US 12,112,392 B2
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 Nov. 30, 2023, as Appl. No. 18/525,474.
Application 18/525,474 is a continuation of application No. 18/223,492, filed on Jul. 18, 2023, granted, now 11,861,753.
Application 18/223,492 is a continuation in part of application No. 18/205,461, filed on Jun. 2, 2023, granted, now 11,887,203.
Application 18/223,492 is a continuation in part of application No. 18/205,465, filed on Jun. 2, 2023, granted, now 11,810,216, issued on Nov. 7, 2023.
Application 18/205,461 is a continuation of application No. 18/104,746, filed on Feb. 1, 2023, granted, now 11,727,519, issued on Aug. 15, 2023.
Application 18/205,465 is a continuation of application No. 18/104,746, filed on Feb. 1, 2023, granted, now 11,727,519, issued on Aug. 15, 2023.
Prior Publication US 2024/0257285 A1, Aug. 1, 2024
Int. Cl. G06Q 50/26 (2024.01); G01W 1/10 (2006.01)
CPC G06Q 50/26 (2013.01) [G01W 1/10 (2013.01)] 21 Claims
OG exemplary drawing
 
1. An event aborting method for aborting forthcoming events at a monitored site, the event aborting method comprising:
providing a first air quality monitor comprising:
a first event monitor responsive to events at the monitored site;
detecting at least one event at the monitored site with the first event monitor;
generating a first set of event parameters indicative of occurrence of the at least one event;
transmitting the first set of event parameters to a first server;
providing a supervisory control and data acquisition system (SCADA system) at the monitored site;
sensing a set of SCADA parameters comprising:
a physical factor of a component at the monitored site; and
an operational factor of the component;
transmitting the set of SCADA parameters to the first server;
training an emission-prediction-machine-learning model to create a trained emission-prediction-machine-learning model with:
the first set of event parameters; and
the set of SCADA parameters,
monitoring over a predefined time period, the first set of event parameters and the set of SCADA parameters to create a refined first set of event parameters and a refined set of SCADA parameters;
refining, iteratively and over the predefined time period, the trained emission-prediction-machine-learning model with the refined first set of event parameters and the refined set of SCADA parameters to:
create a refined emission-prediction-machine-learning model, wherein the refined emission-prediction-machine-learning model generates:
a refined predicted emission parameter corresponding to the component;
predicting emissions fugitively associated with the component with the refined predicted emission parameter;
establishing a set of rules limiting the emissions fugitively associated with the component;
determining a forthcoming breach of the set of rules;
determining at least one action abortive of the forthcoming breach of the set of rules; and
implementing the at least one action abortive of the forthcoming breach with the SCADA system.