US 11,887,203 B1
Air quality monitors minimization system and methods
William J. Foiles, Denver, CO (US); Nathan C. Eichenlaub, Denver, CO (US); Kieran J. Lynn, Denver, CO (US); and Ray K. Mistry, Denver, CO (US)
Assigned to PROJECT CANARY, PBC, Denver, CO (US)
Filed by Project Canary, PBC, Denver, CO (US)
Filed on Jun. 2, 2023, as Appl. No. 18/205,461.
Application 18/205,461 is a continuation of application No. 18/104,746, filed on Feb. 1, 2023, granted, now 11,727,519.
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 50/26 (2012.01); G01W 1/10 (2006.01)
CPC G06Q 50/26 (2013.01) [G01W 1/10 (2013.01)] 20 Claims
OG exemplary drawing
 
1. An emission location method for identifying an emission source of a target substance at a site, the emission location method comprising:
providing a first air quality monitor comprising:
a first sensor responsive to an emissions event of the target substance; and
a first location at which the first air quality monitor is located on the site;
sensing, by the first air quality monitor, a first set of attached parameters at the first location;
transmitting the first set of attached parameters to a first server;
providing a supervisory control and data acquisition system (SCADA system) at the site, the SCADA system configured to:
supervise a physical factor and an operational factor of at least a first device at the site; and
acquire the physical factor and the operational factor from the first device at the site;
acquiring, with the SCADA system, a set of SCADA data from the first device;
transmitting the set of SCADA data to the first server;
training an emissions-location machine learning model with:
the first server,
the first set of attached parameters sensed by the first air quality monitor, and the set of SCADA data,
wherein the emissions-location machine learning model generates a first trained emissions-model parameter;
generating an emissions-simulation model of a plume of the target substance using the first trained emissions-model parameter;
monitoring, over a predefined time period and with the emissions-simulation model, the set of SCADA data, and the first set of attached parameters;
refining, iteratively and over the predefined time period, the emissions-simulation model based on monitoring, to a refined emissions-simulation model; and
locating the emission source of the target substance at the site with:
the refined emissions-simulation model,
the set of SCADA data, and
the first trained emissions-model parameter.