High-Sensitivity Gas-Mapping 3D Imager and Method of Operation
patent-application, April 2017
- Kreitinger, Aaron; Thorpe, Michael
- US Patent Application 15/285550; 20170097302
Laser Scanning Leak Detection and Visualization Apparatus
patent-application, October 2017
- Miranda, John Armando
- US Patent Application 15/471505; 20170284891
Hydrocarbon Leak Imaging and Quantification Sensor
patent-application, November 2017
- Waxman, Allen M.; Bylsma, Jason M.; Vanitses, Allan
- US Patent Application 15/598052; 20170336281